{ "object": "list", "data": [ { "name": "OpenAI: GPT-3.5 Turbo", "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\nTraining data up to Sep 2021.", "id": "gpt-3.5-turbo", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 4000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 4000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5 } } ], "context_length": 4000, "max_model_len": 4000, "max_input_tokens": 4000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-3.5 Turbo 16k", "description": "The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Sep 2021.\nThis version has a higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.", "id": "gpt-3.5-turbo-16k", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 4 } } ], "context_length": 16000, "max_model_len": 16000, "max_input_tokens": 16000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-3.5 Turbo (older v1106)", "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\nTraining data up to Sep 2021.", "id": "gpt-3.5-turbo-1106", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 4000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 4000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 2 } } ], "context_length": 4000, "max_model_len": 4000, "max_input_tokens": 4000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4 Turbo", "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\nTraining data: up to December 2023.", "id": "gpt-4-turbo", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 10, "output": 30, "cache_read": 5.0 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 10, "output": 30, "cache_read": 5.0 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4o", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.", "id": "gpt-4o", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2.5, "output": 10, "cache_read": 1.25 } }, { "id": "azure", "name": "Azure", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4o (2024-05-13)", "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.", "id": "gpt-4o-2024-05-13", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2.5, "output": 10, "cache_read": 1.25 } }, { "id": "azure", "name": "Azure", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4o (2024-08-06)", "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format.\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.", "id": "gpt-4o-2024-08-06", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2.5, "output": 10, "cache_read": 1.25 } }, { "id": "azure", "name": "Azure", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4o (2024-11-20)", "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded files, providing deeper insights & more thorough responses.\nGPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.", "id": "gpt-4o-2024-11-20", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2.5, "output": 10, "cache_read": 1.25 } }, { "id": "azure", "name": "Azure", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4o-mini", "description": "GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.", "id": "gpt-4o-mini", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.075 } }, { "id": "azure", "name": "Azure", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4o-mini (2024-07-18)", "description": "GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.", "id": "gpt-4o-mini-2024-07-18", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.075 } }, { "id": "azure", "name": "Azure", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4.1 Nano", "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.", "id": "gpt-4.1-nano", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.025 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.025 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4.1 Nano (2025-04-14)", "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.", "id": "gpt-4.1-nano-2025-04-14", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.025 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.025 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4.1 Mini", "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.", "id": "gpt-4.1-mini", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 1.6, "cache_read": 0.1 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4.1 Mini (2025-04-14)", "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.", "id": "gpt-4.1-mini-2025-04-14", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 1.6, "cache_read": 0.1 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4.1", "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.", "id": "gpt-4.1", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8, "cache_read": 0.5 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 6 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-4.1 (2025-04-14)", "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.", "id": "gpt-4.1-2025-04-14", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8, "cache_read": 0.5 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 6 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "OpenAI: GPT-5 Nano", "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.", "id": "gpt-5-nano", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.4, "cache_read": 0.005 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.4, "cache_read": 0.005 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5 Mini", "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.", "id": "gpt-5-mini", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.25, "output": 2, "cache_read": 0.025 } }, { "id": "azure", "name": "Azure", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.2 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5", "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.", "id": "gpt-5", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.25, "output": 10, "cache_read": 0.125 } }, { "id": "azure", "name": "Azure", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 8 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5.1", "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5.", "id": "gpt-5.1", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.25, "output": 10, "cache_read": 0.125 } }, { "id": "azure", "name": "Azure", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 8 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5.2", "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.", "id": "gpt-5.2", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.25, "output": 10 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.75, "output": 14, "cache_read": 0.175 } }, { "id": "azure", "name": "Azure", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.25, "output": 10 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5.3 Codex", "description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.", "id": "gpt-5.3-codex", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.75, "output": 14, "cache_read": 0.175 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 1.75, "output": 14, "cache_read": 0.175 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5.4 Nano", "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.", "id": "gpt-5.4-nano", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.75 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.25, "cache_read": 0.02 } }, { "id": "azure", "name": "Azure", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.75 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5.4 Mini", "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.", "id": "gpt-5.4-mini", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.75, "output": 4.5, "cache_read": 0.075 } }, { "id": "azure", "name": "Azure", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3 } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: GPT-5.4", "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.", "id": "gpt-5.4", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 12 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2.5, "output": 15, "cache_read": 0.25 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 12 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "low", "medium", "high", "xhigh" ] } }, { "name": "OpenAI: GPT-5.5", "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.", "id": "gpt-5.5", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 24 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 30, "cache_read": 0.5 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 24 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "low", "medium", "high", "xhigh" ] } }, { "name": "OpenAI: GPT-5.6 Luna", "description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.", "id": "gpt-5.6-luna", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.75 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.2, "cache_read": 0.02, "cache_write_5m": 0.25 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.75 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: GPT-5.6 Terra", "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.", "id": "gpt-5.6-terra", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 9 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 12, "cache_read": 0.2, "cache_write_5m": 2.5 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 9 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: GPT-5.6 Sol", "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series, designed for the most demanding professional workloads. It is suited for complex reasoning, coding, and multimodal workflows, providing the highest level of capability and reliability at the highest price tier.", "id": "gpt-5.6-sol", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 24 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 30, "cache_read": 0.5, "cache_write_5m": 6.25 } }, { "id": "azure", "name": "Azure", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 24 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: o1", "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology.", "id": "o1", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 60, "cache_read": 7.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 60, "cache_read": 7.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: o3 Mini", "description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\nThis model supports the reasoning_effort parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\".\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.", "id": "o3-mini", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.1, "output": 4.4, "cache_read": 0.55 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.1, "output": 4.4, "cache_read": 0.55 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: o3 Mini Online", "description": "This model is combined with a powerful RAG system to provide real-time information and web search capabilities. It is designed to be used in conjunction with the o3-mini model, which is optimized for STEM reasoning tasks.\nThe o3-mini model is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.", "id": "o3-mini-online", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 5, "cache_read": 0.75 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 5, "cache_read": 0.75 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": true, "reasoning": true } }, { "name": "OpenAI: o3", "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.", "id": "o3", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 8, "cache_read": 1.0 } }, { "id": "azure", "name": "Azure", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 6 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: o3 Pro", "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.", "id": "o3-pro", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 20, "output": 80, "cache_read": 10.0 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 20, "output": 80, "cache_read": 10.0 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: o4 Mini", "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.", "id": "o4-mini", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 3.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.1, "output": 4.4, "cache_read": 0.55 } }, { "id": "azure", "name": "Azure", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 3.2 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "OpenAI: GPT OSS 20B (free)", "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.", "id": "gpt-oss-20b:free", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: GPT OSS 20B", "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.", "id": "gpt-oss-20b", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.2, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.2, "cache_read": 0.03 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: GPT OSS 120B (free)", "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.", "id": "gpt-oss-120b:free", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OpenAI: GPT OSS 120B", "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.", "id": "gpt-oss-120b", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Sonnet 4", "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.", "id": "claude-sonnet-4-20250514", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Sonnet 4 (thinking)", "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.", "id": "claude-sonnet-4-20250514-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Haiku 4.5", "description": "Claude Haiku 4.5 is Anthropic's fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4's performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world's best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.", "id": "claude-haiku-4-5-20251001", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 5, "cache_write_5m": 1.25, "cache_write_1h": 2, "cache_read": 0.1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 5, "cache_write_5m": 1.25, "cache_write_1h": 2, "cache_read": 0.1 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Haiku 4.5 (thinking)", "description": "Claude Haiku 4.5 is Anthropic's fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4's performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world's best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.", "id": "claude-haiku-4-5-20251001-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 5, "cache_write_5m": 1.25, "cache_write_1h": 2, "cache_read": 0.1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 5, "cache_write_5m": 1.25, "cache_write_1h": 2, "cache_read": 0.1 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Sonnet 4.5 (free)", "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.", "id": "claude-sonnet-4-5:free", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 5 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Sonnet 4.5", "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.", "id": "claude-sonnet-4-5-20250929", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Sonnet 4.5 (thinking)", "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.", "id": "claude-sonnet-4-5-20250929-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Sonnet 4.6", "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.", "id": "claude-sonnet-4-6", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Sonnet 4.6 (thinking)", "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.", "id": "claude-sonnet-4-6-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_write_5m": 3.75, "cache_write_1h": 6, "cache_read": 0.3 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Sonnet 5", "description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.", "id": "claude-sonnet-5", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Sonnet 5 (thinking)", "description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.", "id": "claude-sonnet-5-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 10, "cache_write_5m": 2.5, "cache_write_1h": 4, "cache_read": 0.2 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 4", "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation.", "id": "claude-opus-4-20250514", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 4 (thinking)", "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation.", "id": "claude-opus-4-20250514-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 4.1", "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.", "id": "claude-opus-4-1-20250805", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 4.1 (thinking)", "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains in multi-file code refactoring, debugging precision, and detail-oriented reasoning. The model supports extended thinking up to 64K tokens and is optimized for tasks involving research, data analysis, and tool-assisted reasoning.", "id": "claude-opus-4-1-20250805-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 15, "output": 75, "cache_write_5m": 18.75, "cache_write_1h": 30, "cache_read": 1.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 4.5", "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.", "id": "claude-opus-4-5-20251101", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 4.5 (thinking)", "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.", "id": "claude-opus-4-5-20251101-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 4.6", "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.", "id": "claude-opus-4-6", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 4.6 (thinking)", "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.", "id": "claude-opus-4-6-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 4.7", "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.", "id": "claude-opus-4-7", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 4.7 (thinking)", "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.", "id": "claude-opus-4-7-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 4.8", "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.", "id": "claude-opus-4-8", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 4.8 (thinking)", "description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.", "id": "claude-opus-4-8-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Anthropic: Claude Opus 5", "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.", "id": "claude-opus-5", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Anthropic: Claude Opus 5 (thinking)", "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.", "id": "claude-opus-5-thinking", "object": "model", "created": 1788985190, "owned_by": "anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "anthropic", "name": "Anthropic", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 25, "cache_write_5m": 6.25, "cache_write_1h": 10, "cache_read": 0.5 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemini 2.5 Flash Lite", "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models.", "id": "gemini-2.5-flash-lite", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 2.5 Flash Lite (thinking)", "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models.", "id": "gemini-2.5-flash-lite-thinking", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.8, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.8, "cache_read": 0.01 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemini 2.5 Flash", "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation.", "id": "gemini-2.5-flash", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 2.5 Flash (thinking)", "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.", "id": "gemini-2.5-flash-thinking", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 5, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 5, "cache_read": 0.03 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemini 2.5 Pro", "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.", "id": "gemini-2.5-pro", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.25, "output": 10, "cache_read": 0.125 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.25, "output": 10, "cache_read": 0.125 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 3 Flash Preview", "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.", "id": "gemini-3-flash-preview", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3, "cache_read": 0.05 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 3.1 Pro Preview", "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window.", "id": "gemini-3.1-pro-preview", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_read": 0.3 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemini 3.5 Flash", "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.", "id": "gemini-3.5-flash", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 9, "cache_read": 0.15 } }, { "id": "vertex", "name": "Vertex AI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 6 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 3.5 Flash Lite", "description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.", "id": "gemini-3.5-flash-lite", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 3.6 Flash", "description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.", "id": "gemini-3.6-flash", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.75, "output": 3.75, "cache_read": 0.075 } }, { "id": "vertex", "name": "Vertex AI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "minimal", "low", "medium", "high" ] } }, { "name": "Google: Gemini 3.7 Flash", "description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.", "id": "gemini-3.7-flash", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.75, "output": 3.75, "cache_read": 0.075 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.75, "output": 3.75, "cache_read": 0.075 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "medium", "high" ] } }, { "name": "Google: Gemma 7B", "description": "Gemma 7B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class.\nDesigned for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness.", "id": "gemma-7b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.1, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.1, "cache_read": 0.05 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 2 9B", "description": "Gemma 2 9B by Google is an advanced, open-source language model that sets a new standard for efficiency and performance in its size class.\nDesigned for a wide variety of tasks, it empowers developers and researchers to build innovative applications, while maintaining accessibility, safety, and cost-effectiveness.", "id": "gemma-2-9b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.15, "cache_read": 0.06 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.15, "cache_read": 0.06 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 2 27B", "description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models.\nGemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning.", "id": "gemma-2-27b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 0.8, "cache_read": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 0.8, "cache_read": 0.4 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 3 1B", "description": "Gemma 3 1B is the smallest of the new Gemma 3 family. It handles context windows up to 32k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.", "id": "gemma-3-1b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.15, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.15, "cache_read": 0.05 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 3 4B", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.", "id": "gemma-3-4b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.25, "cache_read": 0.075 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.25, "cache_read": 0.075 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 3 12B", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after Gemma 3 27B.", "id": "gemma-3-12b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.35, "output": 0.56, "cache_read": 0.175 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.35, "output": 0.56, "cache_read": 0.175 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 3 27B", "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2.", "id": "gemma-3-27b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 0.8, "cache_read": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 0.8, "cache_read": 0.4 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 3n 4B", "description": "Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements.", "id": "gemma-3n-e4b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.35, "output": 0.56, "cache_read": 0.175 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.35, "output": 0.56, "cache_read": 0.175 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Google: Gemma 4 26B A4B (free)", "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.", "id": "gemma-4-26b-a4b-it:free", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemma 4 26B A4B", "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.", "id": "gemma-4-26b-a4b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.13, "output": 0.4, "cache_read": 0.065 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.13, "output": 0.4, "cache_read": 0.065 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemma 4 31B (free)", "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.", "id": "gemma-4-31b-it:free", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Google: Gemma 4 31B", "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.", "id": "gemma-4-31b-it", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.4, "cache_read": 0.07 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.4, "cache_read": 0.07 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Meta: Llama Guard 4 12B", "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.\nLlama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.", "id": "llama-guard-4-12b", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.05 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 3 70B", "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases.", "id": "llama-3-70b", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 0.8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 0.8 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 3.1 8B", "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.", "id": "llama-3.1-8b", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.03, "output": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.03, "output": 0.05 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 3.1 70B", "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.", "id": "llama-3.1-70b", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.3 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 3.2 1B", "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance.\nSupporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models.", "id": "llama-3.2-1b", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.01, "output": 0.02 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.01, "output": 0.02 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 3.2 3B", "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.\nTrained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.", "id": "llama-3.2-3b", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.03, "output": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.03, "output": 0.05 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 3.3 70B Instruct", "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks.\nSupported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.", "id": "llama-3.3-70b-instruct", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.4 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 4 Scout", "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.\nBuilt for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.", "id": "llama-4-scout-17b-16e-instruct", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.5 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meta: Llama 4 Maverick", "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.", "id": "llama-4-maverick-17b-128e-instruct", "object": "model", "created": 1788985190, "owned_by": "meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meta", "name": "Meta", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.8 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.", "id": "nemotron-3-nano-30b-a3b:free", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3 Nano 30B A3B", "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.", "id": "nemotron-3-nano-30b-a3b", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.025 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.025 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3 Nano Omni ", "description": "NVIDIA Nemotron 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.\nBuilt on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines.", "id": "nemotron-3-nano-omni-30b-a3b-reasoning", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.25 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3 Super", "description": "NVIDIA Nemotron 3 Super is a 120B-A12B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.\nBuilt on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines.", "id": "nemotron-3-super-120b-a12b", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.5 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3 Ultra", "description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.\nIt is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.", "id": "nemotron-3-ultra-550b-a55b", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 2.5, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 2.5, "cache_read": 0.2 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3.5 Content Safety", "description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting text and image input and returning text output: a safe/unsafe classification for the user prompt and the response, safety category labels, and an optional reasoning trace. It covers 12 languages with a context window of up to 128K tokens.\nIt is suited for prompt and response moderation, content classification, safety pipelines, and enterprise AI guardrails with policy enforcement, and includes a togglable reasoning mode. It is part of the NVIDIA Nemotron family of open models for agentic AI.", "id": "nemotron-3.5-content-safety", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.005, "output": 0.025 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.005, "output": 0.025 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3.5 Lightning (free)", "description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.", "id": "nemotron-3.5-lightning:free", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "NVIDIA: Nemotron 3.5 Lightning", "description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.", "id": "nemotron-3.5-lightning", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.01, "output": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.01, "output": 0.05 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: R1 0528", "description": "May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.", "id": "deepseek-r1-0528", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.7, "output": 2.5, "cache_read": 0.07 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.7, "output": 2.5, "cache_read": 0.07 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: R1", "description": "DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.", "id": "deepseek-r1", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 3, "cache_read": 0.05 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: R1 Distill Llama 70B", "description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1.", "id": "deepseek-r1-distill-llama-70b", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: R1 Distill Qwen 32B", "description": "DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.", "id": "deepseek-r1-distill-qwen-32b", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1.2, "output": 1.2, "cache_read": 0.12 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1.2, "output": 1.2, "cache_read": 0.12 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3.1", "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference.\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.\nIt succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.", "id": "deepseek-v3.1", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.6, "cache_read": 0.06 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.6, "cache_read": 0.06 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V3.1 (thinking)", "description": "DeepSeek-V3.1-Thinking is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference.\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.\nIt succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.", "id": "deepseek-v3.1-thinking", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.6, "cache_read": 0.06 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.6, "cache_read": 0.06 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3.1 Terminus", "description": "DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean.\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.", "id": "deepseek-v3.1-terminus", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V3.1 Terminus (thinking)", "description": "DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean.\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.", "id": "deepseek-v3.1-terminus-thinking", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3.2 (free)", "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.", "id": "deepseek-v3.2:free", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3.2", "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.", "id": "deepseek-v3.2", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.28, "output": 0.42, "cache_read": 0.028 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.28, "output": 0.42, "cache_read": 0.028 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V3.2 (thinking)", "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.", "id": "deepseek-v3.2-thinking", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.28, "output": 0.42, "cache_read": 0.028 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.28, "output": 0.42, "cache_read": 0.028 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3.2 Exp", "description": "DeepSeek-V3.2-Exp is an intermediate step toward the next-generation architecture of the DeepSeek models by introducing DeepSeek Sparse Attention—a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios.", "id": "deepseek-v3.2-exp", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.27, "output": 0.41, "cache_read": 0.027 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.27, "output": 0.41, "cache_read": 0.027 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V3.2 Exp (thinking)", "description": "DeepSeek-V3.2-Exp is an intermediate step toward the next-generation architecture of the DeepSeek models by introducing DeepSeek Sparse Attention—a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios.", "id": "deepseek-v3.2-exp-thinking", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.27, "output": 0.41, "cache_read": 0.027 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.27, "output": 0.41, "cache_read": 0.027 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3.2 Speciale", "description": "DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning to push capability beyond the base model. Reported evaluations place Speciale ahead of GPT-5 on difficult reasoning workloads, with proficiency comparable to Gemini-3.0-Pro, while retaining strong coding and tool-use reliability. Like V3.2, it benefits from a large-scale agentic task synthesis pipeline that improves compliance and generalization in interactive environments.", "id": "deepseek-v3.2-speciale", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.28, "output": 0.42, "cache_read": 0.028 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.28, "output": 0.42, "cache_read": 0.028 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V4 Flash (free)", "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.", "id": "deepseek-v4-flash:free", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 2 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V4 Flash", "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.", "id": "deepseek-v4-flash", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.2, "cache_read": 0.0028 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.2, "cache_read": 0.0028 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V4 Flash (thinking)", "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.", "id": "deepseek-v4-flash-thinking", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.2, "cache_read": 0.0028 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.2, "cache_read": 0.0028 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V4 Pro", "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.", "id": "deepseek-v4-pro", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 3, "cache_read": 0.003625 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 3, "cache_read": 0.003625 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V4 Pro (thinking)", "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.", "id": "deepseek-v4-pro-thinking", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 3, "cache_read": 0.003625 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 3, "cache_read": 0.003625 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V3 0324", "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.\nIt succeeds the DeepSeek V3 model and performs really well on a variety of tasks.", "id": "deepseek-v3-0324", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "DeepSeek: DeepSeek V3", "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.", "id": "deepseek-v3", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "deepseekai", "name": "DeepSeek", "tokens": 164000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 164000, "max_model_len": 164000, "max_input_tokens": 164000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Codestral 2508", "description": "Low-latency coding model optimized for completion, FIM, and code generation.", "id": "codestral-2508", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Codestral Latest", "description": "Low-latency coding model optimized for completion, FIM, and code generation.", "id": "codestral-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Devstral 2512", "description": "Devstral 2 agentic coding model; still served until retirement.", "id": "devstral-2512", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Devstral Latest", "description": "Devstral latest alias; still served until retirement.", "id": "devstral-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Devstral Medium Latest", "description": "Devstral medium latest alias; still served until retirement.", "id": "devstral-medium-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Devstral Small Latest", "description": "Compatibility alias still accepted by Mistral API.", "id": "devstral-small-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Devstral Small 2", "description": "Compatibility alias still accepted by Mistral API.", "id": "labs-devstral-small-2512", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Magistral Medium 2509", "description": "Magistral Medium alias; listed price from mistral.ai/pricing/api.", "id": "magistral-medium-2509", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 2.0, "output": 5.0, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 2.0, "output": 5.0, "cache_read": 0.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Magistral Medium Latest", "description": "Magistral Medium alias; listed price from mistral.ai/pricing/api.", "id": "magistral-medium-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 2.0, "output": 5.0, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 2.0, "output": 5.0, "cache_read": 0.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Magistral Small 2509", "description": "Magistral Small alias; listed price from mistral.ai/pricing/api.", "id": "magistral-small-2509", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Magistral Small Latest", "description": "Magistral Small alias; listed price from mistral.ai/pricing/api.", "id": "magistral-small-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Ministral 14B 2512", "description": "Powerful Ministral 3 model with best-in-class text and vision capabilities.", "id": "ministral-14b-2512", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2, "cache_read": 0.02 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2, "cache_read": 0.02 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 14B Latest", "description": "Powerful Ministral 3 model with best-in-class text and vision capabilities.", "id": "ministral-14b-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2, "cache_read": 0.02 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2, "cache_read": 0.02 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 3B 2512", "description": "Tiny efficient Ministral 3 edge model with text and vision capabilities.", "id": "ministral-3b-2512", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.1, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.1, "cache_read": 0.01 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 3B Latest", "description": "Tiny efficient Ministral 3 edge model with text and vision capabilities.", "id": "ministral-3b-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.1, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.1, "cache_read": 0.01 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 8B 2512", "description": "Efficient Ministral 3 model with best-in-class text and vision capabilities.", "id": "ministral-8b-2512", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 8B Latest", "description": "Efficient Ministral 3 model with best-in-class text and vision capabilities.", "id": "ministral-8b-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Code Agent Latest", "description": "Code-agent alias for Devstral; still served until retirement.", "id": "mistral-code-agent-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Codestral Latest", "description": "Codestral alias for code completion and FIM workloads.", "id": "mistral-code-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Large 3", "description": "Open-weight general-purpose multimodal flagship model (Mistral Large 3).", "id": "mistral-large-2512", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Large 3", "description": "Open-weight general-purpose multimodal flagship model (Mistral Large 3).", "id": "mistral-large-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Medium 3.5", "description": "Frontier-class multimodal model optimized for agentic and coding use cases, with configurable reasoning effort.", "id": "mistral-medium", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Mistral Medium 3", "description": "Dated Mistral Medium 3 checkpoint; still served until retirement.", "id": "mistral-medium-2505", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Medium 3.1", "description": "Dated Mistral Medium 3.1 checkpoint; still served until retirement.", "id": "mistral-medium-2508", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.0, "cache_read": 0.04 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Medium 2604", "description": "Dated Mistral Medium 3.5 checkpoint (26.04) for agentic and coding workloads.", "id": "mistral-medium-2604", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Mistral Medium 3.5", "description": "Frontier-class multimodal model optimized for agentic and coding use cases, with configurable reasoning effort.", "id": "mistral-medium-3-5", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Mistral Medium 3.5", "description": "Frontier-class multimodal model optimized for agentic and coding use cases, with configurable reasoning effort.", "id": "mistral-medium-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Mistral Small 2501", "description": "Compatibility alias still accepted by Mistral API (routes to Small 4).", "id": "mistral-small-2501", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Small 2506", "description": "Compatibility alias still accepted by Mistral API (routes to Small 4).", "id": "mistral-small-2506", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Small 4", "description": "Hybrid model unifying instruct, reasoning, and coding in a single efficient multimodal model.", "id": "mistral-small-2603", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Mistral Small 4", "description": "Hybrid model unifying instruct, reasoning, and coding in a single efficient multimodal model.", "id": "mistral-small-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Mistral Tiny 2407", "description": "Compatibility alias still accepted by Mistral API (routes to Ministral 8B).", "id": "mistral-tiny-2407", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Tiny Latest", "description": "Compatibility alias still accepted by Mistral API (routes to Ministral 8B).", "id": "mistral-tiny-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Vibe CLI Fast", "description": "Fast Vibe CLI alias routed to Mistral Small 4.", "id": "mistral-vibe-cli-fast", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.015 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Vibe CLI Latest", "description": "Vibe CLI alias routed to Mistral Medium 3.5.", "id": "mistral-vibe-cli-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Vibe CLI With Tools", "description": "Vibe CLI with-tools alias routed to Mistral Medium 3.5.", "id": "mistral-vibe-cli-with-tools", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 7.5, "cache_read": 0.15 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Mistral: Open Mistral Nemo", "description": "Compatibility alias still accepted by Mistral API (routes to Ministral 8B).", "id": "open-mistral-nemo", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Open Mistral Nemo 2407", "description": "Compatibility alias still accepted by Mistral API (routes to Ministral 8B).", "id": "open-mistral-nemo-2407", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Voxtral Small 2507", "description": "Audio understanding model for instruct-style speech and chat use cases.", "id": "voxtral-small-2507", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 32768, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 32768, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 } } ], "context_length": 32768, "max_model_len": 32768, "max_input_tokens": 32768, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Voxtral Small Latest", "description": "Audio understanding model for instruct-style speech and chat use cases.", "id": "voxtral-small-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 32768, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 32768, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4, "cache_read": 0.01 } } ], "context_length": 32768, "max_model_len": 32768, "max_input_tokens": 32768, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 3 8B Instruct (free)", "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", "id": "ministral-3-8b-instruct:free", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Ministral 3 8B Instruct", "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", "id": "ministral-3-8b-instruct", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Small 3.1 24B", "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments.", "id": "mistral-small-3.1-24b-instruct", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Small 3.2 24B (free)", "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).", "id": "mistral-small-3.2-24b-instruct:free", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Mistral: Mistral Small 3.2 24B", "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).", "id": "mistral-small-3.2-24b-instruct", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Cohere: Command Nightly", "description": "Command Nightly is the latest, most experimental, and (possibly) unstable version of its default counterpart. Nightly releases are updated regularly, without warning, and are not recommended for production use.", "id": "command-nightly", "object": "model", "created": 1788985190, "owned_by": "cohere", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "cohere", "name": "Cohere", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 2 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Cohere: Command R (08-2024)", "description": "Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.", "id": "command-r-08-2024", "object": "model", "created": 1788985190, "owned_by": "cohere", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "cohere", "name": "Cohere", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Cohere: North Mini Code", "description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.", "id": "north-mini-code-1-0", "object": "model", "created": 1788985190, "owned_by": "cohere", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.01, "output": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "cohere", "name": "Cohere", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.01, "output": 0.03 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "xAI: Grok 4.20", "description": "Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.", "id": "grok-4.20-0309-non-reasoning", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 2000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 8, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 2000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 8, "cache_read": 0.2 } } ], "context_length": 2000000, "max_model_len": 2000000, "max_input_tokens": 2000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "xAI: Grok 4.20 (thinking)", "description": "Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.", "id": "grok-4.20-0309-reasoning", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 2000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 8, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 2000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 8, "cache_read": 0.2 } } ], "context_length": 2000000, "max_model_len": 2000000, "max_input_tokens": 2000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "xAI: Grok 4.20 Multi-Agent", "description": "Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks. Client-side function calling is not supported — only xAI built-in server tools (web_search, x_search, etc.) and remote MCP. Upstream requires the Responses API; this platform bridges /v1/chat/completions to /v1/responses.", "id": "grok-4.20-multi-agent-0309", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 2000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 8, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 2000000, "pricing": { "type": "per_million_tokens", "input": 4, "output": 8, "cache_read": 0.2 } } ], "context_length": 2000000, "max_model_len": 2000000, "max_input_tokens": 2000000, "metadata": { "vision": true, "function_call": false, "web_search": true, "reasoning": true } }, { "name": "xAI: Grok 4.3", "description": "Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.", "id": "grok-4.3", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 3.5, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 3.5, "cache_read": 0.2 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "xAI: Grok 4.5", "description": "Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.", "id": "grok-4.5", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 500000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 500000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.3 } } ], "context_length": 500000, "max_model_len": 500000, "max_input_tokens": 500000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "xAI: Grok 4.6", "description": "Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.", "id": "grok-4.6", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 500000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 500000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.5 } } ], "context_length": 500000, "max_model_len": 500000, "max_input_tokens": 500000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Microsoft: Phi 4", "description": "Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.\nAt 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs.", "id": "phi-4", "object": "model", "created": 1788985190, "owned_by": "microsoft", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "microsoft", "name": "Microsoft", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3 } } ], "context_length": 16000, "max_model_len": 16000, "max_input_tokens": 16000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Microsoft: WizardLM-2 7B", "description": "WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger opensource leading models. It is a finetune of Mistral 7B Instruct, using the same technique as WizardLM-2 8x22B.", "id": "wizardlm-2-7b", "object": "model", "created": 1788985190, "owned_by": "microsoft", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.07, "output": 0.07 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "microsoft", "name": "Microsoft", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.07, "output": 0.07 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Microsoft: WizardLM-2 8x22B", "description": "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is an instruct finetune of Mixtral 8x22B.", "id": "wizardlm-2-8x22b", "object": "model", "created": 1788985190, "owned_by": "microsoft", "tokens": 64000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "microsoft", "name": "Microsoft", "tokens": 64000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 0.5 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "MiniMax: MiniMax M2", "description": "MiniMax-M2 is a compact, fast, and cost-effective Mixture-of-Experts (MoE) model with 230 billion total parameters and 10 billion active parameters, built for elite performance in coding and agentic tasks while maintaining powerful general intelligence. With just 10 billion activated parameters, MiniMax-M2 provides sophisticated end-to-end tool use performance expected from today's leading models, but in a streamlined form factor that makes deployment and scaling easier than ever. The model excels at multi-file edits, coding-run-fix loops, test-validated repairs, and complex long-horizon toolchains across shell, browser, retrieval, and code runners.", "id": "minimax-m2", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MiniMax: MiniMax M2.1", "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.\nCompared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.", "id": "minimax-m2.1", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MiniMax: MiniMax M2-her", "description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.", "id": "minimax-m2-her", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 65000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 65000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 65000, "max_model_len": 65000, "max_input_tokens": 65000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "MiniMax: MiniMax M2.5", "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.", "id": "minimax-m2.5", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MiniMax: MiniMax M2.7 (free)", "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.", "id": "minimax-m2.7:free", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 2 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MiniMax: MiniMax M2.7", "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.", "id": "minimax-m2.7", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.03, "cache_write_5m": 0.1875 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.06, "cache_write_5m": 0.375 } }, { "id": "daphne", "name": "Daphne", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6, "cache_read": 0.03, "cache_write_5m": 0.1875 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MiniMax: MiniMax M3", "description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.", "id": "minimax-m3", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.06 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gnk", "name": "GNK", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 1.2, "cache_read": 0.06 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen2.5 7B Instruct", "description": "Qwen2.5 7B is the latest series of Qwen large language models. It shows significant improvements in instruction-following capabilities, outperforming its predecessor Qwen1.5 7B in various benchmarks. It is designed to be more efficient and effective in understanding and generating human-like text.", "id": "qwen-2.5-7b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.3, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.3, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen2.5 32B Instruct", "description": "Qwen2.5 32B is the latest series of Qwen large language models. It shows significant improvements in instruction-following capabilities, outperforming its predecessor Qwen2.5 7B in various benchmarks. It is designed to be more efficient and effective in understanding and generating human-like text.", "id": "qwen-2.5-32b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 1, "cache_read": 0.1, "cache_write_5m": 1.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 1, "cache_read": 0.1, "cache_write_5m": 1.25 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen2.5 72B Instruct", "description": "Qwen2.5 72B is the latest series of Qwen large language models. It shows significant improvements in instruction-following capabilities, outperforming its predecessor Qwen2.5 32B in various benchmarks. It is designed to be more efficient and effective in understanding and generating human-like text.", "id": "qwen-2.5-72b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 1, "cache_read": 0.1, "cache_write_5m": 1.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 1, "cache_read": 0.1, "cache_write_5m": 1.25 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen2.5 Coder 7B Instruct", "description": "Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, it incorporates enhancements like RoPE, SwiGLU, RMSNorm, and GQA attention with support for up to 128K tokens using YaRN-based extrapolation. It is trained on a large corpus of source code, synthetic data, and text-code grounding, providing robust performance across programming languages and agentic coding workflows.", "id": "qwen-2.5-coder-7b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2, "cache_read": 0.02, "cache_write_5m": 0.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2, "cache_read": 0.02, "cache_write_5m": 0.25 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen2.5 Coder 32B Instruct", "description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:\nSignificantly improvements in code generation, code reasoning and code fixing.\nA more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.", "id": "qwen-2.5-coder-32b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 33000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 0.8, "cache_read": 0.08, "cache_write_5m": 1.0 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 33000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 0.8, "cache_read": 0.08, "cache_write_5m": 1.0 } } ], "context_length": 33000, "max_model_len": 33000, "max_input_tokens": 33000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen VL Plus", "description": "Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for image input. It delivers significant performance across a broad range of visual tasks.", "id": "qwen-vl-plus", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 7500, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 7500, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 7500, "max_model_len": 7500, "max_input_tokens": 7500, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen VL Max", "description": "Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.", "id": "qwen-vl-max", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 7500, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.5, "cache_read": 0.1, "cache_write_5m": 1.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 7500, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.5, "cache_read": 0.1, "cache_write_5m": 1.25 } } ], "context_length": 7500, "max_model_len": 7500, "max_input_tokens": 7500, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen2.5 VL 72B Instruct", "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", "id": "qwen2.5-vl-72b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 1, "cache_read": 0.1, "cache_write_5m": 1.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 1, "cache_read": 0.1, "cache_write_5m": 1.25 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen-Turbo", "description": "Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.", "id": "qwen-turbo", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01, "cache_write_5m": 0.125 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.01, "cache_write_5m": 0.125 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen Plus", "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.", "id": "qwen-plus", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05, "cache_write_5m": 0.625 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 1.5, "cache_read": 0.05, "cache_write_5m": 0.625 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen-Max", "description": "Qwen-Max, based on Qwen2.5, provides the best inference performance among Qwen models, especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion tokens and further post-trained with curated Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) methodologies.", "id": "qwen-max", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 7, "cache_read": 0.2, "cache_write_5m": 2.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 7, "cache_read": 0.2, "cache_write_5m": 2.5 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3 32B", "description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, coding, and logical inference, and a \"non-thinking\" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.", "id": "qwen3-32b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 41000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.36, "cache_read": 0.012, "cache_write_5m": 0.15 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 41000, "pricing": { "type": "per_million_tokens", "input": 0.12, "output": 0.36, "cache_read": 0.012, "cache_write_5m": 0.15 } } ], "context_length": 41000, "max_model_len": 41000, "max_input_tokens": 41000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3 30B A3B", "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.", "id": "qwen3-30b-a3b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 41000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.3, "cache_read": 0.015, "cache_write_5m": 0.1875 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 41000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.3, "cache_read": 0.015, "cache_write_5m": 0.1875 } } ], "context_length": 41000, "max_model_len": 41000, "max_input_tokens": 41000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3 30B A3B Instruct 2507", "description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.", "id": "qwen3-30b-a3b-instruct-2507", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.3, "cache_read": 0.015, "cache_write_5m": 0.1875 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.3, "cache_read": 0.015, "cache_write_5m": 0.1875 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3 Coder 30B A3B Instruct (free)", "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.", "id": "qwen3-coder-30-a3b-instruct:free", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3 Coder 30B A3B Instruct", "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.", "id": "qwen3-coder-30-a3b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015, "cache_write_5m": 0.1875 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.15, "cache_read": 0.015, "cache_write_5m": 0.1875 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3 Next 80B A3B Instruct", "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.\nThe model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.", "id": "qwen3-next-80b-a3b-instruct", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 2, "cache_read": 0.05, "cache_write_5m": 0.625 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 2, "cache_read": 0.05, "cache_write_5m": 0.625 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3 235B A22B Instruct 2507", "description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement \"thinking mode\" ( blocks).\nCompared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.", "id": "qwen3-235b-a22b-2507", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.24, "output": 0.72, "cache_read": 0.024, "cache_write_5m": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.24, "output": 0.72, "cache_read": 0.024, "cache_write_5m": 0.3 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3 235B A22B Thinking 2507", "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This \"thinking-only\" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode () and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.\nThe model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.", "id": "qwen3-235b-a22b-thinking-2507", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.24, "output": 0.72, "cache_read": 0.024, "cache_write_5m": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.24, "output": 0.72, "cache_read": 0.024, "cache_write_5m": 0.3 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3 Coder 480B A35B", "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts).", "id": "qwen3-coder", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 2.4, "output": 2.4, "cache_read": 0.24, "cache_write_5m": 3.0 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 2.4, "output": 2.4, "cache_read": 0.24, "cache_write_5m": 3.0 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.5 397B A17B", "description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.", "id": "qwen3.5-397b-a17b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 4, "cache_read": 0.1, "cache_write_5m": 1.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 4, "cache_read": 0.1, "cache_write_5m": 1.25 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.5 Plus", "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.", "id": "qwen3.5-plus", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 3, "cache_read": 0.08, "cache_write_5m": 1.0 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 3, "cache_read": 0.08, "cache_write_5m": 1.0 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.6 Flash", "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window.", "id": "qwen3.6-flash", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 2, "cache_read": 0.05, "cache_write_5m": 0.625 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.5, "output": 2, "cache_read": 0.05, "cache_write_5m": 0.625 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.6 Plus", "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with a significantly improved “vibe coding” experience. The model excels at complex tasks such as 3D scenes, games, and repository-level problem solving, achieving a 78.8 score on SWE-bench Verified. It represents a substantial leap in both pure-text and multimodal capabilities, performing at the level of leading state-of-the-art models.", "id": "qwen3.6-plus", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 4, "cache_read": 0.1, "cache_write_5m": 1.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 4, "cache_read": 0.1, "cache_write_5m": 1.25 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.6 27B (free)", "description": "Qwen3.6-27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs — and supports a 262,144-token context window. The model is designed for agentic coding and reasoning tasks, with particular strength in repository-level code comprehension, front-end development workflows, and multi-step problem solving. It includes a built-in thinking mode for extended reasoning and preserves thinking context across conversation history. Qwen3.6 27B supports 201 languages and dialects and is released under the Apache 2.0 license.", "id": "qwen3.6-27b:free", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.6 27B", "description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs — and supports a 262,144-token context window.\nThe model is designed for agentic coding and reasoning tasks, with particular strength in repository-level code comprehension, front-end development workflows, and multi-step problem solving. It includes a built-in thinking mode for extended reasoning and preserves thinking context across conversation history. Qwen3.6 27B supports 201 languages and dialects and is released under the Apache 2.0 license.", "id": "qwen3.6-27b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.6 35B A3B (free)", "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.", "id": "qwen3.6-35b-a3b:free", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.6 35B A3B", "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.", "id": "qwen3.6-35b-a3b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 1, "cache_read": 0.015, "cache_write_5m": 0.1875 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 1, "cache_read": 0.015, "cache_write_5m": 0.1875 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Alibaba: Qwen3.7 Flash", "description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.", "id": "qwen3.7-flash", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.03, "output": 0.13, "cache_read": 0.003, "cache_write_5m": 0.0375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.03, "output": 0.13, "cache_read": 0.003, "cache_write_5m": 0.0375 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.7 Plus", "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its vision-language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its distinguishing trait is multi-modal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references, and perform end-to-end navigation within mobile apps.", "id": "qwen3.7-plus", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.32, "output": 1.28, "cache_read": 0.032, "cache_write_5m": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.32, "output": 1.28, "cache_read": 0.032, "cache_write_5m": 0.4 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.7 Max", "description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.", "id": "qwen3.7-max", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.475, "output": 4.425, "cache_read": 0.1475, "cache_write_5m": 1.8438 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.475, "output": 4.425, "cache_read": 0.1475, "cache_write_5m": 1.8438 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.8 Max", "description": "Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding, coding, and agentic workflows.", "id": "qwen3.8-max", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.2, "cache_write_5m": 2.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.2, "cache_write_5m": 2.5 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.8 2.4T A95B", "description": "Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.", "id": "qwen3.8-2.4t-a95b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.2, "cache_write_5m": 2.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 2, "output": 6, "cache_read": 0.2, "cache_write_5m": 2.5 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.8 27B", "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks.", "id": "qwen3.8-27b", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.45, "output": 3.2, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.45, "output": 3.2, "cache_read": 0.05 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Alibaba: Qwen3.8 Flash", "description": "Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.", "id": "qwen3.8-flash", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.47, "cache_read": 0.016, "cache_write_5m": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.47, "cache_read": 0.016, "cache_write_5m": 0.2 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Sakana: Namazu", "description": "Namazu is a series of prototype models developed by Sakana AI, a Tokyo-based AI research lab. Rather than training from scratch, Sakana AI applies proprietary post-training technology to existing open-weight foundation models — including DeepSeek-V3.1-Terminus, Meta's Llama 3.1 405B, and gpt-oss-120B — to adapt them for Japanese cultural, linguistic, and safety requirements. Namazu preserves the core reasoning, knowledge, and coding capabilities of its base models while significantly improving neutrality and factual accuracy on politically and historically sensitive topics relevant to Japan.", "id": "namazu", "object": "model", "created": 1788985190, "owned_by": "sakana", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "sakana", "name": "Sakana", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Sakana: Fugu Ultra", "description": "Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself.\nFugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.", "id": "fugu-ultra", "object": "model", "created": 1788985190, "owned_by": "sakana", "tokens": 272000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 30, "cache_read": 0.5 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "sakana", "name": "Sakana", "tokens": 272000, "pricing": { "type": "per_million_tokens", "input": 5, "output": 30, "cache_read": 0.5 } } ], "context_length": 272000, "max_model_len": 272000, "max_input_tokens": 272000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "AionLabs: Aion-RP 1.0 (8B)", "description": "Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.", "id": "aion-rp-llama-3.1-8b", "object": "model", "created": 1788985190, "owned_by": "aion-labs", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "aion-labs", "name": "Aion Labs", "tokens": 32000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.2 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "AionLabs: Aion-2.0", "description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging. It also handles mature and darker themes with more nuance and depth.", "id": "aion-2.0", "object": "model", "created": 1788985190, "owned_by": "aion-labs", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.6, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "aion-labs", "name": "Aion Labs", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.6, "cache_read": 0.2 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "AionLabs: Aion-3.0-Mini (Free)", "description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.", "id": "aion-3.0-mini:free", "object": "model", "created": 1788985190, "owned_by": "aion-labs", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "aion-labs", "name": "Aion Labs", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "AionLabs: Aion-3.0-Mini", "description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.", "id": "aion-3.0-mini", "object": "model", "created": 1788985190, "owned_by": "aion-labs", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.7, "output": 1.4, "cache_read": 0.18 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "aion-labs", "name": "Aion Labs", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.7, "output": 1.4, "cache_read": 0.18 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "AionLabs: Aion-3.0 (Free)", "description": "Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.", "id": "aion-3.0:free", "object": "model", "created": 1788985190, "owned_by": "aion-labs", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "aion-labs", "name": "Aion Labs", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "AionLabs: Aion-3.0", "description": "Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.", "id": "aion-3.0", "object": "model", "created": 1788985190, "owned_by": "aion-labs", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 6, "cache_read": 0.75 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "aion-labs", "name": "Aion Labs", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 6, "cache_read": 0.75 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Writer: Palmyra X5", "description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million tokens, powered by a novel transformer architecture and hybrid attention mechanisms. This enables faster inference and expanded memory for processing large volumes of enterprise data, critical for scaling AI agents.", "id": "palmyra-x5", "object": "model", "created": 1788985190, "owned_by": "writer", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "writer", "name": "Writer", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 6 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Poolside: Laguna S 2.1", "description": "Laguna S 2.1 is the latest coding agent model from Poolside(opens in new tab). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license.", "id": "laguna-s-2.1", "object": "model", "created": 1788985190, "owned_by": "poolside", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.2, "cache_read": 0.009 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "poolside", "name": "Poolside", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.2, "cache_read": 0.009 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Poolside: Laguna XS 2.1", "description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside(opens in new tab) and a step forward from their Laguna XS.2 model (released in April 2026). It combines tool calling and reasoning capabilities with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows.", "id": "laguna-xs-2.1", "object": "model", "created": 1788985190, "owned_by": "poolside", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.2, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "poolside", "name": "Poolside", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.2, "cache_read": 0.03 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Amazon: Nova 2 Lite", "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.", "id": "nova-2-lite-v1", "object": "model", "created": 1788985190, "owned_by": "amazon", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03, "cache_write_5m": 0.375 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "amazon", "name": "Amazon", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 2.5, "cache_read": 0.03, "cache_write_5m": 0.375 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Amazon: Nova Pro 1.0", "description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.", "id": "nova-pro-v1", "object": "model", "created": 1788985190, "owned_by": "amazon", "tokens": 300000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 3.2, "cache_read": 0.08, "cache_write_5m": 1.0 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "amazon", "name": "Amazon", "tokens": 300000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 3.2, "cache_read": 0.08, "cache_write_5m": 1.0 } } ], "context_length": 300000, "max_model_len": 300000, "max_input_tokens": 300000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Gryphe: Mythomax L2 13B", "description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.", "id": "mytho-max-l2-13b", "object": "model", "created": 1788985190, "owned_by": "gryphe", "tokens": 4000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "gryphe", "name": "Gryphe", "tokens": 4000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.3 } } ], "context_length": 4000, "max_model_len": 4000, "max_input_tokens": 4000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "NousResearch: Hermes 2 Pro Llama 3 8B", "description": "Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.", "id": "hermes-2-pro-llama-3-8b", "object": "model", "created": 1788985190, "owned_by": "nousresearch", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.14 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nousresearch", "name": "Nous Research", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.14 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "NousResearch: Hermes 4 14B", "description": "Hermes 4 14B is a frontier, hybrid-mode reasoning model based on Qwen 3 14B by Nous Research that is aligned to you.", "id": "hermes-4-14b", "object": "model", "created": 1788985190, "owned_by": "nousresearch", "tokens": 40000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "nousresearch", "name": "Nous Research", "tokens": 40000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.2 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "NousResearch: Hermes 4 70B", "description": "Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit ... reasoning traces before answering. Users can control the reasoning behaviour with the reasoning enabled boolean.\nThis 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.", "id": "hermes-4-70b", "object": "model", "created": 1788985190, "owned_by": "nousresearch", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "nousresearch", "name": "Nous Research", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.4 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "NousResearch: Hermes 4 405B", "description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with ... traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the reasoning enabled boolean.\nThe model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.", "id": "hermes-4-405b", "object": "model", "created": 1788985190, "owned_by": "nousresearch", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "nousresearch", "name": "Nous Research", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.8 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "NousResearch: Hermes 4.3 36B", "description": "Hermes 4.3 36B is a frontier, hybrid-mode reasoning model based on ByteDance Seed 36B base, made by Nous Research that is aligned to you.", "id": "hermes-4.3-36b", "object": "model", "created": 1788985190, "owned_by": "nousresearch", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "nousresearch", "name": "Nous Research", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.6 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Tencent: Hunyuan A13B Instruct", "description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).", "id": "hunyuan-a13b-instruct", "object": "model", "created": 1788985190, "owned_by": "tencent", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.25, "output": 0.25 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "tencent", "name": "Tencent", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.25, "output": 0.25 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Tencent: Hy3", "description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.", "id": "hy3", "object": "model", "created": 1788985190, "owned_by": "tencent", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.58, "cache_read": 0.033 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "tencent", "name": "Tencent", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.58, "cache_read": 0.033 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Meituan: LongCat Flash Chat", "description": "LongCat-Flash-Chat is a powerful and efficient language model with an innovative Mixture-of-Experts (MoE) architecture. It contains 560 billion total parameters but dynamically activates only 18.6 to 31.3 billion parameters (averaging ~27B) per token, optimizing for both performance and efficiency. It is designed to be a non-thinking foundation model with exceptional strengths in agentic tasks.", "id": "longcat-flash-chat", "object": "model", "created": 1788985190, "owned_by": "meituan", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.8, "cache_read": 0.004 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meituan", "name": "Meituan", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 0.8, "cache_read": 0.004 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Meituan: LongCat Flash Chat (thinking)", "description": "LongCat-Flash-Chat-Thinking is a powerful and efficient language model with an innovative Mixture-of-Experts (MoE) architecture. It contains 560 billion total parameters but dynamically activates only 18.6 to 31.3 billion parameters (averaging ~27B) per token, optimizing for both performance and efficiency. This is the thinking variant of the model.", "id": "longcat-flash-chat-thinking", "object": "model", "created": 1788985190, "owned_by": "meituan", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 1.5, "cache_read": 0.003 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "meituan", "name": "Meituan", "tokens": 128000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 1.5, "cache_read": 0.003 } } ], "context_length": 128000, "max_model_len": 128000, "max_input_tokens": 128000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "inclusionAI: Ling 3.0 Flash Fin", "description": "Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment workflows that require complex multi-step tasks and long-horizon planning and execution, while retaining general capabilities in reasoning, coding, and mathematics.", "id": "ling-3.0-flash-fin", "object": "model", "created": 1788985190, "owned_by": "inclusionai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.06, "output": 0.18, "cache_read": 0.012 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "inclusionai", "name": "InclusionAI", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.06, "output": 0.18, "cache_read": 0.012 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "inclusionAI: Ling 3.0 Flash Sante", "description": "Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for medical knowledge reasoning, clinical safety, evidence-based retrieval, and long-horizon medical tasks, while retaining general capabilities in reasoning, coding, and agentic tasks.", "id": "ling-3.0-flash-sante", "object": "model", "created": 1788985190, "owned_by": "inclusionai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.06, "output": 0.18, "cache_read": 0.012 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "inclusionai", "name": "InclusionAI", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.06, "output": 0.18, "cache_read": 0.012 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.5", "description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses.", "id": "glm-4.5", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.2, "cache_read": 0.11 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.2, "cache_read": 0.11 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.5 Turbo", "description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses.", "id": "glm-4.5-turbo", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3, "cache_read": 0.2 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.5V", "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding, image Q&A, OCR, and document parsing, with strong gains in front-end web coding, grounding, and spatial reasoning.", "id": "glm-4.5v", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 65000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.8, "cache_read": 0.11 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 65000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.8, "cache_read": 0.11 } } ], "context_length": 65000, "max_model_len": 65000, "max_input_tokens": 65000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "ZhipuAI: GLM 4.5 Air", "description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a \"thinking mode\" for advanced reasoning and tool use, and a \"non-thinking mode\" for real-time interaction.", "id": "glm-4.5-air", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.1, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.1, "cache_read": 0.03 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.6 (free)", "description": "GLM-4.6 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 200k tokens. GLM-4.6 delivers significantly enhanced capabilities in reasoning, code generation, and agent alignment. It supports a hybrid inference mode with two options, a \"thinking mode\" designed for complex reasoning and tool use, and a \"non-thinking mode\" optimized for instant responses.", "id": "glm-4.6:free", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.6", "description": "Compared with GLM-4.5, this generation brings several key improvements:\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.", "id": "glm-4.6", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.2, "cache_read": 0.11 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.2, "cache_read": 0.11 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.6V", "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts and charts directly as visual inputs, and integrates native multimodal function calling to connect perception with downstream tool execution. The model also enables interleaved image-text generation and UI reconstruction workflows, including screenshot-to-HTML synthesis and iterative visual editing.", "id": "glm-4.6v", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 131000, "pricing": { "type": "per_million_tokens", "input": 0.3, "output": 0.9, "cache_read": 0.05 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "ZhipuAI: GLM 4.7 (free)", "description": "GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.", "id": "glm-4.7:free", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 2 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.7", "description": "GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.", "id": "glm-4.7", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.2, "cache_read": 0.11 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.2, "cache_read": 0.11 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.7 Flash (free)", "description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.", "id": "glm-4.7-flash:free", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 64000, "pricing": { "type": "per_request", "coefficient": 1 } } ], "context_length": 64000, "max_model_len": 64000, "max_input_tokens": 64000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 4.7 Flash", "description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.", "id": "glm-4.7-flash", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.07, "output": 0.4, "cache_read": 0.01 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.07, "output": 0.4, "cache_read": 0.01 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5 (free)", "description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.", "id": "glm-5:free", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 3 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5", "description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.", "id": "glm-5", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.2, "cache_read": 0.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.2, "cache_read": 0.2 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5 Turbo", "description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.", "id": "glm-5-turbo", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.2, "output": 4, "cache_read": 0.24 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1.2, "output": 4, "cache_read": 0.24 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5.1 (free)", "description": "GLM-5.1 is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.", "id": "glm-5.1:free", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 3 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5.1", "description": "GLM-5.1 is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.", "id": "glm-5.1", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.2, "cache_read": 0.26 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.2, "cache_read": 0.26 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5.2 (free)", "description": "GLM-5.2 is Z.ai's most advanced flagship model for agentic software engineering, featuring a usable 1M-token context window — a 5x leap over its predecessor — enabling agents to hold entire repositories in working memory across extended multi-step sessions. Built on the GLM-5 744B Mixture-of-Experts architecture (40B active parameters, 28.5T training tokens) with DeepSeek Sparse Attention, it introduces High and Max thinking-effort modes for deeper reasoning on complex tasks. GLM-5.2 excels at long-horizon autonomous workflows, multi-step tool use, and large-scale code generation, with the capacity to sustain autonomous agent execution loops for hours without human intervention. Ideal for repo-scale code synthesis, complex instruction decomposition, and production-grade agentic pipelines.", "id": "glm-5.2:free", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 40000, "pricing": { "type": "per_request", "coefficient": 3 } } ], "context_length": 40000, "max_model_len": 40000, "max_input_tokens": 40000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "ZhipuAI: GLM 5.2", "description": "GLM-5.2 is Z.ai's most advanced flagship model for agentic software engineering, featuring a usable 1M-token context window — a 5x leap over its predecessor — enabling agents to hold entire repositories in working memory across extended multi-step sessions. Built on the GLM-5 744B Mixture-of-Experts architecture (40B active parameters, 28.5T training tokens) with DeepSeek Sparse Attention, it introduces High and Max thinking-effort modes for deeper reasoning on complex tasks. GLM-5.2 excels at long-horizon autonomous workflows, multi-step tool use, and large-scale code generation, with the capacity to sustain autonomous agent execution loops for hours without human intervention. Ideal for repo-scale code synthesis, complex instruction decomposition, and production-grade agentic pipelines.", "id": "glm-5.2", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.2, "cache_read": 0.26 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1, "output": 3.2, "cache_read": 0.26 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "none", "minimal", "low", "medium", "high", "xhigh", "max" ] } }, { "name": "ZhipuAI: GLM 5.3", "description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.", "id": "glm-5.3", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.4, "output": 4.4, "cache_read": 0.26 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.4, "output": 4.4, "cache_read": 0.26 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "high", "max" ] } }, { "name": "ZhipuAI: GLM 5.3 Flash", "description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.", "id": "glm-5.3-flash", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.5, "cache_read": 0.03 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "zhipuai", "name": "ZhipuAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.15, "output": 0.5, "cache_read": 0.03 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "high", "max" ] } }, { "name": "MoonshotAI: Kimi K2 Thinking", "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.", "id": "kimi-k2-thinking", "object": "model", "created": 1788985190, "owned_by": "moonshotai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.5, "cache_read": 0.12 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "moonshotai", "name": "MoonshotAI", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 2.5, "cache_read": 0.12 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MoonshotAI: Kimi K2.5", "description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.", "id": "kimi-k2.5", "object": "model", "created": 1788985190, "owned_by": "moonshotai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.5, "cache_read": 0.1 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "moonshotai", "name": "MoonshotAI", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.4, "output": 2.5, "cache_read": 0.1 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MoonshotAI: Kimi K2.6", "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. Its agent swarm architecture scales to hundreds of parallel sub-agents for autonomous task decomposition - delivering documents, websites, and spreadsheets in a single run without human oversight.", "id": "kimi-k2.6", "object": "model", "created": 1788985190, "owned_by": "moonshotai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 3, "cache_read": 0.16 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "moonshotai", "name": "MoonshotAI", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 3, "cache_read": 0.16 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MoonshotAI: Kimi K2.7 Code", "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.", "id": "kimi-k2.7-code", "object": "model", "created": 1788985190, "owned_by": "moonshotai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.75, "output": 3.5, "cache_read": 0.19 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "moonshotai", "name": "MoonshotAI", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.75, "output": 3.5, "cache_read": 0.19 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "MoonshotAI: Kimi K3", "description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.", "id": "kimi-k3", "object": "model", "created": 1788985190, "owned_by": "moonshotai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_read": 0.3 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "moonshotai", "name": "MoonshotAI", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 3, "output": 15, "cache_read": 0.3 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "high", "max" ] } }, { "name": "Xiaomi: Mimo V2.5", "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.", "id": "mimo-v2.5", "object": "model", "created": 1788985190, "owned_by": "xiaomi", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.28, "cache_read": 0.0028 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "xiaomi", "name": "Xiaomi", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0.14, "output": 0.28, "cache_read": 0.0028 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "Xiaomi: MiMo V2.5 Pro", "description": "MiMo V2.5 Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.", "id": "mimo-v2.5-pro", "object": "model", "created": 1788985190, "owned_by": "xiaomi", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 4.5, "cache_read": 0.0036 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": true, "providers": [ { "id": "xiaomi", "name": "Xiaomi", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 1.5, "output": 4.5, "cache_read": 0.0036 } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "StepFun: Step 3.5 Flash", "description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.", "id": "step-3.5-flash", "object": "model", "created": 1788985190, "owned_by": "stepfun", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.02 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "stepfun", "name": "StepFun", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.1, "output": 0.3, "cache_read": 0.02 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "StepFun: Step 3.7 Flash", "description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.\nDesigned for coding, agentic workflows, structured outputs, and long-context productivity tasks.", "id": "step-3.7-flash", "object": "model", "created": 1788985190, "owned_by": "stepfun", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.15, "cache_read": 0.04 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "stepfun", "name": "StepFun", "tokens": 256000, "pricing": { "type": "per_million_tokens", "input": 0.2, "output": 1.15, "cache_read": 0.04 } } ], "context_length": 256000, "max_model_len": 256000, "max_input_tokens": 256000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "OumiAI: Halloumi 8B", "description": "HallOumi-8B is a SOTA hallucination detection model, outperforming DeepSeek R1, OpenAI o1, Google Gemini 1.5 Pro, and Claude Sonnet 3.5 at only 8 billion parameters!", "id": "halloumi-8b", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.2 } } ], "context_length": 16000, "max_model_len": 16000, "max_input_tokens": 16000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Sao10K: L3 8B Lunaris", "description": "Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge.\nCreated by Sao10k, this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning.", "id": "l3-lunaris-8b", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.05 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.05, "output": 0.05 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Sao10K: L3 8B Stheno v3.2", "description": "L3-8B-Stheno-v3.2 is a sophisticated language model developed by Sao10K, representing the sixth iteration of the Stheno series. Trained on an H100 SXM GPU over approximately 24 hours, this model combines creative writing capabilities with assistant-style functionality. It's built upon the LLaMA architecture and has been fine-tuned using four carefully curated datasets, including writing prompts, instruct data, and filtered conversational logs.", "id": "l3-8b-stheno-v3.2", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.2 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Orenguteng: Llama 3.1 8B Lexi v2", "description": "Llama 3.1 8B Lexi V2 is an advanced language model based on Meta's Llama-3.1-8B-Instruct architecture. This version offers enhanced compliance and intelligence, designed for flexible text generation tasks. The model demonstrates impressive performance with a 77.92% accuracy on IFEval (0-Shot) testing.", "id": "llama-3.1-8b-lexi-uncensored-v2", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 16000, "pricing": { "type": "per_million_tokens", "input": 0.8, "output": 1.2 } } ], "context_length": 16000, "max_model_len": 16000, "max_input_tokens": 16000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "Sao10K: L3 70B Euryale v2.1", "description": "L3-70B-Euryale-v2.1 is a large language model created by Sao10K, a prominent AI model developer and maintainer. This 70 billion parameter model is designed as a more capable sibling to Sao10K's previous L3-8B-Stheno-v3.1 and L3-8B-Stheno-v3.2 models, with enhanced capabilities in areas like prompt adherence, anatomy/spatial awareness, and adapting to unique formatting. As described on the Sao10K's maintainer profile, this model was trained over 8 NVIDIA H100 SXM GPUs and aims to be a \"big brained version of Stheno.\"", "id": "l3-70b-euryale-v2.1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.7, "output": 0.8 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 0.7, "output": 0.8 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": false } }, { "name": "HuggingFace: Gemma-4-31B-Agares-v1", "description": "Gemma 4 31B DELLA merge testbed combining multiple roleplay donors for the upcoming Goetia line.", "id": "gemma-4-31b-agares-v1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Animus-V14.1", "description": "Full fine-tune of Gemma 4 31B for roleplay and chat with thinking and vision support retained.", "id": "gemma-4-31b-animus-v14.1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-AssGuard", "description": "Experimental Gemma 4 31B creative merge blending literary, adventure, and roleplay donors.", "id": "gemma-4-31b-assguard", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Aura-4o-Rebirth-Merged", "description": "Full BF16 merge of Aura Rebirth LoRA into Gemma 4 31B with multimodal tensors preserved.", "id": "gemma-4-31b-aura-4o-rebirth-merged", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled", "description": "Gemma 4 31B full fine-tune distilled from Claude Opus 4.6 reasoning traces.", "id": "gemma-4-31b-claude-4.6-opus-reasoning-distilled", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Claude-Opus-Distill-v2", "description": "Gemma 4 31B fine-tune distilled from Claude Opus 4.6 high-effort reasoning for coding and analysis.", "id": "gemma-4-31b-claude-opus-distill-v2", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Cognitive-Unshackled", "description": "Gemma 4 31B fine-tune with reduced alignment refusals for creative use.", "id": "gemma-4-31b-cognitive-unshackled", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Dark-Gemistry", "description": "Gemma 4 31B creative roleplay merge with StyleTune voice shaping for darker fiction prose.", "id": "gemma-4-31b-dark-gemistry", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-DarkIdol", "description": "Gemma 4 31B roleplay fine-tune for expressive character dialogue.", "id": "gemma-4-31b-darkidol", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Darwin-Frankenstein-Ghoul", "description": "Darwin V6 evolutionary merge of Gemma 4 31B-it and Claude Opus distill for stronger reasoning.", "id": "gemma-4-31b-darwin-frankenstein-ghoul", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Equinox", "description": "Gemma 4 31B interactive-fiction fine-tune balancing dark adventure and slice-of-life storytelling.", "id": "gemma-4-31b-equinox", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Fable-5-Agent-Distill", "description": "Gemma 4 31B LoRA distilled on Fable 5 agentic coding traces while preserving vision capability.", "id": "gemma-4-31b-fable-5-agent-distill", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Fabled", "description": "Gemma 4 31B conversational fine-tune with characterful multi-turn dialogue.", "id": "gemma-4-31b-fabled", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Garnet", "description": "Gemma 4 31B fine-tune focused on prose quality, longform writing, and roleplay.", "id": "gemma-4-31b-garnet", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-GarnetV2", "description": "Gemma 4 31B writing fine-tune with stronger roleplay and fantasy/sci-fi training.", "id": "gemma-4-31b-garnetv2", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Gembrain", "description": "Gemma 4 31B reasoning-oriented fine-tune for clearer multi-step answers.", "id": "gemma-4-31b-gembrain", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Gembrain-uncensored-heretic", "description": "Uncensored Gembrain variant of Gemma 4 31B for freer creative and roleplay use.", "id": "gemma-4-31b-gembrain-uncensored-heretic", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Gembrain-X-Core", "description": "Successor rebuild of Gembrain for creative roleplay with strong prompt adherence and swipe variety.", "id": "gemma-4-31b-gembrain-x-core", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Gemopus", "description": "Gemma 4 31B fine-tune focused on stable reasoning and clear, structured answers.", "id": "gemma-4-31b-gemopus", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Gemsicle", "description": "Gemma 4 31B merge aiming for creative prose and authentic characters without losing base intelligence.", "id": "gemma-4-31b-gemsicle", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Glamour", "description": "Gemma 4 31B fine-tune that turns natural-language briefs into self-contained front-end web designs.", "id": "gemma-4-31b-glamour", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Glistening-Gem-v1.0", "description": "Experimental Gemma 4 31B merge of Artemis, MeroMero, and Ortenzya for diverse creative prose.", "id": "gemma-4-31b-glistening-gem-v1.0", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Gutenberg", "description": "Gemma 4 31B fine-tune for literary, novelistic prose in the Gutenberg writing series.", "id": "gemma-4-31b-gutenberg", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Isometry-RP", "description": "Gemma 4 31B roleplay and creative-writing merge based on google/gemma-4-31B-it.", "id": "gemma-4-31b-isometry-rp", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-K1-v5", "description": "Gemma 4 31B post-trained with SFT and GRPO for consistent reasoning and logic.", "id": "gemma-4-31b-k1-v5", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Lilith-v1.0", "description": "Uncensored Gemma 4 31B roleplay fine-tune built for lively character cards and creative writing.", "id": "gemma-4-31b-lilith-v1.0", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Melinoe", "description": "Gemma 4 31B multimodal fine-tune for empathetic, intellectually engaging personal conversation.", "id": "gemma-4-31b-melinoe", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Mero-Artemis-v0.3.1", "description": "Gemma 4 31B creative writing and roleplay merge in the Mero-Artemis line.", "id": "gemma-4-31b-mero-artemis-v0.3.1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-MeroMero", "description": "Gemma 4 31B creative fine-tune with diverse, less verbose writing style.", "id": "gemma-4-31b-meromero", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Musica-v1", "description": "Gemma 4 31B fine-tune for roleplay, story generation, and conversation.", "id": "gemma-4-31b-musica-v1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Novelist", "description": "Gemma 4 31B merge tuned for long descriptive prose that stays fluid without feeling overwrought.", "id": "gemma-4-31b-novelist", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Pantheon-Reasoning-1.1", "description": "Gemma 4 StyleTune fine-tune with writer-style reasoning traces for roleplay and interactive fiction.", "id": "gemma-4-31b-pantheon-reasoning-1.1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Queen", "description": "Gemma 4 31B fine-tune for bold, persona-rich creative writing and roleplay.", "id": "gemma-4-31b-queen", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-SDFT-Heretic-RP", "description": "Gemma 4 31B roleplay fine-tune with reduced refusals for creative character work.", "id": "gemma-4-31b-sdft-heretic-rp", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Sphinsikus-Chronist", "description": "Gemma 4 31B creative fine-tune focused on chronicle-style storytelling and roleplay.", "id": "gemma-4-31b-sphinsikus-chronist", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Sprinkle-Vanilla", "description": "Continued pretrain on Gemma 4 31B base, merged into gemma-4-31B-it for a milder Sprinkle variant.", "id": "gemma-4-31b-sprinkle-vanilla", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-StyleTune", "description": "Surgical Gemma 4 31B fine-tune that cuts cliches and reshapes writing style while keeping base capability.", "id": "gemma-4-31b-styletune", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-The-DECKARD-HERETIC-UNCENSORED-Thinking", "description": "Uncensored Gemma 4 31B Heretic fine-tune on The DECKARD datasets for character depth and thinking.", "id": "gemma-4-31b-the-deckard-heretic-uncensored-thinking", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Gemma-4-31B-Versipellis", "description": "Gemma 4 31B character-locked roleplay merge for dialogue-forward, in-character conversation.", "id": "gemma-4-31b-versipellis", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: GLM-4.6-Derestricted-v5", "description": "Derestricted GLM-4.6 variant with reduced refusals while preserving reasoning quality.", "id": "glm-4.6-derestricted-v5", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 200000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 200000, "max_model_len": 200000, "max_input_tokens": 200000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Anko", "description": "Qwen3.5-27B distillation from Doubao Seed 2.0 for better reasoning and less looping.", "id": "qwen3.5-27b-anko", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Blossom-V6.4-Derestricted", "description": "Qwen3.5-27B conversational post-train following Blossom V6.3 recipe with light multimodal retention. Derestricted variant.", "id": "qwen3.5-27b-blossom-v6.4-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Blossom-V6.4-Derestricted-Lite", "description": "Qwen3.5-27B conversational post-train following Blossom V6.3 recipe with light multimodal retention. Lite derestricted variant.", "id": "qwen3.5-27b-blossom-v6.4-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-BlueStar-Derestricted", "description": "Qwen3.5-27B fine-tune for conversation and roleplay with thinking support. Derestricted variant.", "id": "qwen3.5-27b-bluestar-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-BlueStar-Derestricted-Lite", "description": "Qwen3.5-27B fine-tune for conversation and roleplay with thinking support. Lite derestricted variant.", "id": "qwen3.5-27b-bluestar-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-BlueStar-v2-Derestricted", "description": "BlueStar v2 with less repetition, better intelligence, and thinking support. Derestricted variant.", "id": "qwen3.5-27b-bluestar-v2-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-BlueStar-v2-Derestricted-Lite", "description": "BlueStar v2 with less repetition, better intelligence, and thinking support. Lite derestricted variant.", "id": "qwen3.5-27b-bluestar-v2-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-BlueStar-v3-Derestricted", "description": "Qwen3.5-27B fine-tune for roleplay with GLM-5/Kimi reasoning data. Supports thinking and non-thinking modes. Derestricted variant.", "id": "qwen3.5-27b-bluestar-v3-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-BlueStar-v3-Derestricted-Lite", "description": "Qwen3.5-27B fine-tune for roleplay with GLM-5/Kimi reasoning data. Supports thinking and non-thinking modes. Lite derestricted variant.", "id": "qwen3.5-27b-bluestar-v3-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted", "description": "Qwen3.5-27B fine-tune with Claude Opus 4.6 reasoning distillation for math and logic. Derestricted variant.", "id": "qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-Derestricted-Lite", "description": "Qwen3.5-27B fine-tune with Claude Opus 4.6 reasoning distillation for math and logic. Lite derestricted variant.", "id": "qwen3.5-27b-claude-4.6-opus-reasoning-distilled-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Dark-Nexus-v3.0-Derestricted", "description": "Qwen3.5-27B creative merge tuned for darker fiction, roleplay, and uncensored writing. Derestricted variant.", "id": "qwen3.5-27b-dark-nexus-v3.0-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Dark-Nexus-v3.0-Derestricted-Lite", "description": "Qwen3.5-27B creative merge tuned for darker fiction, roleplay, and uncensored writing. Lite derestricted variant.", "id": "qwen3.5-27b-dark-nexus-v3.0-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Derestricted", "description": "Derestricted Qwen3.5-27B with reduced refusals and strong reasoning.", "id": "qwen3.5-27b-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Derestricted-Aconite-v0", "description": "Qwen3.5-27B fine-tune based on a derestricted checkpoint in the Aconite experimental line.", "id": "qwen3.5-27b-derestricted-aconite-v0", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-earica-Derestricted", "description": "Qwen3.5-27B fine-tune for creative text generation and dialogue. Derestricted variant.", "id": "qwen3.5-27b-earica-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-earica-Derestricted-Lite", "description": "Qwen3.5-27B fine-tune for creative text generation and dialogue. Lite derestricted variant.", "id": "qwen3.5-27b-earica-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Enteles-v0-Derestricted", "description": "WAVE merge of Qwen3.5-27B donors for a less restricted generalist with vision weights grafted. Derestricted variant.", "id": "qwen3.5-27b-enteles-v0-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Enteles-v0-Derestricted-Lite", "description": "WAVE merge of Qwen3.5-27B donors for a less restricted generalist with vision weights grafted. Lite derestricted variant.", "id": "qwen3.5-27b-enteles-v0-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Infracelestial", "description": "Qwen3.5-27B roleplay fine-tune for character-driven dialogue.", "id": "qwen3.5-27b-infracelestial", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Marvin-DPO-V2-Derestricted", "description": "Literary writing and roleplay fine-tune with DPO to reduce repetition and AI-isms. Derestricted variant.", "id": "qwen3.5-27b-marvin-dpo-v2-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite", "description": "Literary writing and roleplay fine-tune with DPO to reduce repetition and AI-isms.", "id": "qwen3.5-27b-marvin-dpo-v2-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Marvin-V2-Derestricted", "description": "Qwen3.5-27B fine-tune for high-quality literary writing and roleplay. Derestricted variant.", "id": "qwen3.5-27b-marvin-v2-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Marvin-V2-Derestricted-Lite", "description": "Qwen3.5-27B fine-tune for high-quality literary writing and roleplay.", "id": "qwen3.5-27b-marvin-v2-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Melinoe-Derestricted", "description": "Qwen3.5-27B multimodal fine-tune for empathetic, intellectually engaging personal conversation. Derestricted variant.", "id": "qwen3.5-27b-melinoe-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Melinoe-Derestricted-Lite", "description": "Qwen3.5-27B multimodal fine-tune for empathetic, intellectually engaging personal conversation. Lite derestricted variant.", "id": "qwen3.5-27b-melinoe-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Musica-v1", "description": "Qwen3.5-27B fine-tune for roleplay, story generation, and conversational dialogue.", "id": "qwen3.5-27b-musica-v1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-NaNovel-Derestricted", "description": "Creative writing model for long-form fiction, scene control, and literary tasks. Derestricted variant.", "id": "qwen3.5-27b-nanovel-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-NaNovel-Derestricted-Lite", "description": "Creative writing model for long-form fiction, scene control, and literary tasks.", "id": "qwen3.5-27b-nanovel-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted", "description": "Merged Qwen3.5-27B for unaligned creative and roleplay use. Derestricted variant.", "id": "qwen3.5-27b-omega-evolution-v2.0-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite", "description": "Merged Qwen3.5-27B for unaligned creative and roleplay use. Lite derestricted variant.", "id": "qwen3.5-27b-omega-evolution-v2.0-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted", "description": "Updated Omega Evolution merge with cleaner dataset formatting. Derestricted variant.", "id": "qwen3.5-27b-omega-evolution-v2.2-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite", "description": "Updated Omega Evolution merge with cleaner dataset formatting. Lite derestricted variant.", "id": "qwen3.5-27b-omega-evolution-v2.2-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Omnimerge-v2-Derestricted", "description": "Three-way merged Qwen3.5-27B balancing reasoning and roleplay performance. Derestricted variant.", "id": "qwen3.5-27b-omnimerge-v2-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Omnimerge-v2-Derestricted-Lite", "description": "Three-way merged Qwen3.5-27B balancing reasoning and roleplay performance. Lite derestricted variant.", "id": "qwen3.5-27b-omnimerge-v2-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Queen-Derestricted", "description": "Qwen3.5-27B fine-tune for Queen-style roleplay and persona-driven writing. Derestricted variant.", "id": "qwen3.5-27b-queen-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Queen-Derestricted-Lite", "description": "Qwen3.5-27B fine-tune for Queen-style roleplay and persona-driven writing. Lite derestricted variant.", "id": "qwen3.5-27b-queen-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-QuettaLLMs-Koreasoner-V3-Derestricted", "description": "Korean reasoning fine-tune of Qwen3.5-27B with concise final answers. Derestricted variant.", "id": "qwen3.5-27b-quettallms-koreasoner-v3-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-QuettaLLMs-Koreasoner-V3-Derestricted-Lite", "description": "Korean reasoning fine-tune of Qwen3.5-27B with concise final answers. Lite derestricted variant.", "id": "qwen3.5-27b-quettallms-koreasoner-v3-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-RpRMax-v1", "description": "RPMax fine-tune for creative writing and roleplay with per-turn reasoning steps.", "id": "qwen3.5-27b-rprmax-v1", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Vivid-Durian", "description": "Derestricted Qwen3.5-27B with reduced refusals and strong reasoning.", "id": "qwen3.5-27b-vivid-durian", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Writer-Derestricted", "description": "Qwen3.5-27B writing and roleplay fine-tune using curriculum learning on literary data. Derestricted variant.", "id": "qwen3.5-27b-writer-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Writer-Derestricted-Lite", "description": "Qwen3.5-27B writing and roleplay fine-tune using curriculum learning on literary data.", "id": "qwen3.5-27b-writer-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Writer-V2-Derestricted", "description": "Second Writer release with improved book-chunk writing and anti-repetition training. Derestricted variant.", "id": "qwen3.5-27b-writer-v2-derestricted", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "HuggingFace: Qwen3.5-27B-Writer-V2-Derestricted-Lite", "description": "Second Writer release with improved book-chunk writing and anti-repetition training. Lite derestricted variant.", "id": "qwen3.5-27b-writer-v2-derestricted-lite", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0.6, "output": 1.2 } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true } }, { "name": "DeepSeek: DeepSeek V4 Flash (DevPass)", "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.", "id": "deepseek-v4-flash:dev", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.12, "output": 0.2 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.12, "output": 0.2 } } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true, "devpass_only": true } }, { "name": "DeepSeek: DeepSeek V4 Flash 0731 (DevPass)", "description": "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.", "id": "deepseek-v4-flash-0731:dev", "object": "model", "created": 1788985190, "owned_by": "deepseekai", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.12, "output": 0.2 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 400000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.12, "output": 0.2 } } } ], "context_length": 400000, "max_model_len": 400000, "max_input_tokens": 400000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true, "devpass_only": true } }, { "name": "Xiaomi: Mimo V2.5 (DevPass)", "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.", "id": "mimo-v2.5:dev", "object": "model", "created": 1788985190, "owned_by": "xiaomi", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.14, "output": 0.28 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.14, "output": 0.28 } } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "devpass_only": true } }, { "name": "MiniMax: MiniMax M2.7 (DevPass)", "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.", "id": "minimax-m2.7:dev", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 180000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 1, "reference": { "input": 0.3, "output": 1.2 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 180000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 1, "reference": { "input": 0.3, "output": 1.2 } } } ], "context_length": 180000, "max_model_len": 180000, "max_input_tokens": 180000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true, "devpass_only": true } }, { "name": "Alibaba: Qwen3.8 27B (DevPass)", "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks.", "id": "qwen3.8-27b:dev", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 1, "reference": { "input": 0.45, "output": 3.2 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 1, "reference": { "input": 0.45, "output": 3.2 } } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "devpass_only": true } }, { "name": "ZhipuAI: GLM 5.3 (DevPass)", "description": "GLM-5.3 is Z.ai's flagship text-only reasoning model (744B total, 40B active, FP8). It uses the same base as GLM-5.2, with gains from post-training on coding and long-horizon agent tasks. It supports a 262K-token context window. Reasoning is always on, with reasoning_effort low, high, or max (default max).", "id": "glm-5.3:dev", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 2, "reference": { "input": 1.4, "output": 4.4 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 262000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 2, "reference": { "input": 1.4, "output": 4.4 } } } ], "context_length": 262000, "max_model_len": 262000, "max_input_tokens": 262000, "metadata": { "vision": false, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "high", "max" ], "devpass_only": true } }, { "name": "ZhipuAI: GLM 5.3 Flash (DevPass)", "description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.", "id": "glm-5.3-flash:dev", "object": "model", "created": 1788985190, "owned_by": "zhipuai", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.15, "output": 0.5 } }, "endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "premium_model": false, "providers": [ { "id": "electronhub", "name": "Electron Hub", "tokens": 1000000, "pricing": { "type": "per_million_tokens", "input": 0, "output": 0, "plan": "devpass", "multiplier": 0.5, "reference": { "input": 0.15, "output": 0.5 } } } ], "context_length": 1000000, "max_model_len": 1000000, "max_input_tokens": 1000000, "metadata": { "vision": true, "function_call": true, "web_search": false, "reasoning": true, "supported_reasoning_efforts": [ "low", "high", "max" ], "devpass_only": true } }, { "name": "Stability: Stable Diffusion XL", "description": "A text-to-image generative AI model that creates beautiful images.", "id": "sdxl", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.007 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.007 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Stability: Stable Diffusion XL Turbo", "description": "SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation.", "id": "sdxl-turbo", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.05 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.05 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "ByteDance: Stable Diffusion XL Lightning", "description": "SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps.", "id": "sdxl-lightning", "object": "model", "created": 1788985190, "owned_by": "bytedance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.002 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "bytedance", "name": "ByteDance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.002 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Stability: Stable Diffusion 3", "description": "A text-to-image model with greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.", "id": "stable-diffusion-3", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Stability: Stable Diffusion 3 Medium", "description": "Stable Diffusion 3 Medium is a 2 billion parameter text-to-image model developed by Stability AI. It excels at photorealism, typography, and prompt following.", "id": "stable-diffusion-3-2b", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Stability: Stable Diffusion 3.5 Large", "description": "A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.", "id": "stable-diffusion-3.5-large", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Stability: Stable Diffusion 3.5 Turbo", "description": "A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps.", "id": "stable-diffusion-3.5-turbo", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.12 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.12 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Krea: Krea 2 Raw", "description": "Krea 2 Raw is the base release checkpoint in the Krea 2 model family, published as an open-weight 12B text-to-image model before the additional post-training and distillation used for Krea 2 Turbo. Krea describes it as a better fit for finetuning, post-training, and custom domain work than for general inference, making it especially relevant for LoRA training and other open-model customization workflows.", "id": "krea-2-raw", "object": "model", "created": 1788985190, "owned_by": "krea", "tokens": 2000, "pricing": { "type": "per_image", "coefficient": 0.015 }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "premium_model": true, "providers": [ { "id": "krea", "name": "Krea", "tokens": 2000, "pricing": { "type": "per_image", "coefficient": 0.015 } } ], "context_length": 2000, "max_model_len": 2000, "max_input_tokens": 2000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Krea: Krea 2 Turbo", "description": "Krea 2 Turbo is the open-source Krea image endpoint exposed on Runware for fast, low-cost text-to-image generation. It focuses on prompt-driven generation rather than the richer Krea 2 reference workflow, making it a better fit for simple production pipelines, accelerated runtimes, and workflows that benefit from open-model compatibility such as LoRA-based customization.", "id": "krea-2-turbo", "object": "model", "created": 1788985190, "owned_by": "krea", "tokens": 2000, "pricing": { "type": "per_image", "coefficient": 0.015 }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "premium_model": true, "providers": [ { "id": "krea", "name": "Krea", "tokens": 2000, "pricing": { "type": "per_image", "coefficient": 0.015 } } ], "context_length": 2000, "max_model_len": 2000, "max_input_tokens": 2000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Google: Nano Banana (Gemini 2.5 Flash Image)", "description": "Google Gemini 2.5 Flash Image (Nano Banana) generates and edits images quickly, with solid character consistency, multi-image blending, and natural-language transforms.", "id": "gemini-2.5-flash-image", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Google: Nano Banana 2", "description": "Google Nano Banana 2 (Gemini 3.1 Flash Image) is the next Flash image model, faster and more detailed than Gemini 2.5 Flash Image for generation and light editing.", "id": "nano-banana-2", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Google: Nano Banana 2 (image-to-image)", "description": "Google Nano Banana 2 Edit transforms or composes source images with Gemini 3.1 Flash Image from a text prompt.", "id": "nano-banana-2-edit", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Google: Nano Banana 2 Lite (image-to-image)", "description": "Google Nano Banana 2 Lite Edit is a lighter Banana 2 editing path for faster, cheaper prompt-guided image transforms.", "id": "nano-banana-2-lite-edit", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Google: Nano Banana Pro", "description": "Google Nano Banana Pro (Gemini 3 Pro Image) is Google's higher-quality image model for complex prompts, text-in-image, and multi-turn editing.", "id": "nano-banana-pro", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.2 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.2 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Google: Nano Banana Pro (image-to-image)", "description": "Google Nano Banana Pro Edit is the Pro-tier editor with stronger instruction following and detail preservation than Flash or Banana 2 edit.", "id": "nano-banana-pro-edit", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Neta Art: Neta Lumina", "description": "Neta Lumina illustration model with multilingual natural-language prompting.", "id": "neta-lumina", "object": "model", "created": 1788985190, "owned_by": "neta-art", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "neta-art", "name": "Neta Art", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Neta Art: NetaYume Lumina Image 2.0 v40", "description": "NetaYume Lumina Image 2.0 v40 — anime/illustration checkpoint based on Lumina Image 2.0.", "id": "netayume-lumina-image-2.0-v40", "object": "model", "created": 1788985190, "owned_by": "neta-art", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "neta-art", "name": "Neta Art", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "HuggingFace: Chroma", "description": "Chroma is an open diffusion model for vibrant, stylized illustration and concept art from text prompts.", "id": "chroma", "object": "model", "created": 1788985190, "owned_by": "huggingface", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.02 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "huggingface", "name": "Hugging Face", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.02 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Xiaohongshu: Firered Image (image-to-image)", "description": "FireRed Image Edit from Xiaohongshu transforms a source image from a text prompt and can blend multiple reference images.", "id": "firered-image-edit", "object": "model", "created": 1788985190, "owned_by": "xiaohongshu", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "xiaohongshu", "name": "Xiaohongshu", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Qwen Image", "description": "An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.", "id": "qwen-image", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "864x1152", "1152x864", "1280x720", "720x1280", "832x1248", "1248x832", "1512x648" ] }, { "name": "Alibaba: Wan 2.2 Image", "description": "Wan 2.2 is powerful image generator model. Wan is an original, raw, un-distilled model which leads to advantages over distilled image models.", "id": "wan-2.2-image", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "864x1152", "1152x864", "1280x720", "720x1280", "832x1248", "1248x832", "1512x648" ] }, { "name": "Alibaba: Wan 2.7", "description": "Alibaba Wan 2.7 is a Tongyi text-to-image model for general photoreal and creative generation with solid bilingual prompt support.", "id": "wan-2.7", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.03 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.03 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Wan 2.7 Pro", "description": "Alibaba Wan 2.7 Pro is the higher-quality Wan 2.7 tier for sharper detail and stronger prompt adherence.", "id": "wan-2.7-pro", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Wan 2.7 Pro (image-to-image)", "description": "Alibaba Wan 2.7 Pro Edit is the Pro-tier Wan editor for higher-quality prompt-guided transforms and multi-image composition.", "id": "wan-2-7-pro-edit", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Qwen-Image 2512", "description": "Alibaba Qwen-Image 2512 model.", "id": "qwen-image-2512", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Alibaba: Qwen-Image Edit 2511", "description": "Alibaba Qwen-Image Edit 2511 for image editing workflows.", "id": "qwen-image-edit-2511", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Alibaba: Qwen Edit Uncensored (image-to-image)", "description": "Alibaba Qwen Edit Uncensored is a Qwen image-editing variant with fewer content filters for prompt-guided transforms of a source image.", "id": "qwen-edit-uncensored", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Qwen Image 2", "description": "Alibaba Qwen-Image 2 is a text-to-image model with strong bilingual English and Chinese text rendering and solid human realism.", "id": "qwen-image-2", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.05 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.05 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Qwen Image 2 (image-to-image)", "description": "Alibaba Qwen-Image 2 Edit transforms source images from text prompts and supports multi-image composition.", "id": "qwen-image-2-edit", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Qwen Image 2 Pro", "description": "Alibaba Qwen-Image 2 Pro is the higher-quality Qwen-Image 2 tier for sharper detail and stronger prompt adherence.", "id": "qwen-image-2-pro", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Qwen Image 2 Pro (image-to-image)", "description": "Alibaba Qwen-Image 2 Pro Edit is the Pro-tier Qwen editor for higher-fidelity source-image transforms from text prompts.", "id": "qwen-image-2-pro-edit", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Alibaba: Z-Image", "description": "Alibaba Z-Image text-to-image model.", "id": "z-image", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.02 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.02 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Alibaba: Z-Image Turbo", "description": "Alibaba Z-Image Turbo — faster Z-Image variant for quicker generations.", "id": "z-image-turbo", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.03 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.03 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: AAM XL Anime Mix v1.0", "description": "SDXL-aamXLAnimeMix_v10 is a text-to-image model that generates anime-style images.", "id": "sdxl-aamxl-anime-mix-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: amanatsu Illustrious v20", "description": "Amanatsu Illustrious v20 anime SDXL checkpoint hosted on ArliAI.", "id": "sdxl-amanatsu-illustrious-v-20", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Amanatsu (Illustrious) v1.1", "description": "Amanatsu Illustrious is a text-to-image model that generates anime-style images.", "id": "sdxl-amanatsu-illustrious-v11", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Animij v2", "description": "Animij v2 is a text-to-image model that generates anime-style images.", "id": "sdxl-animij-v2", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Animij v5", "description": "Animij v5 is a text-to-image model that generates anime-style images.", "id": "sdxl-animij-v5", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: ArliMix v1", "description": "ArliMix v1 is a text-to-image model that generates anime-style images.", "id": "sdxl-arlimix-v1", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Aungir T6AO45", "description": "Aungir T6AO45 is a text-to-image model that generates anime-style images.", "id": "sdxl-aungir-t6ao45", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Aungir TestA", "description": "Aungir TestA is a text-to-image model that generates anime-style images.", "id": "sdxl-aungir-testa", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: AutismMix Confetti", "description": "AutismMix_confetti is a small amount of AnimeConfettiTune and AutismMix_pony. Has less style swing than pony and better hands.", "id": "sdxl-autismmix-confetti", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: AutismMix Pony", "description": "AutismMix_pony is a merge of ponyv6 with loras, its more compatible with certain styles made for the base ponydiffusion model.", "id": "sdxl-autismmix-pony", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: BoleroMix (Illustrious) v2.90", "description": "BoleroMix_illustrious is a text-to-image model that generates anime-style images.", "id": "sdxl-boleromix-illustrious-v290", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: ComradeshipXL v1.4kc", "description": "This is a specialized model for high resolutions of 1.5K~1.75K. It is trained on a large dataset of anime images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "sdxl-comradeshipxl-v14kc", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Copycat (Illustrious) v4.0", "description": "Copycat_illustrious is a text-to-image model that generates anime-style images.", "id": "sdxl-copycat-illustrious-v40", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Copycat (Illustrious) v5.0", "description": "Copycat_illustrious is a text-to-image model that generates anime-style images.", "id": "sdxl-copycat-illustrious-v50", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Halcyon v1.9", "description": "This is a very robust model primarily focused on photorealism but capable of generating all types of images.", "id": "sdxl-halcyon-v19", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: IkaStrious v1.42 Stable", "description": "IkaStrious_v142Stable is a text-to-image model that generates anime-style images.", "id": "sdxl-ikastrious-v142-stable", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: IkaStriousXL v9.5", "description": "IkaStriousXL_v95 is a text-to-image model that generates anime-style images.", "id": "sdxl-ikastriousxl-v95", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Illustrij v1.0", "description": "Illustrij_v10 is a comic-anime-hybrid based checkpoint and digital art rendering with a touch of 3D on its way to semirealism", "id": "sdxl-illustrij-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Illustrij v1.7", "description": "Illustrij_v17 is a comic-anime-hybrid based checkpoint and digital art rendering with a touch of 3D on its way to semirealism", "id": "sdxl-illustrij-v17", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Illustrious BlackMagic v3.0", "description": "IllustriousBlackMagic_v30CLEAN is a text-to-image model that generates anime-style images.", "id": "sdxl-illustrious-blackmagic-v30", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Illustrious PencilXL v3.20", "description": "IllustriousPencilXL_v320 is a text-to-image model that generates anime-style images.", "id": "sdxl-illustrious-pencilxl-v320", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: IllustriousXL Mmmix v8.0", "description": "IllustriousXL_mmMix_v80 is a text-to-image model that generates anime-style images.", "id": "sdxl-illustriousxl-mmmix-v80", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: IllustriousXL Smoothft SOLID", "description": " A merge of SPO and NoobAI XL v-pred (the resulting model is normal) - it features richer solid colours and smoother gradients.", "id": "sdxl-illustriousxl-smoothft-solid", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Ilustmix v4.0", "description": "Ilustmix_v40 is a text-to-image model that generates anime-style images.", "id": "sdxl-ilustmix-v40", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Ilustmix v8.0", "description": "Ilustmix_v80 is a text-to-image model that generates anime-style images.", "id": "sdxl-ilustmix-v80", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Janku Illustrious v2.1", "description": "JankuV21Illustrious_v21 is a text-to-image model that generates anime-style images.", "id": "sdxl-janku-illustrious-v21", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Janku v4.0", "description": "Janku_v40 is a text-to-image model that generates anime-style images.", "id": "sdxl-janku-v40", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: KAI illustrious v1", "description": "KAI Illustrious v1 anime SDXL checkpoint hosted on ArliAI.", "id": "sdxl-kai-illustrious-v-1", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: KAI illustrious v2", "description": "KAI Illustrious v2 anime SDXL checkpoint hosted on ArliAI.", "id": "sdxl-kai-illustrious-v-2", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Kiwimix-XL v3", "description": "KiwimixXL_v3 is a text-to-image model that generates anime-style images.", "id": "sdxl-kiwimixxl-v3", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Lunarcherrymix v2.2 BaseIllustrxl20", "description": "LunarCherryMix - Mixed Illustrious model a lot of things. This model excels at producing vibrant anime-style artwork, opening the door to limitless creative exploration and beyond.", "id": "sdxl-lunarcherrymix-v22-baseillustrxl20", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Lunarcherrymix v2.3", "description": "LunarCherryMix - Mixed Illustrious model a lot of things. This model excels at producing vibrant anime-style artwork, opening the door to limitless creative exploration and beyond.", "id": "sdxl-lunarcherrymix-v23", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Miaomiao Harem v1.6G", "description": "MiaomiaoHarem_v16G is a text-to-image model that generates anime-style images.", "id": "sdxl-miaomiao-harem-v16g", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Naixl Mmmix v4.5", "description": "Naixl_mmMix_v45 is a text-to-image model that generates anime-style images. 4.5 Enhanced detail and color expression.", "id": "sdxl-naixl-mmmix-v45", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Naixl Mmmix v5.0", "description": "Naixl_mmMix_v50 is a text-to-image model that generates anime-style images. 5.0 enhances the realistic style, the original painting style is closer to 2.5D, and the texture of stockings has been improved due to personal hobbies.", "id": "sdxl-naixl-mmmix-v50", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Nonnette v0.50", "description": "Nonet is a miscellaneous Noob-based Eps merge model that can be found anywhere.\nBasically, if you follow the usage of Illustrious eps, you can use it without any problem.\nAlthough not limited to this model, I feel that it is necessary to adjust the quality prompts in a timely manner while watching the output, as too much quality prompting can stiffen the atmosphere.", "id": "sdxl-nonnette-v050", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Nova Anime XL IL v10.0", "description": "Nova Anime XL is Nova Anime: Anime/2.5D/3D checkpoint model for SDXL", "id": "sdxl-novaanimexl-ilv100", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Nova Anime XL IL v6.0", "description": "Nova Anime XL is Nova Anime: Anime/2.5D/3D checkpoint model for SDXL", "id": "sdxl-novaanimexl-ilv60", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Nova Furry XL Illustrious v10.0", "description": "A 2d/2.5d furry checkpoint model that can have great details on any type of furs, scales and feathers, which aims to be xl-fied Peaki Furry.", "id": "sdxl-novafurryxl-illustrious-v100", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Nova Orange XL v11.0", "description": "Nova Orange XL is anime checkpoint with detailed skin and depth.", "id": "sdxl-novaorangexl-v110", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Nova Unreal XL v7.0", "description": "Nova Unreal XL is semi-realistic anime checkpoint with detailed skin and depth.", "id": "sdxl-novaunrealxl-v70", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Oblivious Mix v1.0", "description": "Oblivious Mix is a text-to-image model that generates anime-style images.", "id": "sdxl-obliviousmix-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: One For All Anime (Illustrious)", "description": "One For All Anime W IL is a text-to-image model that generates anime-style images.", "id": "sdxl-oneforallanimew-il", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Persona Style (Illustrious)", "description": "Persona Style (Illustrious) is a text-to-image model that generates anime-style images.", "id": "sdxl-personastyle-il", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Plant Milk Model Suite (Almond)", "description": "Plant Milk Model Suite (Almond) is a text-to-image model that generates anime-style images.", "id": "sdxl-plantmilkmodelsuite-almond", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Plant Milk Model Suite (Coconut)", "description": "Plant Milk Model Suite (Coconut) is a text-to-image model that generates anime-style images.", "id": "sdxl-plantmilkmodelsuite-coconut", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Plant Milk Model Suite (Flax)", "description": "Plant Milk Model Suite (Flax) is a text-to-image model that generates anime-style images.", "id": "sdxl-plantmilkmodelsuite-flax", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Plant Milk Model Suite (Oat)", "description": "Plant Milk Model Suite (Oat) is a text-to-image model that generates anime-style images.", "id": "sdxl-plantmilkmodelsuite-oat", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Plant Milk Model Suite (Walnut)", "description": "Plant Milk Model Suite (Walnut) is a text-to-image model that generates anime-style images.", "id": "sdxl-plantmilkmodelsuite-walnut", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Praeclarus v2.0", "description": "Praeclarus is a text-to-image model that generates anime-style images.", "id": "sdxl-praeclarus-v20", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Prefect Illustrious XL v1.0", "description": "Prefect Illustrious XL v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-prefectillustriousxl-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Prefect Illustrious XL v1.0", "description": "Prefect Illustrious XL v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-prefectiousxl-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Richy Rich Mixi XL v1.0", "description": "Richy Rich Mixi XL v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-richyrichmixixl-v1", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Sakura Platinum v2025.03.09", "description": "Sakura Platinum v20250309 is a text-to-image model that generates anime-style images.", "id": "sdxl-sakuraplatinum-v20250309", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Shiitake Mix v2.0", "description": "Shiitake Mix v2.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-shiitakemix-v20", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Silence Mix v4.0", "description": "Silence Mix v4.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-silencemix-v40", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: SS Mix Illustrious v1.0", "description": "SS Mix Illustrious v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-ssmixillustrious-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Sudachi XL Illustrious v1.0", "description": "Sudachi XL Illustrious v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-sudachixlillustrious-v1", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Tanemo Mix v2.0", "description": "Tanemo Mix v2.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-tanemomix-v2", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Tanemo Mix v6.0", "description": "Tanemo Mix v6.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-tanemomix-v6", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: tN3 v8.0", "description": "tN3 v8.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-tn3-v8", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Toonify Illustrious v1.0", "description": "Toonify is an excellent model if you're looking for cartoonish renders. This is a versatile merged model.\nPrompt suggestions :use cartoon in prompt for more cartoonish images, you can use anime or realistic prompts both works the same.", "id": "sdxl-toonify-illustrious", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Vixons Illustrious v1.4", "description": "Vixons Illustrious v1.4 is a text-to-image model that generates anime-style images.", "id": "sdxl-vixonsillust-v14", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: wai Illustrious v1.30", "description": "wai Illustrious v1.30 is a text-to-image model that generates anime-style images.", "id": "sdxl-wai-illustrious-v130", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: wai Illustrious v1.40", "description": "wai Illustrious v1.40 is a text-to-image model that generates anime-style images.", "id": "sdxl-wai-illustrious-v140", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: waiCheapfastANI v1.0", "description": "The advantage of this model is that it can generate more stable images at lower resolutions, and the diversity of styles is also very good.", "id": "sdxl-waicheapfastani-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Zuki Anime Illustrious v4.0", "description": "Zuki Anime Illustrious v4.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-zukianimeill-v40", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Zuki Best Anime Mix v1.0", "description": "Zuki Best Anime Mix v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-zukibestanimemix-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Zuki Cute Illustrious v6.0", "description": "Zuki Cute Illustrious v6.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-zukicuteill-v60", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Zuki Kawaii Mix v1.0", "description": "Zuki Kawaii Mix v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-zukikawaimix-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: Zuki Soft Illustrious v1.0", "description": "Zuki Soft Illustrious v1.0 is a text-to-image model that generates anime-style images.", "id": "sdxl-zukisoftill-v10", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: TastyRice Magic on Paper (anime Guofeng Animation)", "description": "TastyRice Magic on Paper (anime Guofeng Animation) is a text-to-image model that generates anime-style images.", "id": "sdxl-tastyrice-magic-on-paper-anime-guofeng-animation", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Stability: TastyRice Lingyun Caijing (Zhencai World)", "description": "TastyRice Lingyun Caijing (Zhencai World) is a text-to-image model that generates anime-style images.", "id": "sdxl-tastyrice-lingyun-caijing-zhencai-world", "object": "model", "created": 1788985190, "owned_by": "stabilityai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "stabilityai", "name": "Stability AI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Fal: Animagine XL 3.1", "description": "Anime-themed text-to-image stable diffusion model.", "id": "animagine-xl-3.1", "object": "model", "created": 1788985190, "owned_by": "falai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "falai", "name": "Fal", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Fal: Animagine XL 4.0", "description": "Anime-themed text-to-image stable diffusion model.", "id": "animagine-xl-4.0", "object": "model", "created": 1788985190, "owned_by": "falai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "falai", "name": "Fal", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Fal: NoobAI XL", "description": "NoobAI XL is a text-to-image model that is based on the SDXL architecture and trained primarily for anime image generation. It uses the complete Danbooru and e621 datasets and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "noobai-xl", "object": "model", "created": 1788985190, "owned_by": "falai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "falai", "name": "Fal", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "NovelAI: NAI Diffusion Furry V3", "description": "A text-to-image model that generates furry-style images. It is trained on a large dataset of furry images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "nai-diffusion-furry-3", "object": "model", "created": 1788985190, "owned_by": "novelai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "novelai", "name": "NovelAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "NovelAI: NAI Diffusion Anime V3", "description": "A text-to-image model that generates anime-style images. It is trained on a large dataset of anime images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "nai-diffusion-3", "object": "model", "created": 1788985190, "owned_by": "novelai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "novelai", "name": "NovelAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "NovelAI: NAI Diffusion V4 Full", "description": "A text-to-image model that generates images. It is trained on a large dataset of images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "nai-diffusion-4-full", "object": "model", "created": 1788985190, "owned_by": "novelai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "novelai", "name": "NovelAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "NovelAI: NAI Diffusion V4 Curated", "description": "A text-to-image model that generates images. It is trained on a large dataset of images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "nai-diffusion-4-curated-preview", "object": "model", "created": 1788985190, "owned_by": "novelai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "novelai", "name": "NovelAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "NovelAI: NAI Diffusion V4.5 Full", "description": "A text-to-image model that generates images. It is trained on a large dataset of images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "nai-diffusion-4-5-full", "object": "model", "created": 1788985190, "owned_by": "novelai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "novelai", "name": "NovelAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "NovelAI: NAI Diffusion V4.5 Curated", "description": "A text-to-image model that generates images. It is trained on a large dataset of images and should be able to complete generation tasks excellently with as few lora models as possible.", "id": "nai-diffusion-4-5-curated", "object": "model", "created": 1788985190, "owned_by": "novelai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "novelai", "name": "NovelAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.044 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "512x1024", "1024x512", "832x1216", "1216x832", "704x1280", "1280x704", "768x1024", "1024x768" ] }, { "name": "Luma: Uni 1 (image-to-image)", "description": "Luma Uni 1 Edit transforms a source image from a text prompt for restyling and guided modifications.", "id": "luma-uni-1-edit", "object": "model", "created": 1788985190, "owned_by": "lumalabs", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "lumalabs", "name": "Luma", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Luma: Uni 1 Max (image-to-image)", "description": "Luma Uni 1 Max Edit is a higher-capability Luma editor for more demanding prompt-guided transforms from a source image.", "id": "luma-uni-1-max-edit", "object": "model", "created": 1788985190, "owned_by": "lumalabs", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "lumalabs", "name": "Luma", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Recraft: Recraft V4", "description": "Recraft V4 is a design-forward text-to-image model built for composition, color, typography, and production-ready raster assets for marketing, branding, and UI mockups.", "id": "recraft-v4", "object": "model", "created": 1788985190, "owned_by": "recraft", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "recraft", "name": "Recraft", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Recraft: V4 Pro", "description": "Recraft V4 Pro is the higher-resolution Recraft V4 tier for print-oriented and large-format creative assets, with the same design taste and finer detail.", "id": "recraft-v4-pro", "object": "model", "created": 1788985190, "owned_by": "recraft", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "recraft", "name": "Recraft", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "HiDream: HiDream I1 Fast", "description": "HiDream-I1 Fast is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.", "id": "hidream-i1-fast", "object": "model", "created": 1788985190, "owned_by": "hidream-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "hidream-ai", "name": "HiDream", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "HiDream: HiDream I1 Dev", "description": "HiDream-I1 Dev is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.", "id": "hidream-i1-dev", "object": "model", "created": 1788985190, "owned_by": "hidream-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.5 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "hidream-ai", "name": "HiDream", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.5 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "HiDream: HiDream I1 Full", "description": "HiDream-I1 Full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.", "id": "hidream-i1-full", "object": "model", "created": 1788985190, "owned_by": "hidream-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.8 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "hidream-ai", "name": "HiDream", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.8 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX.1 [schnell]", "description": "The fastest image generation model tailored for local development and personal use.", "id": "flux-schnell", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.005 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.005 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX.1 [dev]", "description": "A 12 billion parameter rectified flow transformer capable of generating images from text descriptions.", "id": "flux-dev", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX.1 [pro]", "description": "State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.", "id": "flux-pro", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.5 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.5 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: Flux1.1 [pro]", "description": "Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.", "id": "flux-1.1-pro", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.7 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.7 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX1.1 [pro] ultra", "description": "FLUX1.1 [pro] in ultra mode. Images are up to 4 megapixels.", "id": "flux-1.1-pro-ultra", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.8 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.8 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX1.1 [pro] ultra raw", "description": "FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.", "id": "flux-1.1-pro-ultra-raw", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 1 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX.2 [klein] 4B", "description": "FLUX.2 [klein] is an ultra-fast, distilled image model. It unifies image generation and editing in a single model, delivering state-of-the-art quality enabling interactive workflows, real-time previews, and latency-critical applications.", "id": "flux-2-klein-4b", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX.2 [klein] 9B", "description": "FLUX.2 [klein] 9B is an ultra-fast, distilled image model with enhanced quality. It unifies image generation and editing in a single model, delivering state-of-the-art quality enabling interactive workflows, real-time previews, and latency-critical applications.", "id": "flux-2-klein-9b", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.2 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.2 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: Flux 2 Max - Edit", "description": "FLUX.2 Max Edit from Black Forest Labs is the highest-fidelity FLUX.2 editing path, with strong prompt adherence, typography, and multi-image composition.", "id": "flux-2-max-edit", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "BlackForestLabs: Flux 2 Pro", "description": "FLUX.2 Pro from Black Forest Labs is a 32B production image model with reliable text-in-image, multi-reference consistency, and up to about 4MP output.", "id": "flux-2-pro", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "BlackForestLabs: FLUX.1 Krea [dev]", "description": "An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated \"AI look\".", "id": "flux-1-krea-dev", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.6 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.6 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "BlackForestLabs: FLUX.1 Kontext [dev]", "description": "FLUX.1 Kontext [dev] is a premium model with maximum performance and improved typography generation. It is a state-of-the-art image editing model from Black Forest Labs that allows you to edit images using text prompts. It’s the best in class for text-guided image editing and offers superior results compared to other models like OpenAI’s 4o/gpt-image-1.", "id": "flux-1-kontext-dev", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.8 }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "premium_model": false, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 0.8 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1568x672", "1504x688", "1456x720", "1392x752", "1328x800", "1248x832", "1184x880", "1104x944", "944x1104", "880x1184", "832x1248", "800x1328", "752x1392", "720x1456", "688x1504", "672x1568" ] }, { "name": "BlackForestLabs: FLUX.1 Kontext [pro]", "description": "FLUX.1 Kontext [pro] has been optimized for text-guided image editing, providing exceptional performance with high-quality outputs, great prompt following, and consistent results. It is a state-of-the-art image editing model from Black Forest Labs that allows you to edit images using text prompts. It’s the best in class for text-guided image editing and offers superior results compared to other models like OpenAI’s 4o/gpt-image-1.", "id": "flux-1-kontext-pro", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 1 }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 1 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1568x672", "1392x752", "1184x880", "1248x832", "832x1248", "880x1184", "752x1392", "672x1568" ] }, { "name": "BlackForestLabs: FLUX.1 Kontext [max]", "description": "FLUX.1 Kontext [max] is a premium model with maximum performance and improved typography generation. It is a state-of-the-art image editing model from Black Forest Labs that allows you to edit images using text prompts. It’s the best in class for text-guided image editing and offers superior results compared to other models like OpenAI’s 4o/gpt-image-1.", "id": "flux-1-kontext-max", "object": "model", "created": 1788985190, "owned_by": "blackforestlabs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 1.2 }, "endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "premium_model": true, "providers": [ { "id": "blackforestlabs", "name": "Black Forest Labs", "tokens": 32000, "pricing": { "type": "per_image", "coefficient": 1.2 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000, "sizes": [ "1024x1024", "1568x672", "1392x752", "1184x880", "1248x832", "832x1248", "880x1184", "752x1392", "672x1568" ] }, { "name": "XLabs: Flux Realism", "description": "FLUX.1-dev with XLabs-AI’s realism lora.", "id": "flux-realism", "object": "model", "created": 1788985190, "owned_by": "xlabsai", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "xlabsai", "name": "xLabs", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Flux Half Illustration", "description": "Flux lora, use \"in the style of TOK\" to trigger generation, creates half photo half illustrated elements.", "id": "flux-half-illustration", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Flux Black Light", "description": "A flux lora fine-tuned on black light images.", "id": "flux-black-light", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Flux Minecraft Movie", "description": "Flux lora, use \"MNCRFTMOV\" to trigger image generation.", "id": "flux-minecraft-movie", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Flux Dreamscape", "description": "Flux lora, use \"BSstyle004\" to trigger image generation.", "id": "flux-dreamscape", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Flux Lineart", "description": "Flux finetuned for black and white line art.", "id": "flux-lineart", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Flux Master", "description": "Master Flux is a Flux-based text-to-image model for detailed, high-quality image generation.", "id": "flux-master", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Replicate: Phlux - Photorealism with style", "description": "This is a Flux LoRA that can generate photorealistic images with incredible texture and lighting.", "id": "phlux", "object": "model", "created": 1788985190, "owned_by": "replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "replicate", "name": "Replicate", "tokens": 600, "pricing": { "type": "per_image", "coefficient": 0.3 } } ], "context_length": 600, "max_model_len": 600, "max_input_tokens": 600, "sizes": [ "1024x1024", "1024x1536", "1536x1024", "1024x576", "576x1024" ] }, { "name": "Tencent: Hunyuan Image 3.0", "description": "Tencent Hunyuan Image 3.0 is a bilingual English and Chinese text-to-image model with strong Chinese text rendering and solid general quality.", "id": "hunyuan-image-3", "object": "model", "created": 1788985190, "owned_by": "tencent", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.02 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "tencent", "name": "Tencent", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.02 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "ByteDance: Seedream V5 Lite", "description": "ByteDance Seedream V5 Lite is an efficient Seedream text-to-image model that balances speed and quality for everyday generation.", "id": "seedream-5-lite", "object": "model", "created": 1788985190, "owned_by": "bytedance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.03 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "bytedance", "name": "ByteDance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.03 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "ByteDance: Seedream v4 - Edit", "description": "ByteDance Seedream v4 Edit transforms source images from text prompts and supports multi-image composition.", "id": "seedream-v4-edit", "object": "model", "created": 1788985190, "owned_by": "bytedance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "bytedance", "name": "ByteDance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "ByteDance: Seedream V5 Lite (image-to-image)", "description": "ByteDance Seedream V5 Lite Edit is a lighter Seedream editor for faster prompt-guided transforms of a source image.", "id": "seedream-v5-lite-edit", "object": "model", "created": 1788985190, "owned_by": "bytedance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "bytedance", "name": "ByteDance", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "OpenAI: GPT Image 1.5", "description": "OpenAI GPT Image 1.5 is a general text-to-image model suited to product shots, UI mockups, and everyday creative work.", "id": "gpt-image-1.5", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "OpenAI: GPT Image 1.5 - Edit", "description": "OpenAI GPT Image 1.5 Edit restyles or transforms a source image from a text prompt, with optional reference images.", "id": "gpt-image-1-5-edit", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.5 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.5 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "OpenAI: GPT Image 2 - Edit", "description": "OpenAI GPT Image 2 Edit is a higher-tier image editor for detailed transforms and multi-image composition from text instructions.", "id": "gpt-image-2-edit", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.5 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.5 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "xAI: Grok Imagine", "description": "xAI Grok Imagine (Aurora) is an autoregressive MoE image model with strong real-world entity, logo, and text rendering across photoreal and stylized looks.", "id": "grok-imagine", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "xAI: Grok Imagine - Edit", "description": "xAI Grok Imagine Edit applies Aurora to image-to-image work: restyling, guided transforms, and multi-image composition from prompts.", "id": "grok-imagine-edit", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "xAI: Grok Imagine High Quality", "description": "xAI Grok Imagine Quality is a quality-focused Aurora generation path for cleaner detail when standard Grok Imagine is not enough.", "id": "grok-imagine-quality", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 }, "endpoints": [ "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.08 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "xAI: Grok Imagine Quality (image-to-image)", "description": "xAI Grok Imagine Quality Edit is the quality-tier Aurora editor for higher-fidelity transforms from a source image and text prompt.", "id": "grok-imagine-quality-edit", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 }, "endpoints": [ "/v1/images/edits", "/v1/images/generations" ], "premium_model": false, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "xAI: Grok Imagine Pro", "description": "xAI Grok Imagine Pro is a higher-quality Aurora tier with sharper detail and more reliable text and logo rendering than standard Grok Imagine.", "id": "grok-imagine-pro", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 }, "endpoints": [ "/v1/images/generations" ], "premium_model": true, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 1000, "pricing": { "type": "per_image", "coefficient": 0.1 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "sizes": [ "1024x1024", "1152x896", "896x1152", "1344x768", "768x1344", "1280x720", "720x1280" ] }, { "name": "Mistral: Voxtral TTS", "description": "State-of-the-art TTS with zero-shot voice cloning and multilingual support.", "id": "voxtral-mini-tts-2603", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 16 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 16 } } ], "context_length": 4096, "max_model_len": 4096, "max_input_tokens": 4096, "voices": [ "en_paul_sad", "en_paul_neutral", "en_paul_happy", "en_paul_frustrated", "en_paul_excited", "en_paul_confident", "en_paul_cheerful", "en_paul_angry", "gb_oliver_neutral", "gb_jane_sarcasm" ] }, { "name": "Mistral: Voxtral TTS", "description": "State-of-the-art TTS with zero-shot voice cloning and multilingual support.", "id": "voxtral-mini-tts-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 16 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 16 } } ], "context_length": 4096, "max_model_len": 4096, "max_input_tokens": 4096, "voices": [ "en_paul_sad", "en_paul_neutral", "en_paul_happy", "en_paul_frustrated", "en_paul_excited", "en_paul_confident", "en_paul_cheerful", "en_paul_angry", "gb_oliver_neutral", "gb_jane_sarcasm" ] }, { "name": "OpenAI: TTS-1", "description": "TTS is a model that converts text to natural sounding spoken text. The tts-1 model is optimized for realtime text-to-speech use cases.", "id": "tts-1", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 15 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 15 } } ], "context_length": 4096, "max_model_len": 4096, "max_input_tokens": 4096, "voices": [ "alloy", "ash", "ballad", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer", "verse" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "max_length": 4096, "description": "The text to generate audio for. The maximum length is 4096 characters." }, "voice": { "required": true, "type": "string", "description": "The voice to use when generating the audio" }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm." }, "speed": { "required": false, "type": "number", "minimum": 0.25, "maximum": 4.0, "default": 1.0, "description": "The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default." } } }, { "name": "OpenAI: TTS-1 HD", "description": "TTS is a model that converts text to natural sounding spoken text. The tts-1-hd model is optimized for high quality text-to-speech use cases.", "id": "tts-1-hd", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 30 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 4096, "pricing": { "type": "per_million_tokens", "input": 30 } } ], "context_length": 4096, "max_model_len": 4096, "max_input_tokens": 4096, "voices": [ "alloy", "ash", "ballad", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer", "verse" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "max_length": 4096, "description": "The text to generate audio for. The maximum length is 4096 characters." }, "voice": { "required": true, "type": "string", "description": "The voice to use when generating the audio" }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm." }, "speed": { "required": false, "type": "number", "minimum": 0.25, "maximum": 4.0, "default": 1.0, "description": "The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default." } } }, { "name": "OpenAI: GPT-4o Mini TTS", "description": "GPT-4o mini TTS is a text-to-speech model built on GPT-4o mini, a fast and powerful language model. Use it to convert text to natural sounding spoken text.", "id": "gpt-4o-mini-tts", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 2000, "pricing": { "type": "per_million_tokens", "input": 10 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 2000, "pricing": { "type": "per_million_tokens", "input": 10 } } ], "context_length": 2000, "max_model_len": 2000, "max_input_tokens": 2000, "voices": [ "alloy", "ash", "ballad", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer", "verse" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "max_length": 4096, "description": "The text to generate audio for. The maximum length is 4096 characters." }, "voice": { "required": true, "type": "string", "description": "The voice to use when generating the audio" }, "instructions": { "required": false, "type": "string", "description": "Control the voice of your generated audio with additional instructions" }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm." } } }, { "name": "Google: Gemini 2.5 Flash TTS Preview", "description": "Google's Gemini 2.5 Flash model optimized for text-to-speech generation. Supports single-speaker synthesis with 30 high-quality voice options for natural-sounding speech output.", "id": "gemini-2.5-flash-preview-tts", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 10 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 10 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "voices": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "max_length": 8000, "description": "Text to convert to speech", "original_field": "text" }, "voice": { "required": false, "type": "string", "enum": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ], "default": "Kore", "description": "Voice name for speech synthesis" } } }, { "name": "Google: Gemini 2.5 Pro TTS Preview", "description": "Google's Gemini 2.5 Pro model optimized for text-to-speech generation. Supports single-speaker synthesis with 30 high-quality voice options for natural-sounding speech output with enhanced quality and capabilities.", "id": "gemini-2.5-pro-preview-tts", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 20 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": true, "providers": [ { "id": "google", "name": "Google", "tokens": 8000, "pricing": { "type": "per_million_tokens", "input": 20 } } ], "context_length": 8000, "max_model_len": 8000, "max_input_tokens": 8000, "voices": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "max_length": 8000, "description": "Text to convert to speech", "original_field": "text" }, "voice": { "required": false, "type": "string", "enum": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ], "default": "Kore", "description": "Voice name for speech synthesis" } } }, { "name": "MyShell: MeloTTS", "description": "MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai.", "id": "melotts", "object": "model", "created": 1788985190, "owned_by": "myshell", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 20 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "myshell", "name": "MyShell", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 20 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "en", "fr", "es", "de", "it", "pt", "ru", "zh", "ja", "ko" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "A text description of the audio you want to generate", "original_field": "prompt" }, "voice": { "required": false, "type": "string", "default": "en", "description": "The speech language (e.g., 'en' for English, 'fr' for French). Defaults to 'en' if not specified", "original_field": "lang" } } }, { "name": "Mistral: Voxtral Mini Transcribe 2", "description": "Efficient audio transcription model (Voxtral Mini Transcribe 2).", "id": "voxtral-mini-2602", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 16384, "pricing": { "type": "per_minute", "coefficient": 0.003 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 16384, "pricing": { "type": "per_minute", "coefficient": 0.003 } } ], "context_length": 16384, "max_model_len": 16384, "max_input_tokens": 16384 }, { "name": "Mistral: Voxtral Mini Transcribe 2", "description": "Efficient audio transcription model (Voxtral Mini Transcribe 2).", "id": "voxtral-mini-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 16384, "pricing": { "type": "per_minute", "coefficient": 0.003 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 16384, "pricing": { "type": "per_minute", "coefficient": 0.003 } } ], "context_length": 16384, "max_model_len": 16384, "max_input_tokens": 16384 }, { "name": "Mistral: Voxtral Mini Transcribe Realtime", "description": "Open model optimized for live/realtime transcription.", "id": "voxtral-mini-realtime-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 32768, "pricing": { "type": "per_minute", "coefficient": 0.006 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 32768, "pricing": { "type": "per_minute", "coefficient": 0.006 } } ], "context_length": 32768, "max_model_len": 32768, "max_input_tokens": 32768 }, { "name": "Mistral: Voxtral Mini Transcribe Realtime", "description": "Open model optimized for live/realtime transcription.", "id": "voxtral-mini-transcribe-realtime-2602", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 32768, "pricing": { "type": "per_minute", "coefficient": 0.006 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 32768, "pricing": { "type": "per_minute", "coefficient": 0.006 } } ], "context_length": 32768, "max_model_len": 32768, "max_input_tokens": 32768 }, { "name": "Mistral: Codestral Embed", "description": "State-of-the-art embeddings for code and natural-language queries.", "id": "codestral-embed", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.15 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.15 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Mistral: Codestral Embed 2505", "description": "Official codestral-embed Mistral AI model", "id": "codestral-embed-2505", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.15 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.15 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Mistral: Mistral Embed", "description": "Official mistral-embed-2312 Mistral AI model", "id": "mistral-embed", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.1 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.1 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Mistral: Mistral Embed 2312", "description": "Semantic embedding model for text representation.", "id": "mistral-embed-2312", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.1 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.1 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "OpenAI: Text Embedding Ada 002", "description": "Text-embedding-ada-002 is a powerful model by OpenAI designed for generating high-dimensional text embeddings. These embeddings are numerical representations of text data, enabling a variety of natural language processing (NLP) tasks such as semantic search, clustering, and text classification.", "id": "text-embedding-ada-002", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.1 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.1 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "OpenAI: Text Embedding 3 Large", "description": "Text-embedding-3-large is a robust language model by OpenAI designed for generating high-dimensional text embeddings for a wide range of natural language processing (NLP) tasks including semantic search, text clustering, and classification.", "id": "text-embedding-3-large", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.13 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.13 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "OpenAI: Text Embedding 3 Small", "description": "Text-embedding-3-small is a compact and efficient model developed for generating high-quality text embeddings. These embeddings are numerical representations of text data, enabling a variety of natural language processing (NLP) tasks such as semantic search, clustering, and text classification", "id": "text-embedding-3-small", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.02 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.02 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Google: Gemini Embedding 2", "description": "Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.", "id": "gemini-embedding-2", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.2 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.2 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Google: Gemini Embedding 2 Preview", "description": "Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.", "id": "gemini-embedding-2-preview", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.2 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 8192, "pricing": { "type": "per_million_tokens", "input": 0.2 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Google: Gemini Embedding 001", "description": "Gemini-embedding-001 is a state-of-the-art model by Google designed for generating high-dimensional text embeddings. These embeddings are numerical representations of text data, enabling a variety of natural language processing (NLP) tasks such as semantic search, clustering, and text classification.", "id": "gemini-embedding-001", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 2048, "pricing": { "type": "per_million_tokens", "input": 0.15 }, "endpoints": [ "/v1/embeddings" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 2048, "pricing": { "type": "per_million_tokens", "input": 0.15 } } ], "context_length": 2048, "max_model_len": 2048, "max_input_tokens": 2048 }, { "name": "Mistral: Mistral Moderation 24.11", "description": "Legacy moderation classifier; still accepted by Mistral API.", "id": "mistral-moderation-2411", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 8192, "pricing": { "type": "per_request", "coefficient": 0 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 8192, "pricing": { "type": "per_request", "coefficient": 0 } } ], "context_length": 8192, "max_model_len": 8192, "max_input_tokens": 8192 }, { "name": "Mistral: Mistral Moderation 2", "description": "Latest moderation classifier with 128k context and jailbreak detection.", "id": "mistral-moderation-2603", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_request", "coefficient": 0 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_request", "coefficient": 0 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000 }, { "name": "Mistral: Mistral Moderation Latest", "description": "Moderation latest alias; still accepted by Mistral API.", "id": "mistral-moderation-latest", "object": "model", "created": 1788985190, "owned_by": "mistralai", "tokens": 131000, "pricing": { "type": "per_request", "coefficient": 0 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "mistralai", "name": "Mistral", "tokens": 131000, "pricing": { "type": "per_request", "coefficient": 0 } } ], "context_length": 131000, "max_model_len": 131000, "max_input_tokens": 131000 }, { "name": "OpenAI: Omni Moderation Latest", "description": "Identify potentially harmful content in text and images.", "id": "omni-moderation-latest", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000 }, { "name": "OpenAI: Omni Moderation 2024-09-26", "description": "Identify potentially harmful content in text and images.", "id": "omni-moderation-2024-09-26", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000 }, { "name": "OpenAI: Text Moderation Latest", "description": "Identify potentially harmful content in text.", "id": "text-moderation-latest", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000 }, { "name": "OpenAI: Text Moderation Stable", "description": "Identify potentially harmful content in text.", "id": "text-moderation-stable", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000 }, { "name": "OpenAI: Text Moderation 007", "description": "Identify potentially harmful content in text.", "id": "text-moderation-007", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 }, "endpoints": [ "/v1/moderations" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 32000, "pricing": { "type": "per_request", "coefficient": 0.001 } } ], "context_length": 32000, "max_model_len": 32000, "max_input_tokens": 32000 }, { "name": "AWS: Polly Neural", "description": "AWS Polly neural TTS voices.", "id": "aws-polly", "object": "model", "created": 1788985190, "owned_by": "aws", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 24 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "aws", "name": "Aws", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 24 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aditi", "adriano-neural", "amy", "amy-neural", "andres-neural", "aria-neural", "arlet-neural", "arthur-neural", "astrid", "ayanda-neural", "bianca", "bianca-neural", "brian", "brian-neural", "burcu-neural", "camila", "camila-neural", "carla", "carmen", "celine", "chantal", "conchita", "cristiano", "daniel-neural", "danielle-neural", "dora", "elin-neural", "emma", "emma-neural", "enrique", "ewa", "filiz", "gabrielle-neural", "geraint", "giorgio", "gregory-neural", "gwyneth", "hala-neural", "hannah-neural", "hans", "hiujin-neural", "ida-neural", "ines", "ines-neural", "isabelle-neural", "ivy", "ivy-neural", "jacek", "jan", "jasmine-neural", "jihye-neural", "jitka-neural", "joanna", "joanna-neural", "joey", "joey-neural", "justin", "justin-neural", "kajal-neural", "karl", "kazuha-neural", "kendra", "kendra-neural", "kevin-neural", "kimberly", "kimberly-neural", "laura-neural", "lea", "lea-neural", "liam-neural", "lisa-neural", "liv", "lotte", "lucia", "lucia-neural", "lupe", "lupe-neural", "mads", "maja", "marlene", "mathieu", "matthew", "matthew-neural", "maxim", "mia", "mia-neural", "miguel", "mizuki", "naja", "niamh-neural", "nicole", "ola-neural", "olivia-neural", "pedro-neural", "penelope", "raveena", "remi-neural", "ricardo", "ruben", "russell", "ruth-neural", "sabrina-neural", "salli", "salli-neural", "seoyeon", "seoyeon-neural", "sergio-neural", "sofie-neural", "stephen-neural", "suvi-neural", "takumi", "takumi-neural", "tatyana", "thiago-neural", "tomoko-neural", "vicki", "vicki-neural", "vitoria", "vitoria-neural", "zayd-neural", "zeina", "zhiyu", "zhiyu-neural" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "language": { "required": false, "type": "string", "description": "BCP-47 language code (e.g. en-US). AWS Polly ``language_code``." }, "text_type": { "required": false, "type": "string", "default": "text", "description": "``text`` or ``ssml`` (AWS Polly / Azure)." }, "response_format": { "required": false, "type": "string", "description": "Polly ``output_format``." }, "sample_rate": { "required": false, "type": "string", "description": "Polly ``sample_rate``." } } }, { "name": "Azure: Neural", "description": "Azure Cognitive Services neural TTS voices.", "id": "azure-neural", "object": "model", "created": 1788985190, "owned_by": "azure", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 48 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "azure", "name": "Azure", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 48 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aarav", "aarohi", "aarti", "aarti-dragon-hd-latest", "aarti-indic", "aashi", "abbi", "abdullah", "abeo", "abril", "achara", "ada-dragon-hd-latest", "ada-multilingual", "adam-dragon-hd-latest", "adam-multilingual", "adri", "agnieszka", "ahmet", "aigenerate1", "aigenerate2", "aigul", "ainhoa", "alain", "alba", "aled", "alejo-mai-voice-2", "alejo-mai-voice-2-flash", "aleksandar", "alessio-dragon-hd-latest", "alessio-dragon-latest", "alessio-multilingual", "alex", "alfie", "ali", "alina", "alloy-dragon-hd-latest", "alloy-turbo-multilingual", "alonso", "alvaro", "amal", "amala", "amanda-multilingual", "amany", "amber", "ameha", "amina", "ana", "anahit", "ananya", "anbu", "ander", "andrea", "andrei-mai-voice-2", "andrei-mai-voice-2-flash", "andres", "andrew", "andrew-dragon-hd-latest", "andrew-dragon-hd-omni-latest", "andrew-dragon-latest", "andrew-multilingual", "andrew-preview-dragon-hd-latest", "angelo", "angelo-dragon-hd-latest", "anila", "annette", "antoine", "antonin", "antonio", "anu", "aoi", "arabella-multilingual", "ardi", "ardi-dragon-hd-latest", "aria", "aria-dragon-hd-latest", "ariane", "arjun", "arjun-dragon-hd-latest", "arjun-indic", "arjun-mai-voice-2", "arjun-mai-voice-2-flash", "arnau", "arnaud", "asad", "ash-turbo-multilingual", "ashley", "asilia", "athina", "ava", "ava-dragon-hd-latest", "ava-dragon-hd-omni-latest", "ava-dragon-latest", "ava-multilingual", "ava-preview-dragon-hd-latest", "avri", "ayd-n-mai-voice-2", "ayd-n-mai-voice-2-flash", "aysha", "babek", "banu", "bashkar", "bassel", "bataa", "beatriz", "belkys", "bella", "bence-mai-voice-2", "bence-mai-voice-2-flash", "benigno", "bernd", "blessica", "blessica-dragon-hd-latest", "blue", "blushzephyr-dragon-hd-omni-latest", "bo-mai-voice-2", "bo-mai-voice-2-flash", "bongjin", "borislav", "brandon", "brandon-multilingual", "bree-dragon-hd-latest", "brenda", "brian", "brian-dragon-hd-latest", "brian-multilingual", "brigitte", "caio-mai-voice-2", "caio-mai-voice-2-flash", "caleb-dragon-hd-omni-latest", "calimero", "camila", "candela", "carlos", "carlota", "carly", "cataldo", "catalina", "cecilio", "celeste", "chanthavong", "charline", "chilemba", "chinese-multitalker-dragon-hd-latest", "christel", "christoph", "christopher", "christopher-multilingual", "clara", "claude", "colette", "colm", "connor", "conrad", "cora", "cora-multilingual", "coralie", "cyanspark-dragon-hd-omni-latest", "daichi", "dalia", "dalia-dragon-hd-latest", "dalia-multilingual", "dana-dragon-hd-omni-latest", "dario", "dariya", "darren", "daudi", "daulet", "davis", "davis-dragon-hd-latest", "davis-multilingual", "dena", "denise", "denise-dragon-latest", "derek-multilingual", "dhruv-mai-voice-2", "dhruv-mai-voice-2-flash", "dhwani", "diego", "dilara", "dimas", "diya-dragon-hd-latest", "diya-dragon-latest", "dmitry", "donato", "duarte", "duncan", "dustin-multilingual", "echo-turbo-multilingual", "eka", "elena", "elena-mai-voice-2", "elena-mai-voice-2-flash", "elias", "elif-mai-voice-2", "elif-mai-voice-2-flash", "elimu", "elizabeth", "elke", "elliot", "eloise", "elsa", "elsie", "elvira", "elza", "emel", "emil", "emilio", "emily", "emma", "emma-dragon-hd-latest", "emma-dragon-hd-omni-latest", "emma-multilingual", "english-multitalker-dragon-hd-latest", "enric", "eric", "estrella", "ethan", "ethan-mai-voice-2", "ethan-mai-voice-2-flash", "evelyn-dragon-hd-latest", "evelyn-multilingual", "everita", "ezinne", "fabio", "fabiola", "fable-turbo-multilingual", "fabrice", "fahed", "farid", "fatima", "federico", "fenna", "fernanda", "fiamma", "finn", "fleur-mai-voice-2", "fleur-mai-voice-2-flash", "florian-dragon-hd-latest", "florian-multilingual", "francisca", "francisca-dragon-latest", "french-multitalker-dragon-hd-latest", "freya", "gabrijela", "gadis", "gadis-dragon-hd-latest", "gagan", "gerard", "gerardo", "gianni", "giorgi", "giovanna", "gisela", "giuseppe", "giuseppe-dragon-hd-latest", "giuseppe-multilingual", "goldenspark-dragon-hd-omni-latest", "gonzalo", "gookmin", "goran", "grace", "grant-mai-voice-2", "grant-mai-voice-2-flash", "gudrun", "gul", "gul-nawaz", "gunnar", "guy", "haena-mai-voice-2", "haena-mai-voice-2-flash", "hamdan", "hamed", "harper-mai-voice-2", "harper-mai-voice-2-flash", "harri", "hayk", "hedi", "hemkala", "henri", "hila", "hillevi", "hiugaai", "hiumaan", "hoaimy", "hollie", "hsiaochen", "hsiaoyu", "humberto", "hyunsu", "hyunsu-dragon-hd-latest", "hyunsu-multilingual", "ilir", "iman", "imani", "imelda", "ingrid", "injoon", "ioana-mai-voice-2", "ioana-mai-voice-2-flash", "irene", "iris-mai-voice-2", "iris-mai-voice-2-flash", "irma", "isabella", "isabella-dragon-hd-latest", "isabella-dragon-latest", "isabella-multilingual", "iselin", "isidora-multilingual", "isla-mai-voice-2", "isla-mai-voice-2-flash", "ismael", "jacob", "jacqueline", "jajang", "jamal", "james", "jan", "jane", "jane-dragon-hd-latest", "jason", "jasper-mai-voice-2", "jasper-mai-voice-2-flash", "javier", "jean", "jelly-dragon-hd-omni-latest", "jenny", "jenny-dragon-hd-latest", "jenny-multilingual", "jeppe", "jerome", "jimin", "jimmie-dragon-hd-flash-latest", "jimmie-dragon-hd-latest", "joana", "joanne", "jonas", "jorge", "jorge-dragon-hd-latest", "jorge-multilingual", "joseph", "josephine", "juan", "julio", "junho-mai-voice-2", "junho-mai-voice-2-flash", "juno-dragon-hd-latest", "kai", "kalina", "kani", "karina", "karla", "kasper", "katja", "kavya", "kavya-mai-voice-2", "kavya-mai-voice-2-flash", "keita", "ken", "keomany", "kert", "killian", "kim", "klarissa", "klaus", "klaus-mai-voice-2", "klaus-mai-voice-2-flash", "krit-mai-voice-2", "krit-mai-voice-2-flash", "kumar", "kunal", "laia", "laila", "laith", "lan-mai-voice-2", "lan-mai-voice-2-flash", "larasati-dragon-hd-latest", "larissa", "latifa", "lavanya-dragon-hd-latest", "layla", "leah", "leila", "leni", "leonas", "leticia", "lev-mai-voice-2", "lev-mai-voice-2-flash", "levente-mai-voice-2", "levente-mai-voice-2-flash", "lewis-dragon-hd-omni-latest", "lewis-multilingual", "lia", "liam", "libby", "liberto", "lilla-mai-voice-2", "lilla-mai-voice-2-flash", "lisandro", "lola-multilingual", "lorena", "lorenzo", "louisa", "luana-mai-voice-2", "luana-mai-voice-2-flash", "luca-mai-voice-2", "luca-mai-voice-2-flash", "luciano", "lucien-multilingual", "luis", "lukas", "luke", "luna", "maarten", "macerio-dragon-hd-latest", "macerio-dragon-latest", "macerio-multilingual", "madhur", "madina", "maisie", "maja", "manohar", "manuel", "manuela", "marc-mai-voice-2", "marc-mai-voice-2-flash", "marcello-multilingual", "marcelo", "marek", "margarita", "maria", "mariela-dragon-hd-latest", "marija", "marina", "mario", "maroonallegro-dragon-hd-omni-latest", "marta", "marta-mai-voice-2", "marta-mai-voice-2-flash", "maryam", "masaru-dragon-hd-latest", "masaru-multilingual", "masha-mai-voice-2", "masha-mai-voice-2-flash", "mateo", "mattias", "maurice", "mayu", "meera-dragon-hd-latest", "mei-mai-voice-2", "mei-mai-voice-2-flash", "mekdes", "mia", "mia-mai-voice-2", "mia-mai-voice-2-flash", "michelle", "midhun", "mila-dragon-hd-latest", "mitchell", "moaz", "mohan", "molly", "monica", "mouna", "muuse", "nabanita", "nadira-dragon-hd-latest", "namminh", "nanami", "nanami-dragon-hd-latest", "nancy", "nancy-multilingual", "naoki", "natasha", "nattapong-mai-voice-2", "nattapong-mai-voice-2-flash", "neerja", "neerja-dragon-hd-latest", "neerja-indic", "neil", "nestoras", "nia", "nicholas", "nicholas-latin", "nicolau", "nil", "nilar", "nils", "niranjan", "niwat", "noah", "noemi", "noora", "noura", "nova-dragon-hd-latest", "nova-turbo-multilingual", "nuria", "ojas", "oliver", "olivia", "olivia-mai-voice-2", "olivia-mai-voice-2-flash", "ollie-dragon-hd-latest", "ollie-multilingual", "omar", "ona", "onyx-turbo-multilingual", "orla", "osman", "osman-dragon-hd-latest", "ostap", "pallavi", "palmira", "paloma", "paola", "pedro-mai-voice-2", "pedro-mai-voice-2-flash", "pelayo", "pernille", "petra", "phoebe-dragon-hd-latest", "phoebe-dragon-hd-omni-latest", "phoebe-multilingual", "pierina", "piseth", "polina", "prabhat", "prabhat-indic", "pradeep", "premwadee", "priya-mai-voice-2", "priya-mai-voice-2-flash", "priyom", "radu-mai-voice-2", "radu-mai-voice-2-flash", "rafael-mai-voice-2", "rafael-mai-voice-2-flash", "rafiki", "ralf", "rami", "ramona", "rana", "raquel", "reem", "rehaan", "rehema", "reka-mai-voice-2", "reka-mai-voice-2-flash", "remy-dragon-hd-latest", "remy-dragon-latest", "remy-multilingual", "renata", "rinaldo", "roberto", "rodrigo", "roger", "roi", "rok", "rosa", "rosa-mai-voice-2", "rosa-mai-voice-2-flash", "rui-mai-voice-2", "rui-mai-voice-2-flash", "ryan", "ryan-dragon-hd-latest", "ryan-multilingual", "sabela", "sagar", "saleh", "salma", "salman", "salome", "sam", "sameera", "samuel-multilingual", "sana", "sander-mai-voice-2", "sander-mai-voice-2-flash", "sapna", "sara", "saranya", "sardor", "saul", "sebastian", "selma", "seohyeon", "seraphina-dragon-hd-latest", "seraphina-dragon-latest", "seraphina-multilingual", "serena-dragon-hd-latest", "serena-multilingual", "serena-preview-dragon-hd-latest", "shakir", "shimmer-turbo-multilingual", "shiori", "shruti", "siennatopaz-dragon-hd-omni-latest", "siqiniq", "siti", "sobhana", "sofia", "sofie", "soleil-mai-voice-2", "soleil-mai-voice-2-flash", "sonia", "sonia-dragon-hd-latest", "soonbok", "sophie", "sophie-latin", "srecko", "sreymom", "steffan", "steffan-dragon-hd-latest", "steffan-multilingual", "subhasini", "sukant", "sun-hi", "sunhi-dragon-hd-latest", "surya", "svetlana", "swara", "sylvie", "sylvie-dragon-hd-latest", "taim", "tamas", "tania", "tanishaa", "tanja", "taqqiq", "teo", "teresa", "tessa-dragon-hd-latest", "thalita", "thalita-dragon-hd-latest", "thalita-multilingual", "thando", "themba", "thierry", "thierry-dragon-hd-latest", "thiha", "thilini", "thomas", "tiana-dragon-hd-flash-latest", "tiana-dragon-hd-latest", "tim", "tina", "tomas", "tony", "triana", "tristan-dragon-hd-latest", "tristan-multilingual", "tuti", "tyler-dragon-hd-flash-latest", "tyler-dragon-hd-latest", "ubax", "uzma", "vaani", "valentina", "valeria-mai-voice-2", "valeria-mai-voice-2-flash", "valerio", "valluvar", "vance-dragon-hd-latest", "venba", "vera", "vesna", "victor", "viktoria", "vivienne-dragon-hd-latest", "vivienne-multilingual", "vlasta", "wanlung", "wayne", "wei-mai-voice-2", "wei-mai-voice-2-flash", "willem", "william", "william-multilingual", "xiaobei", "xiaochen", "xiaochen-dragon-hd-flash-latest", "xiaochen-dragon-hd-latest", "xiaochen-multilingual", "xiaohan", "xiaohan-dragon-hd-flash-latest", "xiaoke-dragon-hd-flash-latest", "xiaomeng", "xiaomin", "xiaomo", "xiaomo-dragon-hd-flash-latest", "xiaoni", "xiaoqi-dragon-hd-flash-latest", "xiaoqi-dragon-latest", "xiaoqiu", "xiaorou", "xiaorou-dragon-hd-flash-latest", "xiaorui", "xiaoshuang", "xiaoshuang-dragon-hd-flash-latest", "xiaoshuang-multilingual", "xiaotong", "xiaoxiao", "xiaoxiao-dialects", "xiaoxiao-dragon-hd-flash-latest", "xiaoxiao-multilingual", "xiaoxiao2-dragon-hd-flash-latest", "xiaoyan", "xiaoyi", "xiaoyi-dragon-hd-flash-latest", "xiaoyou", "xiaoyou-dragon-hd-flash-latest", "xiaoyou-multilingual", "xiaoyu-dragon-hd-flash-latest", "xiaoyu-multilingual", "xiaoyue-dragon-hd-omni-latest", "xiaozhen", "ximena", "ximena-dragon-hd-latest", "ximena-multilingual", "yago", "yan", "yara", "yashica", "yasmin", "yasmin-dragon-hd-latest", "yesui", "yolanda", "yujin", "yunbiao", "yundeng", "yunfan-dragon-hd-flash-latest", "yunfan-dragon-hd-latest", "yunfan-dragon-latest", "yunfan-multilingual", "yunfeng", "yunfeng-dragon-hd-flash-latest", "yunhan-dragon-hd-flash-latest", "yunhao", "yunjhe", "yunjian", "yunjie", "yunjie-dragon-hd-flash-latest", "yunqi", "yunqi-dragon-hd-omni-latest", "yunsong", "yunxi", "yunxi-dragon-hd-flash-latest", "yunxia", "yunxia-dragon-hd-flash-latest", "yunxiang", "yunxiao-dragon-hd-flash-latest", "yunxiao-multilingual", "yunyang", "yunye", "yunye-dragon-hd-flash-latest", "yunyi-dragon-hd-flash-latest", "yunyi-multilingual", "yunze", "yunzhe", "yves", "yvette", "zariyah", "zofia", "zuri" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "language": { "required": false, "type": "string", "default": "en-US", "description": "BCP-47 language code (Azure ``language_code``)." }, "text_type": { "required": false, "type": "string", "default": "text", "description": "``text`` or ``ssml``." }, "response_format": { "required": false, "type": "string", "description": "Azure audio output format string." }, "effect": { "required": false, "type": "string", "description": "Azure audio effect." }, "gender": { "required": false, "type": "string", "description": "Voice gender preference." } } }, { "name": "Fish Audio: S1", "description": "Fish Audio S1 TTS voices.", "id": "fish-audio-s1", "object": "model", "created": 1788985190, "owned_by": "fish-audio", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 15 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "fish-audio", "name": "Fish Audio", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "adrian", "aria", "atlas", "claire", "ethan", "mateo", "max", "nova", "paula", "yuki" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." } } }, { "name": "Fish Audio: S2 Pro", "description": "Fish Audio S2 Pro TTS voices.", "id": "fish-audio-s2-pro", "object": "model", "created": 1788985190, "owned_by": "fish-audio", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 15 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "fish-audio", "name": "Fish Audio", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "adrian", "aria", "atlas", "claire", "ethan", "mateo", "max", "nova", "paula", "yuki" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." } } }, { "name": "Fish Audio: S2.1 Pro", "description": "Fish Audio S2.1 Pro TTS voices.", "id": "fish-audio-s2.1-pro", "object": "model", "created": 1788985190, "owned_by": "fish-audio", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 15 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "fish-audio", "name": "Fish Audio", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 15 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "adrian", "aria", "atlas", "claire", "ethan", "mateo", "max", "nova", "paula", "yuki" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." } } }, { "name": "Humain: Humain TTS", "description": "Humain: Humain TTS text-to-speech.", "id": "humain", "object": "model", "created": 1788985190, "owned_by": "humain", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 5 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "humain", "name": "Humain", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 5 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "abdulaziz", "abdullah", "nourah", "sara" ] }, { "name": "Inworld: Max", "description": "Inworld Max TTS voices.", "id": "inworld-max", "object": "model", "created": 1788985190, "owned_by": "inworld", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 10 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "inworld", "name": "Inworld", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 10 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aanya", "aarav", "abby", "aditya", "alaric", "alistair", "alvaro", "alyona", "amara", "amina", "anjali", "arkady", "arthur", "ashley", "asuka", "beatrice", "beatriz", "blake", "borja", "brian", "brick", "bright-natural-german-female-voice-ideal-for-business-e-learning-and-narration", "british-accented-english-language-male-voice-with-a-calm-cordial-quality", "brooke", "bruna", "bruno", "bryce", "callum", "calm-refined-german-female-voice-ideal-for-business-e-learning-and-narration", "calm-refined-german-male-voice-ideal-for-business-e-learning-and-narration", "calm-young-adult-french-male", "camila", "camille", "celeste", "chioma", "chip", "citlali", "claire", "clear-composed-german-male-voice-ideal-for-business-e-learning-and-narration", "clear-deep-mature-korean-male-voice", "clear-professional-american-male-voice-well-suited-for-support-and-training", "composed-portuguese-speaking-male-voice-with-a-neutral-tone", "confident-grounded-german-male-voice-ideal-for-business-e-learning-and-narration", "cooper", "cordelia", "cuauhtemoc", "curro", "damon", "daniel", "deborah", "deep-smooth-middle-aged-male-french-voice-composed-and-calm", "derek", "dhruv", "dmitry", "dominus", "duncan", "dutch-woman-with-an-expressive-voice", "edward", "eldrin", "eleanor", "elliot", "emeka", "energetic-and-expressive-mid-range-male-voice-with-a-mildly-nasal-quality", "energetic-expressive-man-with-a-rapid-fire-delivery", "ethan", "evelyn", "even-toned-female-voice-with-an-indian-accent", "fast-talking-young-adult-woman-with-a-questioning-and-curious-tone", "felix", "folake", "freddie", "galina", "gianni", "gleb", "gonzalo", "graham", "grant", "gravelly-male-voice-with-a-time-worn-quality", "grigory", "guadalupe", "hades", "hana", "harold", "haruto", "hazel", "hina", "hyunwoo", "ignacio", "imogen", "indi", "inigo", "inmaculada", "ishaan", "itzel", "jake", "james", "jarrah", "jason", "jing", "joaquin", "johanna", "jonah", "josef", "joy", "kabir", "kayla", "kelsey", "laid-back-young-male-voice-with-a-chill-friendly-vibe", "larissa", "lauren", "lennart", "leonor", "lev", "levi", "liam", "lively-upbeat-american-male-voice", "lore", "loretta", "lucian", "luna", "madalena", "maisie", "malcolm", "manoj", "marcus", "mariana", "marta", "mateo", "mathieu", "matilda", "matilde", "mature-british-male-voice-with-a-warm-storytelling-quality", "mauricio", "maximiliano", "mayte", "meher", "mei", "mercedes", "mid-range-female-hebrew-voice-suitable-for-narrations-storytelling-and-more", "middle-aged-french-woman-with-a-smooth-musical-and-graceful-voice", "middle-aged-man-with-a-smooth-calm-and-friendly-voice", "middle-aged-portuguese-speaking-female-voice", "miguel", "ming", "minji", "morgana", "murilo", "nacho", "nate", "nigel", "nikhil", "nikolai", "nour", "oksana", "older-british-male-with-a-refined-and-articulate-voice", "older-dutch-male-voice-with-a-weathered-edge", "oliver", "olivia", "omar", "oren", "orietta", "paloma", "patricia", "penelope", "pilar", "piper", "pippa", "polina", "posh-middle-aged-british-female-voice", "professional-middle-aged-woman-perfect-for-narrations-and-voiceovers", "punchy-expressive-female-voice-ideal-for-short-form-social-ugc-and-viral-content", "quirky-high-pitched-female-voice-that-delivers-lines-with-playful-energy", "ren", "renata", "riya", "rocio", "rodion", "ronald", "rosalind", "ruben", "rupert", "ruslan", "salvador", "satoshi", "sebastian", "seema", "sergio", "shaun", "shreya", "simon", "snezhana", "sofia", "soft-high-pitched-female-voice-with-a-moderate-pace-and-slightly-breathy-quality", "sophie", "spanish-speaking-male-voice-with-a-soothing-gentle-quality", "stepan", "stylized-low-key-male-voice-ideal-for-anime-content-gaming-and-dubbing", "szymon", "tahlia", "tamara", "tatiana", "tessa", "timofey", "tunde", "vadim", "vanessa", "vibrant-energetic-young-spanish-speaking-female-voice", "victor", "victoria", "vikram", "vincent", "wade", "warm-engaging-german-female-voice-ideal-for-business-e-learning-and-narration", "warm-natural-german-male-voice-ideal-for-business-e-learning-and-narration", "warren", "winifred", "wojciech", "xiaoyin", "ximena", "xinyi", "xochitl", "yash", "yegor", "yichen", "yoona", "yulia", "zoe" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "language": { "required": false, "type": "string", "description": "BCP-47 language code (supported by Inworld on Telnyx)." } } }, { "name": "Inworld: Mini", "description": "Inworld Mini TTS voices.", "id": "inworld-mini", "object": "model", "created": 1788985190, "owned_by": "inworld", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 6 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "inworld", "name": "Inworld", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 6 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aanya", "aarav", "abby", "aditya", "alaric", "alistair", "alvaro", "alyona", "amara", "amina", "anjali", "arkady", "arthur", "ashley", "asuka", "beatrice", "beatriz", "blake", "borja", "brian", "brick", "bright-natural-german-female-voice-ideal-for-business-e-learning-and-narration", "british-accented-english-language-male-voice-with-a-calm-cordial-quality", "brooke", "bruna", "bruno", "bryce", "callum", "calm-refined-german-female-voice-ideal-for-business-e-learning-and-narration", "calm-refined-german-male-voice-ideal-for-business-e-learning-and-narration", "calm-young-adult-french-male", "camila", "camille", "celeste", "chioma", "chip", "citlali", "claire", "clear-composed-german-male-voice-ideal-for-business-e-learning-and-narration", "clear-deep-mature-korean-male-voice", "clear-professional-american-male-voice-well-suited-for-support-and-training", "composed-portuguese-speaking-male-voice-with-a-neutral-tone", "confident-grounded-german-male-voice-ideal-for-business-e-learning-and-narration", "cooper", "cordelia", "cuauhtemoc", "curro", "damon", "daniel", "deborah", "deep-smooth-middle-aged-male-french-voice-composed-and-calm", "derek", "dhruv", "dmitry", "dominus", "duncan", "dutch-woman-with-an-expressive-voice", "edward", "eldrin", "eleanor", "elliot", "emeka", "energetic-and-expressive-mid-range-male-voice-with-a-mildly-nasal-quality", "energetic-expressive-man-with-a-rapid-fire-delivery", "ethan", "evelyn", "even-toned-female-voice-with-an-indian-accent", "fast-talking-young-adult-woman-with-a-questioning-and-curious-tone", "felix", "folake", "freddie", "galina", "gianni", "gleb", "gonzalo", "graham", "grant", "gravelly-male-voice-with-a-time-worn-quality", "grigory", "guadalupe", "hades", "hana", "harold", "haruto", "hazel", "hina", "hyunwoo", "ignacio", "imogen", "indi", "inigo", "inmaculada", "ishaan", "itzel", "jake", "james", "jarrah", "jason", "jing", "joaquin", "johanna", "jonah", "josef", "joy", "kabir", "kayla", "kelsey", "laid-back-young-male-voice-with-a-chill-friendly-vibe", "larissa", "lauren", "lennart", "leonor", "lev", "levi", "liam", "lively-upbeat-american-male-voice", "lore", "loretta", "lucian", "luna", "madalena", "maisie", "malcolm", "manoj", "marcus", "mariana", "marta", "mateo", "mathieu", "matilda", "matilde", "mature-british-male-voice-with-a-warm-storytelling-quality", "mauricio", "maximiliano", "mayte", "meher", "mei", "mercedes", "mid-range-female-hebrew-voice-suitable-for-narrations-storytelling-and-more", "middle-aged-french-woman-with-a-smooth-musical-and-graceful-voice", "middle-aged-man-with-a-smooth-calm-and-friendly-voice", "middle-aged-portuguese-speaking-female-voice", "miguel", "ming", "minji", "morgana", "murilo", "nacho", "nate", "nigel", "nikhil", "nikolai", "nour", "oksana", "older-british-male-with-a-refined-and-articulate-voice", "older-dutch-male-voice-with-a-weathered-edge", "oliver", "olivia", "omar", "oren", "orietta", "paloma", "patricia", "penelope", "pilar", "piper", "pippa", "polina", "posh-middle-aged-british-female-voice", "professional-middle-aged-woman-perfect-for-narrations-and-voiceovers", "punchy-expressive-female-voice-ideal-for-short-form-social-ugc-and-viral-content", "quirky-high-pitched-female-voice-that-delivers-lines-with-playful-energy", "ren", "renata", "riya", "rocio", "rodion", "ronald", "rosalind", "ruben", "rupert", "ruslan", "salvador", "satoshi", "sebastian", "seema", "sergio", "shaun", "shreya", "simon", "snezhana", "sofia", "soft-high-pitched-female-voice-with-a-moderate-pace-and-slightly-breathy-quality", "sophie", "spanish-speaking-male-voice-with-a-soothing-gentle-quality", "stepan", "stylized-low-key-male-voice-ideal-for-anime-content-gaming-and-dubbing", "szymon", "tahlia", "tamara", "tatiana", "tessa", "timofey", "tunde", "vadim", "vanessa", "vibrant-energetic-young-spanish-speaking-female-voice", "victor", "victoria", "vikram", "vincent", "wade", "warm-engaging-german-female-voice-ideal-for-business-e-learning-and-narration", "warm-natural-german-male-voice-ideal-for-business-e-learning-and-narration", "warren", "winifred", "wojciech", "xiaoyin", "ximena", "xinyi", "xochitl", "yash", "yegor", "yichen", "yoona", "yulia", "zoe" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "language": { "required": false, "type": "string", "description": "BCP-47 language code (supported by Inworld on Telnyx)." } } }, { "name": "Inworld: TTS2", "description": "Inworld TTS2 voices.", "id": "inworld-tts2", "object": "model", "created": 1788985190, "owned_by": "inworld", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 10 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "inworld", "name": "Inworld", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 10 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aanya", "aarav", "abby", "aditya", "alaric", "alistair", "alvaro", "alyona", "amara", "amina", "anjali", "arkady", "arthur", "ashley", "asuka", "beatrice", "beatriz", "blake", "borja", "brian", "brick", "bright-natural-german-female-voice-ideal-for-business-e-learning-and-narration", "british-accented-english-language-male-voice-with-a-calm-cordial-quality", "brooke", "bruna", "bruno", "bryce", "callum", "calm-refined-german-female-voice-ideal-for-business-e-learning-and-narration", "calm-refined-german-male-voice-ideal-for-business-e-learning-and-narration", "calm-young-adult-french-male", "camila", "camille", "celeste", "chioma", "chip", "citlali", "claire", "clear-composed-german-male-voice-ideal-for-business-e-learning-and-narration", "clear-deep-mature-korean-male-voice", "clear-professional-american-male-voice-well-suited-for-support-and-training", "composed-portuguese-speaking-male-voice-with-a-neutral-tone", "confident-grounded-german-male-voice-ideal-for-business-e-learning-and-narration", "cooper", "cordelia", "cuauhtemoc", "curro", "damon", "daniel", "deborah", "deep-smooth-middle-aged-male-french-voice-composed-and-calm", "derek", "dhruv", "dmitry", "dominus", "duncan", "dutch-woman-with-an-expressive-voice", "edward", "eldrin", "eleanor", "elliot", "emeka", "energetic-and-expressive-mid-range-male-voice-with-a-mildly-nasal-quality", "energetic-expressive-man-with-a-rapid-fire-delivery", "ethan", "evelyn", "even-toned-female-voice-with-an-indian-accent", "fast-talking-young-adult-woman-with-a-questioning-and-curious-tone", "felix", "folake", "freddie", "galina", "gianni", "gleb", "gonzalo", "graham", "grant", "gravelly-male-voice-with-a-time-worn-quality", "grigory", "guadalupe", "hades", "hana", "harold", "haruto", "hazel", "hina", "hyunwoo", "ignacio", "imogen", "indi", "inigo", "inmaculada", "ishaan", "itzel", "jake", "james", "jarrah", "jason", "jing", "joaquin", "johanna", "jonah", "josef", "joy", "kabir", "kayla", "kelsey", "laid-back-young-male-voice-with-a-chill-friendly-vibe", "larissa", "lauren", "lennart", "leonor", "lev", "levi", "liam", "lively-upbeat-american-male-voice", "lore", "loretta", "lucian", "luna", "madalena", "maisie", "malcolm", "manoj", "marcus", "mariana", "marta", "mateo", "mathieu", "matilda", "matilde", "mature-british-male-voice-with-a-warm-storytelling-quality", "mauricio", "maximiliano", "mayte", "meher", "mei", "mercedes", "mid-range-female-hebrew-voice-suitable-for-narrations-storytelling-and-more", "middle-aged-french-woman-with-a-smooth-musical-and-graceful-voice", "middle-aged-man-with-a-smooth-calm-and-friendly-voice", "middle-aged-portuguese-speaking-female-voice", "miguel", "ming", "minji", "morgana", "murilo", "nacho", "nate", "nigel", "nikhil", "nikolai", "nour", "oksana", "older-british-male-with-a-refined-and-articulate-voice", "older-dutch-male-voice-with-a-weathered-edge", "oliver", "olivia", "omar", "oren", "orietta", "paloma", "patricia", "penelope", "pilar", "piper", "pippa", "polina", "posh-middle-aged-british-female-voice", "professional-middle-aged-woman-perfect-for-narrations-and-voiceovers", "punchy-expressive-female-voice-ideal-for-short-form-social-ugc-and-viral-content", "quirky-high-pitched-female-voice-that-delivers-lines-with-playful-energy", "ren", "renata", "riya", "rocio", "rodion", "ronald", "rosalind", "ruben", "rupert", "ruslan", "salvador", "satoshi", "sebastian", "seema", "sergio", "shaun", "shreya", "simon", "snezhana", "sofia", "soft-high-pitched-female-voice-with-a-moderate-pace-and-slightly-breathy-quality", "sophie", "spanish-speaking-male-voice-with-a-soothing-gentle-quality", "stepan", "stylized-low-key-male-voice-ideal-for-anime-content-gaming-and-dubbing", "szymon", "tahlia", "tamara", "tatiana", "tessa", "timofey", "tunde", "vadim", "vanessa", "vibrant-energetic-young-spanish-speaking-female-voice", "victor", "victoria", "vikram", "vincent", "wade", "warm-engaging-german-female-voice-ideal-for-business-e-learning-and-narration", "warm-natural-german-male-voice-ideal-for-business-e-learning-and-narration", "warren", "winifred", "wojciech", "xiaoyin", "ximena", "xinyi", "xochitl", "yash", "yegor", "yichen", "yoona", "yulia", "zoe" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "language": { "required": false, "type": "string", "description": "BCP-47 language code (supported by Inworld on Telnyx)." } } }, { "name": "MiniMax: Speech 02 Turbo", "description": "MiniMax Speech 02 Turbo TTS voices.", "id": "minimax-speech-02-turbo", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 34 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "minimax", "name": "MiniMax", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 34 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "airheaded-girl", "ambitious-woman", "angry-man", "anime-character", "arnold", "arrogant-miss", "assertive-queen", "assetive-woman", "assured-presenter", "athletic-girl", "athletic-student", "attractive-girl", "attractive-guy", "aussie-bloke", "bad-tempered-boy", "bashful-girl", "bossy-lady", "bossy-leader", "brave-adventurer", "brave-female-warrior", "brave-heroine", "brave-youth", "calm-gentleman", "calm-lady", "calm-leader", "calm-woman", "captivating-female", "captivating-storyteller", "caring-girlfriend", "caring-man", "caring-woman", "casual-man", "casual-woman", "charming-elder-sister", "charming-girl", "charming-lady", "charming-queen", "charming-santa", "charming-sister", "chatty-girl", "cheerful-boyfriend", "cheerful-cool-junior", "cheerful-little-sister", "childhood-friend-girl", "cocky-guy", "cold-girl", "cold-queen", "cold-young-man", "comedian", "compelling-girl", "compelling-lady", "confident-boss", "confident-woman", "conscientious-instructor", "considerate-senior", "crazy-girl", "crisp-girl", "cute-girl", "cute-spirit", "debator", "decent-young-man", "decisive-princess", "decisive-queen", "deep-toned-man", "deep-voiced-gentleman", "dependable-woman", "determined-boy", "determined-manager", "diligent-leader", "diligent-man", "dominant-man", "dramatist", "elegant-girl", "elegant-lady", "elegant-princess", "enchanting-sister", "energetic-boy", "energetic-woman", "energetic-youth", "enthusiastic-teen", "explorative-girl", "expressive-narrator", "fascinating-boy", "female-anchor", "female-narrator", "fragile-boy", "frank-lady", "friendly-big-sister", "friendly-boy", "friendly-guy", "friendly-man", "friendly-neighbor", "fussy-hostess", "generous-izakaya-owner", "gentle-boss", "gentle-butler", "gentle-girl", "gentle-lady", "gentle-senior", "gentle-teacher", "gentle-voiced-man", "gentle-woman", "gentle-youth", "gentleman", "ghost", "girl-next-door", "godfather", "gorgeous-lady", "graceful-lady", "graceful-maiden", "grim-reaper", "grinch", "handsome-childhood-friend", "haughty-lady", "hk-flight-attendant", "humorous-elder", "imposing-queen", "innocent-boy", "inspiring-lady", "intellectual-girl", "intellectual-man", "intellectual-senior", "intonate-girl", "jovial-man", "kind-hearted-antie", "kind-hearted-elder", "kind-hearted-girl", "kind-lady", "kind-woman", "laid-back-girl", "level-headed-man", "lonely-warrior", "lovely-girl", "lovely-lady", "loyal-knight", "lyrical-voice", "magnetic-voiced-male", "male-anchor", "male-announcer", "male-debater", "male-narrator", "man-with-deep-voice", "mature-lady", "mature-partner", "mature-woman", "movie-lead-female", "mysterious-girl", "narrator", "naughty-schoolgirl", "news-anchor", "optimistic-youth", "passionate-warrior", "patient-female-presenter", "patient-man", "pessimistic-girl", "playboy-charmer", "playful-girl", "playful-man", "playful-spirit", "pompous-lady", "possessive-man", "powerful-soldier", "powerful-veteran", "professional-female-host", "professional-male-host", "pure-hearted-boy", "quirky-girl", "radiant-girl", "radio-host", "rational-man", "reliable-executive", "reliable-man", "reliable-sister", "reliable-youth", "reserved-young-man", "robot-armor", "romantic-husband", "rudolph", "russian-brightheroine", "sad-teen", "santa-claus", "sassy-girl", "sensible-manager", "sentimental-lady", "serene-elder", "serene-man", "serene-woman", "serious-commander", "shy-girl", "sincere-adult", "sincere-teen", "smart-young-girl", "soft-girl", "soft-spoken-girl", "soothing-lady", "sophisticated-lady", "southern-young-man", "sporty-student", "steadfast-narrator", "steady-mentor", "straightforward-boy", "stressed-lady", "strict-boss", "strong-willed-boy", "stubborn-friend", "sweet-girl", "sweet-lady", "teen-boy", "theatrical-actor", "thoughtful-lady", "thoughtful-man", "thoughtful-mentor", "thoughtful-woman", "tough-boss", "tranquil-woman", "trustworthy-advisor", "trustworthy-man", "unrestrained-young-man", "upbeat-man", "upbeat-woman", "upset-girl", "wandering-sorcerer", "warm-bestie", "warm-girl", "warm-hearted-aunt", "warm-hearted-girl", "whimsical-girl", "whispering-girl", "wise-elf", "wise-lady", "wise-scholar", "wise-teacher", "wise-women" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "speed": { "required": false, "type": "number", "description": "Speech speed multiplier." }, "volume": { "required": false, "type": "number", "description": "Volume level (MiniMax ``vol``)." }, "pitch": { "required": false, "type": "integer", "description": "Pitch adjustment." }, "language": { "required": false, "type": "string", "description": "Language boost code (MiniMax ``language_boost``)." }, "response_format": { "required": false, "type": "string", "description": "Audio output format." } } }, { "name": "MiniMax: Speech 2.6 Turbo", "description": "MiniMax Speech 2.6 Turbo TTS voices.", "id": "minimax-speech-2.6-turbo", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 34 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "minimax", "name": "MiniMax", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 34 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "airheaded-girl", "ambitious-woman", "angry-man", "anime-character", "arnold", "arrogant-miss", "assertive-queen", "assetive-woman", "assured-presenter", "athletic-girl", "athletic-student", "attractive-girl", "attractive-guy", "aussie-bloke", "bad-tempered-boy", "bashful-girl", "bossy-lady", "bossy-leader", "brave-adventurer", "brave-female-warrior", "brave-heroine", "brave-youth", "calm-gentleman", "calm-lady", "calm-leader", "calm-woman", "captivating-female", "captivating-storyteller", "caring-girlfriend", "caring-man", "caring-woman", "casual-man", "casual-woman", "charming-elder-sister", "charming-girl", "charming-lady", "charming-queen", "charming-santa", "charming-sister", "chatty-girl", "cheerful-boyfriend", "cheerful-cool-junior", "cheerful-little-sister", "childhood-friend-girl", "cocky-guy", "cold-girl", "cold-queen", "cold-young-man", "comedian", "compelling-girl", "compelling-lady", "confident-boss", "confident-woman", "conscientious-instructor", "considerate-senior", "crazy-girl", "crisp-girl", "cute-girl", "cute-spirit", "debator", "decent-young-man", "decisive-princess", "decisive-queen", "deep-toned-man", "deep-voiced-gentleman", "dependable-woman", "determined-boy", "determined-manager", "diligent-leader", "diligent-man", "dominant-man", "dramatist", "elegant-girl", "elegant-lady", "elegant-princess", "enchanting-sister", "energetic-boy", "energetic-woman", "energetic-youth", "enthusiastic-teen", "explorative-girl", "expressive-narrator", "fascinating-boy", "female-anchor", "female-narrator", "fragile-boy", "frank-lady", "friendly-big-sister", "friendly-boy", "friendly-guy", "friendly-man", "friendly-neighbor", "fussy-hostess", "generous-izakaya-owner", "gentle-boss", "gentle-butler", "gentle-girl", "gentle-lady", "gentle-senior", "gentle-teacher", "gentle-voiced-man", "gentle-woman", "gentle-youth", "gentleman", "ghost", "girl-next-door", "godfather", "gorgeous-lady", "graceful-lady", "graceful-maiden", "grim-reaper", "grinch", "handsome-childhood-friend", "haughty-lady", "hk-flight-attendant", "humorous-elder", "imposing-queen", "innocent-boy", "inspiring-lady", "intellectual-girl", "intellectual-man", "intellectual-senior", "intonate-girl", "jovial-man", "kind-hearted-antie", "kind-hearted-elder", "kind-hearted-girl", "kind-lady", "kind-woman", "laid-back-girl", "level-headed-man", "lonely-warrior", "lovely-girl", "lovely-lady", "loyal-knight", "lyrical-voice", "magnetic-voiced-male", "male-anchor", "male-announcer", "male-debater", "male-narrator", "man-with-deep-voice", "mature-lady", "mature-partner", "mature-woman", "movie-lead-female", "mysterious-girl", "narrator", "naughty-schoolgirl", "news-anchor", "optimistic-youth", "passionate-warrior", "patient-female-presenter", "patient-man", "pessimistic-girl", "playboy-charmer", "playful-girl", "playful-man", "playful-spirit", "pompous-lady", "possessive-man", "powerful-soldier", "powerful-veteran", "professional-female-host", "professional-male-host", "pure-hearted-boy", "quirky-girl", "radiant-girl", "radio-host", "rational-man", "reliable-executive", "reliable-man", "reliable-sister", "reliable-youth", "reserved-young-man", "robot-armor", "romantic-husband", "rudolph", "russian-brightheroine", "sad-teen", "santa-claus", "sassy-girl", "sensible-manager", "sentimental-lady", "serene-elder", "serene-man", "serene-woman", "serious-commander", "shy-girl", "sincere-adult", "sincere-teen", "smart-young-girl", "soft-girl", "soft-spoken-girl", "soothing-lady", "sophisticated-lady", "southern-young-man", "sporty-student", "steadfast-narrator", "steady-mentor", "straightforward-boy", "stressed-lady", "strict-boss", "strong-willed-boy", "stubborn-friend", "sweet-girl", "sweet-lady", "teen-boy", "theatrical-actor", "thoughtful-lady", "thoughtful-man", "thoughtful-mentor", "thoughtful-woman", "tough-boss", "tranquil-woman", "trustworthy-advisor", "trustworthy-man", "unrestrained-young-man", "upbeat-man", "upbeat-woman", "upset-girl", "wandering-sorcerer", "warm-bestie", "warm-girl", "warm-hearted-aunt", "warm-hearted-girl", "whimsical-girl", "whispering-girl", "wise-elf", "wise-lady", "wise-scholar", "wise-teacher", "wise-women" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "speed": { "required": false, "type": "number", "description": "Speech speed multiplier." }, "volume": { "required": false, "type": "number", "description": "Volume level (MiniMax ``vol``)." }, "pitch": { "required": false, "type": "integer", "description": "Pitch adjustment." }, "language": { "required": false, "type": "string", "description": "Language boost code (MiniMax ``language_boost``)." }, "response_format": { "required": false, "type": "string", "description": "Audio output format." } } }, { "name": "MiniMax: Speech 2.8 Turbo", "description": "MiniMax Speech 2.8 Turbo TTS voices.", "id": "minimax-speech-2.8-turbo", "object": "model", "created": 1788985190, "owned_by": "minimax", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 34 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "minimax", "name": "MiniMax", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 34 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "airheaded-girl", "ambitious-woman", "angry-man", "anime-character", "arnold", "arrogant-miss", "assertive-queen", "assetive-woman", "assured-presenter", "athletic-girl", "athletic-student", "attractive-girl", "attractive-guy", "aussie-bloke", "bad-tempered-boy", "bashful-girl", "bossy-lady", "bossy-leader", "brave-adventurer", "brave-female-warrior", "brave-heroine", "brave-youth", "calm-gentleman", "calm-lady", "calm-leader", "calm-woman", "captivating-female", "captivating-storyteller", "caring-girlfriend", "caring-man", "caring-woman", "casual-man", "casual-woman", "charming-elder-sister", "charming-girl", "charming-lady", "charming-queen", "charming-santa", "charming-sister", "chatty-girl", "cheerful-boyfriend", "cheerful-cool-junior", "cheerful-little-sister", "childhood-friend-girl", "cocky-guy", "cold-girl", "cold-queen", "cold-young-man", "comedian", "compelling-girl", "compelling-lady", "confident-boss", "confident-woman", "conscientious-instructor", "considerate-senior", "crazy-girl", "crisp-girl", "cute-girl", "cute-spirit", "debator", "decent-young-man", "decisive-princess", "decisive-queen", "deep-toned-man", "deep-voiced-gentleman", "dependable-woman", "determined-boy", "determined-manager", "diligent-leader", "diligent-man", "dominant-man", "dramatist", "elegant-girl", "elegant-lady", "elegant-princess", "enchanting-sister", "energetic-boy", "energetic-woman", "energetic-youth", "enthusiastic-teen", "explorative-girl", "expressive-narrator", "fascinating-boy", "female-anchor", "female-narrator", "fragile-boy", "frank-lady", "friendly-big-sister", "friendly-boy", "friendly-guy", "friendly-man", "friendly-neighbor", "fussy-hostess", "generous-izakaya-owner", "gentle-boss", "gentle-butler", "gentle-girl", "gentle-lady", "gentle-senior", "gentle-teacher", "gentle-voiced-man", "gentle-woman", "gentle-youth", "gentleman", "ghost", "girl-next-door", "godfather", "gorgeous-lady", "graceful-lady", "graceful-maiden", "grim-reaper", "grinch", "handsome-childhood-friend", "haughty-lady", "hk-flight-attendant", "humorous-elder", "imposing-queen", "innocent-boy", "inspiring-lady", "intellectual-girl", "intellectual-man", "intellectual-senior", "intonate-girl", "jovial-man", "kind-hearted-antie", "kind-hearted-elder", "kind-hearted-girl", "kind-lady", "kind-woman", "laid-back-girl", "level-headed-man", "lonely-warrior", "lovely-girl", "lovely-lady", "loyal-knight", "lyrical-voice", "magnetic-voiced-male", "male-anchor", "male-announcer", "male-debater", "male-narrator", "man-with-deep-voice", "mature-lady", "mature-partner", "mature-woman", "movie-lead-female", "mysterious-girl", "narrator", "naughty-schoolgirl", "news-anchor", "optimistic-youth", "passionate-warrior", "patient-female-presenter", "patient-man", "pessimistic-girl", "playboy-charmer", "playful-girl", "playful-man", "playful-spirit", "pompous-lady", "possessive-man", "powerful-soldier", "powerful-veteran", "professional-female-host", "professional-male-host", "pure-hearted-boy", "quirky-girl", "radiant-girl", "radio-host", "rational-man", "reliable-executive", "reliable-man", "reliable-sister", "reliable-youth", "reserved-young-man", "robot-armor", "romantic-husband", "rudolph", "russian-brightheroine", "sad-teen", "santa-claus", "sassy-girl", "sensible-manager", "sentimental-lady", "serene-elder", "serene-man", "serene-woman", "serious-commander", "shy-girl", "sincere-adult", "sincere-teen", "smart-young-girl", "soft-girl", "soft-spoken-girl", "soothing-lady", "sophisticated-lady", "southern-young-man", "sporty-student", "steadfast-narrator", "steady-mentor", "straightforward-boy", "stressed-lady", "strict-boss", "strong-willed-boy", "stubborn-friend", "sweet-girl", "sweet-lady", "teen-boy", "theatrical-actor", "thoughtful-lady", "thoughtful-man", "thoughtful-mentor", "thoughtful-woman", "tough-boss", "tranquil-woman", "trustworthy-advisor", "trustworthy-man", "unrestrained-young-man", "upbeat-man", "upbeat-woman", "upset-girl", "wandering-sorcerer", "warm-bestie", "warm-girl", "warm-hearted-aunt", "warm-hearted-girl", "whimsical-girl", "whispering-girl", "wise-elf", "wise-lady", "wise-scholar", "wise-teacher", "wise-women" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "speed": { "required": false, "type": "number", "description": "Speech speed multiplier." }, "volume": { "required": false, "type": "number", "description": "Volume level (MiniMax ``vol``)." }, "pitch": { "required": false, "type": "integer", "description": "Pitch adjustment." }, "language": { "required": false, "type": "string", "description": "Language boost code (MiniMax ``language_boost``)." }, "response_format": { "required": false, "type": "string", "description": "Audio output format." } } }, { "name": "Resemble: Pro", "description": "Resemble Pro TTS voices.", "id": "resemble-pro", "object": "model", "created": 1788985190, "owned_by": "resemble", "tokens": 950, "pricing": { "type": "per_million_tokens", "input": 8 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "resemble", "name": "Resemble", "tokens": 950, "pricing": { "type": "per_million_tokens", "input": 8 } } ], "context_length": 950, "max_model_len": 950, "max_input_tokens": 950, "voices": [ "aaron-en-us", "abigail-en-us", "aida", "alessandro", "alma", "alparslan", "anaya-en-us", "andrew-en-us", "andy-en-us", "anne-louise-da", "archer-en-us", "avigail", "ayaan", "brian-en-us", "casual-conversational-dialogue", "chloe-en-us", "christina-en-us", "darlene-en-us", "deborah-en-us", "dorothy-en-us", "dylan-en-us", "elaine-en-us", "eloise-fr-fr", "emmanuel-en-us", "eric-en-us", "erica-en-us", "ethan-en-us", "evelyn-en-us", "fiona-en-us", "francesca", "gavin-en-us", "gianluca-en-us", "gordon-en-us", "grace-en-us", "grant-en-us", "hao", "harel", "haruto", "helmi", "jaakko", "jason-en-us", "jessica-en-us", "ji-ho-ko", "ji-woo-ko", "kari", "laura-en-us", "lauren-en-us", "linda-en-us", "lisa-en-us", "lucia", "lucy-en-us", "marisol-en-us", "mark-en-us", "mateo", "meera-en-us", "mei", "mikhail", "minho-en-us", "nikodem", "noah", "ola", "pleasant-conversational-dialogue", "pleasant-informative-educational", "professional-conversational-dialogue", "rajesh-en-us", "raphael-fr-fr", "rupert-en-us", "social-media-gaming-ads-e-learning-voice-assistant-dubbing-podcasts", "soren", "tess", "walter-en-us", "zuzanna" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "response_format": { "required": false, "type": "string", "description": "Audio format (Resemble ``format``)." }, "sample_rate": { "required": false, "type": "string", "description": "Audio sample rate." }, "precision": { "required": false, "type": "string", "description": "Synthesis precision." } } }, { "name": "Resemble: Turbo", "description": "Resemble Turbo TTS voices.", "id": "resemble-turbo", "object": "model", "created": 1788985190, "owned_by": "resemble", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 8 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "resemble", "name": "Resemble", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 8 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aaron-en-us", "abigail-en-us", "adam-lofbomm-en-us", "alex-en-us", "amelia-en-us", "anaya-en-us", "andrew-en-us", "andy-en-us", "annika-en-us", "archer-en-us", "arthur-en-us", "ash-en-us", "aurora-en-us", "austin-en-us", "beth-en-us", "blade-en-us", "brandy-sky-en-us", "brenley-en-us", "brian-en-us", "britney-en-us", "broadcast-joe-en-us", "carl-bishop-angry-en-us", "carl-bishop-conversational-en-us", "carl-bishop-en-us", "carl-bishop-happy-en-us", "carl-bishop-scared-en-us", "charles-en-us", "charlotte-en-us", "chloe-en-us", "chris-whiting-en-us", "christina-en-us", "cliff-en-us", "connor-en-us", "darlene-en-us", "david-en-us", "deanna-en-us", "deborah-en-us", "dorothy-en-us", "dylan-en-us", "elaine-en-us", "ember-en-us", "emmanuel-en-us", "eric-en-us", "erica-en-us", "ethan-en-us", "evelyn-en-us", "fiona-en-us", "gavin-en-us", "gene-amore-en-us", "gianluca-en-us", "gordon-en-us", "grace-en-us", "grant-en-us", "harry-robinson-en-us", "helena-en-us", "hem-en-us", "jason-en-us", "jessica-en-us", "john-en-us", "josh-en-us", "julie-hoverson-en-us", "justin-en-us", "justin-meditative-en-us", "karl-nordman-en-us", "kate-en-us", "katya-en-us", "ken-en-us", "kessi-en-us", "laura-en-us", "lauren-en-us", "linda-en-us", "lisa-en-us", "little-ari-en-us", "little-brittle-en-us", "liz-en-us", "lothar-en-us", "lucy-en-us", "luna-en-us", "marisol-en-us", "mark-en-us", "matt-weller-en-us", "maureen-angry-en-us", "maureen-caring-en-us", "maureen-en-us", "maureen-happy-en-us", "maureen-sad-en-us", "maureen-scared-en-us", "mauren-announcer-en-us", "meera-en-us", "melody-en-us", "mike-en-us", "minho-en-us", "niki-en-us", "olga-en-us", "olivia-en-us", "orion-en-us", "pete-en-us", "primrose-en-us", "primrose-winded-en-us", "professor-shaposhnikov-en-us", "radio-nikole-en-us", "rajesh-en-us", "richard-garifo-en-us", "rico-en-us", "robert-en-us", "rupert-en-us", "sam-en-us", "samantha-en-us", "siobhan-en-us", "steve-scared-en-us", "tanja-en-us", "tanja-telephonic-en-us", "tanja-warm-word-weaver-en-us", "tarkos-en-us", "tyler-en-us", "vicky-en-us", "vivian-en-us", "walter-en-us", "william-whispering-en-us", "willow-ii-whispering-en-us", "willow-whispering-en-us" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "response_format": { "required": false, "type": "string", "description": "Audio format (Resemble ``format``)." }, "sample_rate": { "required": false, "type": "string", "description": "Audio sample rate." }, "precision": { "required": false, "type": "string", "description": "Synthesis precision." } } }, { "name": "Speechify: simba 3.0 TTS", "description": "Speechify: simba 3.0 TTS text-to-speech.", "id": "speechify-simba-3.0", "object": "model", "created": 1788985190, "owned_by": "speechify", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 5 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "speechify", "name": "Speechify", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 5 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aadi", "aaliya", "aamir", "abhay", "abhijit", "abirami", "adeline", "aditya", "adriana", "aesha", "aftab", "agathe", "agrippina", "agueda", "ah-reum", "aicha", "aishwarya", "aitana", "akari", "akhila", "alec", "alejandra", "alejandro", "alessia", "alessio", "alexa", "alexandre", "alexei", "alfonso", "alicia", "aline", "alok", "alondra", "alper", "alton", "amalia", "amelie", "amey", "amir", "ammu", "amon", "anagha", "anais", "anatoly", "anders", "andra", "andre", "andreas", "andrey", "anette", "angel", "angele", "angelique", "aniket", "anirban", "ankit", "anneli", "anni", "annika", "anniken", "anouk", "anthony", "anton", "anup", "anwesha", "aparna", "apeksha", "aravind", "archie", "arda", "arianna", "aritra", "arkady", "arooj", "artem", "arturo", "arun", "asa", "ashwin", "ashwini", "asif", "asuka", "augustin", "augustine", "aurelie", "aurora", "avik", "axel", "ayaka", "ayden", "aylin", "ayse", "bar-s", "bart", "bas", "beatrice", "belinda", "ben", "benedetta", "benedikt", "bengt", "benjamin", "bente", "bertha", "beth", "beverly", "bhagyashree", "bhanu", "bharani", "bharat", "bharath", "bhavani", "bhavin", "bhumika", "bhushan", "bilal", "birgitta", "birgitte", "bjorn", "bo", "bo-kyung", "boris", "bram", "brenda", "bridget", "brishti", "britt", "bruna", "bruno", "burak", "bushra", "busra", "byron", "caio", "camilla", "camille", "can", "carina", "carine", "carlotta", "carly", "carmen", "carol", "carolina", "carsten", "carter", "caterina", "catriona", "cecile", "cecilie", "celia", "cem", "ceyda", "chad", "chaitali", "chaitanya", "charan", "charlotte", "charvi", "chase", "chetan", "chi-wai", "chiara", "chihiro", "chinmay", "christelle", "chun-kit", "chun-wah", "chuy", "cihan", "clarissa", "claudette", "claudine", "claus", "clement", "cleon", "collin", "cristiane", "da-hyun", "daan", "dae-hyun", "daiki", "daisy", "daniela", "daniele", "danilo", "danna-sofia", "daria", "darina", "darla", "davi", "davide", "debashish", "debora", "declan", "deepak", "delphine", "denise", "deniz", "dhaval", "diego", "diksha", "dinesh", "diogo", "ditte", "divya", "do-hyun", "dominic", "dominika", "dominique", "donald", "dorian", "douglas", "earnest", "ebba", "ebru", "eden", "edmund", "edoardo", "eduarda", "egil", "egor", "eino", "eirik", "eirin", "ekaterina", "elango", "eleni", "eleonora", "elia", "eliane", "elif", "elijah", "elina", "elisabeth", "elise", "elizaveta", "ella", "emanuela", "emelie", "emiliano", "emilie", "emily", "emmanuel", "emre", "enea", "enzo", "eren", "eri", "erica", "erin", "erkan", "esben", "esmeralda", "espen", "esra", "estefania", "estela", "estelle", "etienne", "eugenie", "eun-ha", "eun-ji", "evelyn", "evelyne", "evie", "fabian", "fabio", "faizan", "falak", "farhan", "farzana", "fatma", "federica", "fedor", "femke", "fernando", "fidel", "filip", "filippo", "floris", "francesca", "francesco", "francisco", "fraser", "frederick", "frederik", "fredrik", "freja", "frida", "friedrich", "froja", "funda", "ga-young", "gabi", "gabin", "gabriel", "gabriele", "gael", "gaia", "galina", "garry", "gary", "geffen", "george", "gerrit", "giada", "gijs", "gil", "ginevra", "gioele", "giorgia", "gitte", "giulia", "giulio", "gleb", "gokul", "gozde", "greta", "grishma", "gry", "guille", "gunilla", "guro", "gustavo", "gwen", "ha-eun", "hakan", "hamish", "hande", "hanna", "hanne", "hannes", "harald", "harini", "harper", "harsha", "harshal", "haru", "haruka", "haruto", "hassan", "hatice", "havard", "hedda", "hee-young", "heidi", "helen", "helena", "helene", "helle", "helmi", "hemant", "hendrik", "henrik", "henrique", "henry", "hetal", "hetvi", "hikaru", "himi", "hina", "hinata", "hiren", "hiu-ching", "hugh", "hye-jin", "hye-won", "hyeon-seok", "hyun-joo", "hyun-woo", "ibrahim", "iker", "ilango", "ilaria", "ilya", "imogen", "imran", "inbar", "indranil", "ines", "inessa", "inger", "ipsita", "iravati", "irina", "isabela", "isabelle", "ishaan", "ishita", "ismail", "iswarya", "itsuki", "ivanna", "jack", "jacob", "jagadeesh", "jaime", "jakob", "james", "janani", "janelle", "jannik", "jasmijn", "jasper", "jean", "jennifer", "jens", "jeroen", "jesper", "jesse", "jesus", "ji-eun", "ji-hoon", "ji-seok", "jignesh", "jimena", "joao", "joe", "johan", "johanne", "john-rhys-davies", "jonathan", "joo-hyun", "joon-ho", "joost", "jordan", "jose-angel", "jose-luis", "jose-manuel", "josefin", "josefine", "juan-carlos", "juan-pablo", "jules", "juliana", "julie", "julieta", "juna", "junaid", "jung-ho", "jyoti", "ka-yan", "kaan", "kaede", "kaito", "kakoli", "kalai", "kalpit", "kalyani", "kana", "kara", "karen", "karin", "karlijn", "karthik", "karuna", "kashif", "katarina", "katharina", "kausalya", "kaviya", "kayla", "kazuki", "keenan", "keisuke", "kenshin", "kerstin", "ketaki", "keyur", "khusbu", "kim", "kin-fung", "kinjal", "kiran", "kirill", "kjeld", "kjetil", "koel", "koen", "komal", "konstantin", "kostas", "krishna", "kristian", "kristin", "kristy", "krunal", "ksenia", "kshitij", "kumari", "kylian", "kyung-soo", "l-rke", "laboni", "lakshmi", "lalitha", "larisa", "lars", "lasse", "lazzaro", "leah", "leif", "lenny", "leonard", "leonardo", "leonid", "lesya", "leticia", "lexi", "lieke", "liis", "lillian", "lina", "linda", "lindy", "line", "linnea", "linus", "lisa", "lisanne", "lisbeth", "lital", "lizbeth", "lola", "lorne", "lotte", "louis", "louise", "lowell", "luana", "lubna", "luca", "lucas", "lucia", "luciana", "ludmila", "ludovica", "ludvig", "luigi", "luis-angel", "luisa", "luiz", "luiza", "lyla", "lyle", "lyudmila", "madhu", "mael", "magnus", "maheshwar", "malin", "mandar", "manikandan", "manjula", "marcio", "marco", "marcus", "margherita", "mari", "marian", "mariana", "marianne", "marieke", "marit", "marius", "marjolein", "mark", "markus", "marnie", "mart", "martijn", "martina", "martine", "masaki", "mason", "mateus", "mathilda", "mathilde", "mathis", "matias", "matilde", "mats", "matteo", "mattia", "maud", "maxime", "maximilian", "maximiliano", "meenal", "meera", "mees", "megan", "mehmet", "mehul", "mei", "melek", "melina", "melisa", "merle", "mi-ran", "micha", "michael", "mieke", "miguel-angel", "mihir", "mikael", "mikhail", "mikkel", "mila", "milan", "milana", "mildred", "milind", "mille", "milyena", "min-jae", "min-seo", "misaki", "momoka", "monica", "monika", "moritz", "moshe", "mousumi", "mrunal", "murat", "murugan", "mustafa", "nadezhda", "nael", "naitik", "najma", "nandhini", "nandita", "nanna", "naresh", "nargis", "natalia", "natsuki", "naureen", "naveed", "naveen", "navit", "nazia", "neha", "nehir", "nele", "niccolo", "nick", "nico", "nicoline", "niels", "nienke", "nikhil", "nikki", "niklas", "nikolai", "nikolaj", "nila", "nilay", "nilesh", "ninad", "nino", "nirali", "nirav", "nivedita", "noe", "noman", "nozomi", "oda", "odd", "oguz", "oksana", "ole", "oleg", "olga", "oliver", "omer", "omkar", "oskar", "otavio", "otto", "oxana", "ozge", "padma", "parag", "partha", "patricia", "patrik", "paulette", "paulo", "pavel", "pavithra", "payel", "pepe", "per", "phil", "philip", "philipp", "pia", "pietro", "piyali", "pooja", "poul", "prabhu", "prajakta", "pranav", "prasanna", "pratik", "preben", "priscila", "priya", "priyadharshini", "purva", "quinten", "rachele", "rafael", "ragavan", "raghu", "ragnhild", "raissa", "rajdeep", "rajeshwari", "rajeswari", "rajiv", "rajvardhan", "rakesh", "raktim", "ramanan", "ramon", "raphael", "rasmus", "ravi", "ravindra", "rayan", "reba", "regina", "reina", "rekha", "ren", "rens", "revathi", "revati", "rianne", "riccardo", "richard", "riddhi", "rika", "rikke", "riko", "riku", "rimjhim", "rin", "ritwik", "riya", "rizwan", "roar", "rob", "robbie", "roel", "rohan", "rohit", "rohon", "rolf", "romain", "romina", "romy", "ronja", "roos", "rory", "rosana", "rosanna", "roshni", "rubina", "ruby", "rukhsar", "runa", "rupal", "rupsha", "ryosuke", "ryota", "s-ren", "sabrina", "sacha", "sachin", "sagnik", "sai", "sajid", "sakshi", "sakura", "salvatore", "samarth", "sameer", "samina", "samuele", "sander", "sang-hoon", "sanjai", "sanket", "sanne", "sanya", "saptarshi", "saravanan", "saskia", "sathish", "sayaka", "sayali", "sayantan", "selin", "senga", "senthil", "sergey", "serkan", "seung-min", "seung-yeon", "sevgi", "shabnam", "shahid", "shahrukh", "shanna", "shanvika", "sharvani", "shazia", "shohei", "shota", "shraddha", "shubhangi", "sibel", "siddharth", "sienna", "sigrid", "silje", "silvia", "sinan", "sirisha", "snehalatha", "sofia", "soham", "solveig", "soo-min", "soujanya", "sourav", "souta", "sowmya", "sraboni", "sreya", "srikanth", "srilatha", "srinivas", "stacy", "stanislav", "stefan", "stefano", "steve", "stian", "stine", "subha", "suchismita", "suman", "sumbul", "sun-hee", "sundar", "sung-hoon", "sunitha", "sunniva", "suraj", "suresh", "susan", "sven", "sverre", "swapna", "swati", "tae-hyun", "taimoor", "taisiya", "tak-wah", "tanmay", "tanmoy", "tanushree", "tanvi", "taras", "tariq", "tasha", "tasneem", "tatiana", "tatiane", "tatsuya", "tehmina", "tejaswini", "tharani", "tharun", "thea", "thiago", "thijs", "thoa", "tiago", "timo", "timofey", "tine", "tirtha", "tithi", "titli", "tiyasha", "todd", "tommaso", "tonje", "tonya", "tor", "torben", "tore", "tove", "trine", "trinh", "tsubasa", "turid", "tushar", "twan", "ugur", "ujjwal", "ulla", "ulyana", "unai", "urja", "usman", "utsav", "vaidehi", "valentin", "valeria", "valery", "vamsi", "varsha", "varun", "vasudha", "veerle", "vega", "vegard", "velu", "vetri", "vibeke", "victoria", "vidar", "vidhya", "vignesh", "viktor", "vinay", "vincenzo", "violetta", "vitor", "vittoria", "vladislav", "vyacheslav", "vyom", "wai-kin", "waleed", "wesley", "wing-hong", "woo-jin", "woodrow", "wouter", "wren", "wyatt", "xenia", "ximena", "yamileth", "yamuna", "yan-ting", "yasemin", "yash", "yasir", "yeon-woo", "yoo-jin", "yoon-jung", "ystein", "yug", "yui", "yulia", "yuna", "yusuf", "yuto", "yuvaraj", "zainab", "zeeshan", "zeynep", "zoya", "zubair" ] }, { "name": "Speechify: simba 3.2 TTS", "description": "Speechify: simba 3.2 TTS text-to-speech.", "id": "speechify-simba-3.2", "object": "model", "created": 1788985190, "owned_by": "speechify", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 5 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "speechify", "name": "Speechify", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 5 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "alec", "alfonso", "alicia", "alton", "amon", "ankit", "anthony", "archie", "arun", "beatrice", "belinda", "benjamin", "bertha", "beth", "beverly", "brenda", "bridget", "byron", "carly", "carol", "carter", "catriona", "chad", "charlotte", "chase", "clarissa", "claudette", "cleon", "collin", "daisy", "darla", "declan", "denise", "dominic", "donald", "dorian", "douglas", "earnest", "edmund", "elijah", "emily", "erica", "erin", "evelyn", "evie", "fraser", "garry", "gary", "geffen", "george", "gwen", "hamish", "harper", "helen", "henry", "hugh", "imogen", "jack", "jacob", "jaime", "james", "janelle", "jean", "jennifer", "jesse", "joe", "john-rhys-davies", "jordan", "julie", "kara", "karen", "kayla", "keenan", "kim", "kristin", "kristy", "leah", "leonard", "lexi", "lillian", "linda", "lindy", "lisa", "lorne", "lowell", "lyla", "lyle", "marco", "marcus", "marian", "mark", "marnie", "mason", "megan", "michael", "mildred", "monica", "nick", "nikki", "oliver", "paulette", "phil", "reba", "regina", "richard", "rob", "robbie", "rohit", "rory", "ruby", "sabrina", "senga", "sienna", "stacy", "steve", "susan", "tasha", "todd", "tonya", "victoria", "woodrow", "wren", "wyatt" ] }, { "name": "Telnyx: Bayan TTS", "description": "Telnyx Bayan Arabic dialect TTS voices.", "id": "telnyx-bayan-tts", "object": "model", "created": 1788985190, "owned_by": "telnyx", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 3 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "telnyx", "name": "Telnyx", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "bah", "egy", "en", "eng", "irq", "jor", "ksa", "kuw", "leb", "msa", "oma", "pls", "qat", "syr", "uae" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "Audio format. Sukhan is restricted to mp3 or pcm (no wav)." } } }, { "name": "Hexgrad: Kokoro TTS", "description": "Hexgrad Kokoro-82M low-latency open-weight TTS.", "id": "kokoro-tts", "object": "model", "created": 1788985190, "owned_by": "hexgrad", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 3 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "hexgrad", "name": "Hexgrad", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "adam", "alex", "alice", "alloy", "aoede", "bella", "daniel", "dora", "echo", "emma", "eric", "fable", "fenrir", "george", "heart", "isabella", "jessica", "kore", "lewis", "liam", "lily", "michael", "nicola", "nova", "onyx", "puck", "river", "santa", "sara", "sarah", "siwis", "sky" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." } } }, { "name": "Telnyx: LibriTTS", "description": "Telnyx LibriTTS open voices.", "id": "telnyx-libritts", "object": "model", "created": 1788985190, "owned_by": "telnyx", "tokens": 400, "pricing": { "type": "per_million_tokens", "input": 3 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "telnyx", "name": "Telnyx", "tokens": 400, "pricing": { "type": "per_million_tokens", "input": 3 } } ], "context_length": 400, "max_model_len": 400, "max_input_tokens": 400, "voices": [ "0", "1" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "speed": { "required": false, "type": "number", "minimum": 0.5, "maximum": 2.0, "default": 1.0, "description": "Speech rate multiplier (Telnyx ``voice_speed``). Range 0.5–2.0." }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "Audio response format when supported." } } }, { "name": "Alibaba: Qwen3 TTS", "description": "Alibaba Qwen3 TTS multilingual voices (Whiskey, Delta, Coastal Anchor, …).", "id": "qwen3-tts", "object": "model", "created": 1788985190, "owned_by": "alibaba", "tokens": 800, "pricing": { "type": "per_million_tokens", "input": 32 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "alibaba", "name": "Alibaba", "tokens": 800, "pricing": { "type": "per_million_tokens", "input": 32 } } ], "context_length": 800, "max_model_len": 800, "max_input_tokens": 800, "voices": [ "coastal-anchor", "delta", "pmm-tech-narrator", "sophie-marcea", "whiskey" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "speed": { "required": false, "type": "number", "minimum": 0.5, "maximum": 2.0, "default": 1.0, "description": "Speech rate multiplier (Telnyx ``voice_speed``). Range 0.5–2.0." }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "Audio response format when supported." } } }, { "name": "Telnyx: Sukhan TTS", "description": "Telnyx Sukhan TTS voices (narrator, support, news).", "id": "telnyx-sukhan-tts", "object": "model", "created": 1788985190, "owned_by": "telnyx", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 3 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "telnyx", "name": "Telnyx", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 3 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "broadband-support", "male-narrator", "news-reader", "paediatrician", "podcast-host", "prime-time-anchor", "qissa-khawan", "seerah-educator", "seerah-scholar", "senior-anchor", "shopkeeper", "sindhi-navigator", "sindhi-networker", "urdu-professor" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "Audio format. Sukhan is restricted to mp3 or pcm (no wav)." } } }, { "name": "Telnyx: Ultra TTS", "description": "Telnyx Ultra neural TTS — multilingual expressive speech.", "id": "telnyx-ultra-tts", "object": "model", "created": 1788985190, "owned_by": "telnyx", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 32 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "telnyx", "name": "Telnyx", "tokens": 1000, "pricing": { "type": "per_million_tokens", "input": 32 } } ], "context_length": 1000, "max_model_len": 1000, "max_input_tokens": 1000, "voices": [ "aadhya-soother", "aarav-old-time-storyteller", "aarti-conversationalist", "adi-efficient-expert", "adrian-explorer", "adriana-bright-entertainer", "agnieszka-coordinator", "agustin-clear-storyteller", "aiden-yogi", "aiko-calming-voice", "ailsa-warm-guide", "aina-meditation-guru", "aisyah-chat-partner", "alaric-wizard", "albert-firm-guide", "alec-spirited-salesman", "alejandro-calm-mentor", "alessandra-melodic-guide", "alexander-reliable-advisor", "alexei-articulate-analyst", "alfie-composed-advisor", "alina-engaging-assistant", "alistair-composed-consultant", "allen-modern-voice", "allie-natural-conversationalist", "alma-clear-advisor", "alondra-reassuring-sister", "amanda-warm-guide", "amazon-brooke-big-sister", "amazon-ronald-thinker", "amber-warm-support-agent", "amelia-instructor", "amelie-decisive-agent", "amelie-warm-concierge", "amira-dreamy-whisperer", "amit-sports-student", "ana-paula-marketer", "andi-dynamic-presenter", "andrada-steady-speaker", "andrea-clear-communicator", "andreas-recorder", "andrei-conversationalist-guy", "andres-trusted-voice", "andrzej-elder-voice", "anele-bright-presenter", "angel-welcoming-host", "angelo-calm-narrator", "anika-enthusiastic-seller", "anita-meditation-guide", "anitha-warm-guide", "anneke-trusted-guide", "anneliese-methodical-guide", "antoine-stern-man", "anuj-engaging-narrator", "archie-approachable-mate", "ariana-kind-friend", "ariane-captivating-tone", "arthur-polished-advisor", "arun-lively-voice", "arushi-hinglish-speaker", "arvin-reliable-guide", "asaf-steady-advisor", "asher-podcaster", "astrid-direct-director", "aubrey-easygoing-pal", "aurora-fairy-princess", "austin-conversational-guide", "avery-gaming-girl", "avi-calm-consultant", "aviva-patient-guide", "ayako", "aykut-friendly-companion", "aylin-warm-guide", "ayumi-sales-guide", "ayush-friendly-neighbor", "azra-service-specialist", "barry-2-0-helper", "barry-helper", "beatriz-support-guide", "ben-helpful-man", "bence-focused-facilitator", "benedict-measured-mediator", "benedict-royal-narrator", "benito-digital-voice", "benji-joyful-spirit", "benoit-methodical-moderator", "betty-reassured-guide", "bhavani-reassuring-companion", "blake-helpful-agent", "blanca-graceful-host", "brandon-confident-guy", "brenda-host", "brent-steady-conversationalist", "brittany-intense-performer", "brooke-big-sister", "bruno-reliable-communicator", "bryce-clear-explainer", "caleb-seasoned-pro", "callie-encourager", "callum-brand-spokesperson", "calm-french-woman", "calypso-asmr-lady", "cameron-chill-companion", "camila", "camila-happy-conversationalist", "camille-friendly-expert", "camille-gracious-guide", "carl-steady-storyteller", "carlo-roman-guide", "carlos", "carmen-friendly-neighbor", "carol-task-coach", "carolina-friendly-guide", "caroline-southern-guide", "carson-angry-friendly-support", "carson-curious-conversationalist", "carson-disgusted-friendly-support", "carson-friendly-support", "carson-sad-friendly-support", "carson-scared-friendly-support", "carson-surprised-friendly-support", "casper-gentle-narrator", "caspian-oracle", "catalina-neighborly-guide", "cathy-coworker", "cees-nordic-narrator", "celine-soothing-presence", "cera-lighthearted-muse", "chakrit-reliable-communicator", "chandler-easygoing-pal", "charlotte-heiress", "chase-steady-helper", "chloe-persuasive-lady", "christian", "cindy-baker-receptionist", "cindy-receptionist", "clara-instructor", "clarence-newsman", "clark-trustworthy-expert", "clarkson-executive-tone", "claudia-welcoming-lady", "clementine-hospitable-host", "clint-rugged-actor", "clyde-calm-narrator", "colby-lively-guy", "cole-clear-communicator", "colin-assured-guide", "connie-candid-conversationalist", "connor-grateful-person", "conor-decisive-agent", "conrad-seasoned-support", "cooper-friendly-mate", "corey-supportive-buddy", "cory-relaxed-voice", "dafna-supportive-guide", "daisuke-businessman", "daisy-reading-girl", "dallas-fireside-friend", "damon-commanding-narrator", "dana-balanced-spirit", "daniel-modern-assistant", "daniela-relaxed-woman", "daphne-excited-woman", "daria-decisive-dispatcher", "darius-engaging-narrator", "darla-resolution-agent", "david-angry-greeter", "david-curious-greeter", "david-disgusted-greeter", "david-greeter", "david-happy-greeter", "david-sad-greeter", "david-scared-greeter", "david-surprised-greeter", "dean-laidback-pal", "denise-professional-woman", "derek-deep-advisor", "derrick-professional-man", "despina-motherly-woman", "dev-friendly-host", "devansh-warm-support-agent", "devin-relaxed-spirit", "diana-animated-narrator", "diana-gentle-mom", "diane-service-assistant", "diego-hype-guy", "dieter-commercial-man", "dina-trusted-advisor", "diogo-promotion-lead", "divya-joyful-narrator", "diya-service-specialist", "dmitri-gentle-voice", "dominic-sportscaster", "donny-steady-presence", "doreen-decisive-coordinator", "doris-friend", "dorothy-easy-charm", "dottie-sweet-gal", "dylan-chill-companion", "eden-clear-advisor", "edith-matriarch", "edna-graceful-veteran", "edric-refined-mentor", "edward-persuasive-promoter", "eitan-modern-communicator", "elaine-confident-guide", "eleanor-composed-clarifier", "elena-narrator", "eleni-troubleshooter", "elias-night-warden", "elif-structured-supporter", "elina-clear-presenter-woman", "eliott-positive-spirit", "elise-helpful-voice", "elizabeth-manager", "ella-caring-scout", "ellie-mae-friendly-companion", "elliott-reflective-storyteller", "eloise-dialogue-anchor", "emi", "emi-soft-spoken-friend", "emilio-friendly-optimist", "emily-easygoing-pal", "emma-customer-care-line", "emmanuelle", "emre-calming-speaker", "erik-social-speaker", "erin-joyful-guide", "erwan-everyday-speaker", "esther-gracious-helper", "eszter-customer-companion", "ethan-casual-assistant", "evan-practical-guide", "evelyn-digital-assistante", "evelyn-peaceful-whisper", "evie-engaging-expert", "ewa-efficient-envoy", "eyal-grounded-guide", "faiz-family-guide", "fatima-graceful-guide", "faye-hospitable-neighbor", "fernanda-friendly-guide", "fiona-witty-woman", "fleur-vibrant-voice", "francesca-elegant-partner", "freja-nordic-reader", "french-narrator-lady", "french-narrator-man", "friendly-french-man", "gabor-reassuring-voice", "garrett-enthusiastic-pal", "gary-composed-advisor", "gavin-friendly-vibe", "gemma-decisive-agent", "george-composed-consultant", "georgi-conversationalist", "gerard", "gerard-monsieur-noir", "giancarlo-support-leader", "gil-friendly-host", "giulia-teacherly-voice", "giuseppe-retro-man", "gonzalo-grounded-storyteller", "grace-helpful-hand", "graham-assured-helper", "grant-friendly-support", "greg-supporter", "griffin-excited-narrator", "griffin-narrator", "guadalupe-wise-storyteller", "gurpreet-companion", "gustavo-steady-advisor", "haeun-polished-presence", "haley-engaging-friend", "hana-easygoing-support", "hao-friendly-guy", "harlan-vintage-tone", "harley-comforting-voice", "harper-conversationalist", "harrison-diligent-detailer", "haruka-gracious-guide", "hassan-authoritative-narrator", "heath-calm-composed", "hector-tour-leader", "heitor-easygoing-local", "helmi-warm-friend", "henrik-refined-narrator", "henrik-steady-analyst", "henry-plainspoken-guy", "hermann-businessman", "hinata-graceful-guide", "hiroshi-dependable-director", "holly-joyful-presence", "howard-approachable-man", "hua-sunny-support", "huda-approachable-speaker", "hugh-confident-veteran", "hugo-teatime-friend", "hyerin-graceful-host", "imogen-polished-guide", "imran-hindi-film-actor", "ines-poised-communicator", "ingrid-peaceful-guide", "irina-poetic-voice", "iris-friendly-specialist", "isa-empathetic-ear", "isabel-confident-woman", "isabel-teacher", "isabella-warm-storyteller", "isabelle-professional-liaison", "isha-learner", "ishan-ally", "isla-serene-flow", "itai-measured-advisor", "ivan-bar-companion", "ivana-instruction-provider", "jace-cool-conversationalist", "jacqueline-reassuring-agent", "jaewon-steady-advisor", "jake-sidekick", "jakub-gentle-guide", "james-navigator", "jameson-easygoing-support", "jamie-comforting-presence", "jan", "jan-capable-coordinator", "jana-crisp-conversationalist", "jane-digital-guide", "janet-sunny-speaker", "janice-engaging-tone", "janvi-steady-agent", "jari-reliable-representative", "jasper-service-specialist", "jasper-vibrant-stylist", "jaspreet-commercial-woman", "javier-gentle-advisor", "jennifer", "jeremy-energetic-promoter", "jeroen-clear-storyteller", "jerome-empathetic-voice", "jeronimo-empathetic-advisor", "jessica-clear-communicator", "jett-helpful-pal", "jewel-commercial-announcer", "jian-direct-dispatcher", "jihyun-anchorwoman", "jillian-happy-spirit", "jing-clear-coordinator", "jiwoo-service-specialist", "jo-go-to-gal", "joan-messenger", "joanie-vibrant-speaker", "joey-neighborhood-guy", "johan-deep-consultant", "jolene-warm-storyteller", "jonas", "jordan-chill-pal", "jorge-regular-guy", "joris-command-coach", "joseph-empathetic-voice", "joy-crisp-narrator", "juan-clear-communicator", "juanita-helpful-companion", "judith-poised-strength", "julia-gentle-guide", "julian-vibrant-voice", "julien-polished-partner", "juliette", "kacper-diligent-detailer", "kai-commercial-man", "kanya-gentle-helper", "kari-crisp-coordinator", "karin-companion", "kasia-natural-conversationalist", "katarina-friendly-sales", "katarzyna-melodic-storyteller", "kate-practical-voice", "katie-friendly-fixer", "katrine-calm-caregiver", "katsuya-promo-host", "katya", "kavita-customer-care-agent", "kavitha-clear-communicator", "kavya-warm-presence", "kayla-easygoing-pal", "keith-easygoing-friend", "kelly-friendly-spirit", "kelsey-ball-of-energy", "kendra-smooth-communicator", "kenji-calm-man", "kenneth-friendly-rep", "khaled-keen-problem-solver", "khalid-bright-energy", "kiara-joyful-woman", "kiefer-assured-tone", "kim-cheerful-pal", "kira-trusted-confidant", "klara-empathetic-voice", "klaus-archivist", "krishna-friendly-pal", "krit-efficient-envoy", "kriti-clear-explainer", "kurt-phone-support", "kyle-approachable-friend", "lacey-sunny-soul", "lakshmi-everyday-voice", "lan-instructor", "larissa-bright-companion", "lars-casual-conversationalist", "latha-friendly-host", "laurel-caring-sister", "lauren-lively-narrator", "laurent-dependable-anchor", "lawson-suave-storyteller", "layla-casual-friend", "lea-breezy-voice", "lea-logical-liaison", "leander", "lena-muse", "leni-daymaker", "leo", "leo-genuine-companion", "levan-support-guide", "levi-steady-spokesman", "lexi-fun-friend", "leyla-story-companion", "liam-guy-next-door", "lien-gentle-coordinator", "liezel-steady-informer", "lila-meditation-guide", "liliana-doting-mother", "lily-casual-pal", "linda-conversational-guide", "lindsey-relaxed-rep", "linh-soft-presence", "liora-gentle-guide", "lira-tranquil-voice", "liu-plain-talker", "liv-casual-friend", "logan-approachable-friend", "lorelei-helpful-guide", "lorenzo-hospitable-host", "loretta-still-comfort", "lori-cheerleader", "lori-curious-cheerleader", "lori-disgusted-cheerleader", "lori-happy-cheerleader", "lori-sad-cheerleader", "lori-scared-cheerleader", "lori-surprised-cheerleader", "luana-public-speaker", "luca-everyday-friend", "lucas-storyteller", "lucia-radiant-host", "lucy-capable-coordinator", "luis-news-caster", "lukas-professional", "luke-angry-broadway-voice", "luke-broadway-voice", "luke-disgusted-broadway-voice", "luke-happy-broadway-voice", "luke-sad-broadway-voice", "luke-scared-broadway-voice", "luke-surprised-broadway-voice", "lulu-madame-mischief", "luz-casual-speaker", "maayan-refined-speaker", "madeleine-reliable-resident", "madison-best-friend", "madison-curious-best-friend", "madison-disgusted-best-friend", "madison-happy-best-friend", "madison-sad-best-friend", "madison-scared-best-friend", "madison-surprised-best-friend", "mae-calm-authority", "maeve-steady-host", "maia-agile-support", "manon-bright-belle", "manuel-newsman", "marc-conversational-buddy", "marcin-charismatic-presenter", "marco-friendly-conversationalist", "marcos-steady-advisor", "marcus-reliable-guy", "marek-steady-specialist", "marge-seasoned-grace", "marian-poised-narrator", "mariana-nurturing-guide", "marie-eve-team-mentor", "marilyn-explainer", "marjorie-encouraging-aunt", "mark-promotion-lead", "marlene-elegant-speaker", "marta-friendly-guide", "martin-meticulous-operator", "marvin-steady-ally", "mary-nurse", "maryam-friendly-voice", "mason-calm-vibe", "mateo-friendly-host", "mathieu-assured-expert", "matt-goofy-friend", "matteo-gentle-narrator", "matti-measured-manager", "maxime-methodical-moderator", "maxine-relaxed-energy", "maya-easygoing-ally", "meena-measured-professional", "meera-bright-companion", "mei-expressive-assistant", "melanie-lively-spirit", "melina-bright-spirit", "melisa-v3", "mette-polished-facilitator", "michelle-empathetic-voice", "mika-empathetic-friend", "mikko-narration-expert", "milena-composed-clarifier", "miles-yogi", "milla-modern-communicator", "mindy-spirited-ally", "minh-conversational-partner", "minho-friendly-spirit", "minji-modern-communicator", "mirella-upbeat-speaker", "molly-upbeat-conversationalist", "monica-emotive-voice", "morgan-executive-expert", "moritz-modern-communicator", "murat-anatolian-storyteller", "nadia-singaporean-female", "narin-warm-concierge", "natalia-steady-strategist", "natalie-caring-specialist", "natalya-soothing-guide", "natasha-upbeat-guide", "nathan-easy-talker", "nava-warm-specialist", "neeraj-tour-guide", "neha-virtual-assistant", "nico-friendly-agent", "nikos-radio-storyteller", "nils-friendly-host", "nisha-elegant-speaker", "nithya-polished-presence", "noa-reassuring-responder", "noah-calming-presence", "noam-broadcaster", "nolan-expressive-agent", "nora-calm-companion", "nour-engaging-speaker", "nuria-trusted-advisor", "oleh-professional-guy", "olga-confident-saleswoman", "oliver-customer-chap", "olivia-sunny-woman", "omar-high-energy-presenter", "oren-steady-advisor", "orin-velvet-gentleman", "oscar-clear-specialist", "oskar-steady-advisor", "palak-presenter", "paloma-clear-presenter-woman", "paola-expressive-performer", "parker-supportive-pal", "parvati-friendly-supporter", "patricia-veteran-support", "paul-straight-talker", "pauline-helpful-companion", "pavan-bright-voice", "pearl-calm-solutionist", "pedro-formal-speaker", "peter-narrator-man", "petr-pastor", "petra-strict-lecturer", "pierre", "pierre-baritone-storyteller", "pieter-polished-analyst", "piotr-corporate-lead", "pippa-bright-assistant", "pooja-everyday-assistant", "prakash-instructor", "preston-relatable-pal", "priya-trusted-operator", "quinn-calm-authority", "rachel-polished-presence", "rafael-dynamic-speaker", "rahul-calm-office-guy", "rakesh-thoughtful-speaker", "ralph-dynamic-commentator", "ramya-graceful-host", "rania-spirited-storyteller", "ray-conversationalist", "rebecca-counselor", "reed-polished-professional", "reese-warm-companion", "reflective-woman", "regis-news-anchor", "ren-calm-navigator", "rena", "renata-cheerful-conversationalist", "renee-commander", "riley-chill-friend", "rina-articulate-coordinator", "riya-college-roommate", "robyn-storycrafter", "rodrigo-calm-companion", "rohan-steady-communicator", "romeo-calm-narrator", "ronald-thinker", "ronan-warm-buddy", "ronen-calm-consultant", "rory-maternal-vibe", "rosa-optimist-mother", "ross-reliable-partner", "rowan-team-leader", "roxane-problem-solver", "roy-stern-realist", "rubel-city-guide", "ruby-helpful-handler", "rupert-caring-dad", "ruth-manager", "ryeowook-easygoing-pal", "s-ren-steady-strategist", "sabine-firm-newscaster", "sabrina-casual-ally", "sagar-helpful-friend", "saira-organized-coordinator", "samantha-angry-support-leader", "samantha-happy-support-leader", "samantha-sad-support-leader", "samantha-support-leader", "samantha-yelling-support-leader", "sameer-problem-solver", "sanjay-clear-speaker", "sanne-clear-companion", "santiago-modern-navigator", "sanya-modern-communicator", "sarah-mindful-woman", "sarika-calm-spirit", "sasha-cool-friend", "savannah-magnolia-belle", "scott-sportscaster", "sean-steady-companion", "sebastian-orator", "selene-soothing-aura", "seoyun-warm-guide", "serena-laidback-girl", "sergei-steady-supporter", "shailika-clear-explainer", "shane-helpful-guide", "shanti-calm-authority", "sheldon-help-desk-man", "shelly-warm-companion", "shira-comforting-presence", "shuwen-precision-guide", "sibylle", "sienna-encourager", "sierra-california-girl", "silas-nighttime-narrator", "simi-support-specialist", "sindhu-conversational-partner", "siobhan-warm-welcomer", "siti-ad-narrator", "skylar-friendly-guide", "skyler-laidback-partner", "sneha-empathetic-voice", "sofia-methodical-moderator", "somchai-star", "soojin-helpful-tone", "sophie-teacher", "soren-executive-voice", "soyeon-bright-companion", "spencer-chill-gentleman", "stephanie-steady-professional", "sterling-monarch", "steve-angry-baritone", "steve-baritone", "steve-curious-baritone", "steve-disgusted-baritone", "steve-happy-baritone", "steve-sad-baritone", "steve-scared-baritone", "steve-surprised-baritone", "steven-big-brother", "stjin-helpful-handler", "subin-elegant-speaker", "suda-fortune-teller", "sunil-official-announcer", "sunny-pep-talker", "suresh-instruction-voice", "suzanne-laidback-aunt", "tabitha-smooth-energy", "taehyun-friendly-host", "takashi-professional-conversationalist", "talia-approachable-guide", "tamar-crisp-announcer", "tamara-support-specialist", "tanner-laidback-spirit", "tanner-upbeat-assistant", "tao-lecturer", "tara-confident-ally", "tariq-wise-advisor", "tatiana-friendly-storyteller", "taylan-expressive-voice", "tehila-calm-specialist", "tereza-decisive-agent", "tessa-kind-companion", "thaksin-tactful-tracker", "thandi-direct-dispatcher", "theo-modern-narrator", "thijs-confident-coordinator", "thomas-anchor", "tiago-narration-expert", "tiffany-dynamic-presence", "tim-pal", "tina-customer-ally", "toby-genuine-guide", "todd-matter-of-fact-salesman", "tohru-career-coach", "travis-how-to-guide", "trevor-movieman", "troy-fix-it-man", "tyler-friendly-salesman", "valeria-cheerful-promoter", "valerie-support-authority", "valerie-vibrant-voice", "vanessa", "vicky-businesswoman", "victoria-refined-coordinator", "vidya-empathetic-voice", "vijay-comfort-voice", "vikas-approachable-voice", "vikram-folk-narrator", "viktoria-phone-conversationalist", "vincent", "vishal-assured-expert", "vivek-composed-voice", "vivian-fierce-narrator", "vreni-diligent-advisor", "wade-2-0-southern-soul", "wade-southern-soul", "walid-steady-presence", "wang-guide", "warren-seasoned-pragmatist", "wes-customer-companion", "wesley-chill-flow", "whitney-composed-concierge", "willow-approachable-ally", "wyatt-dependable-dispatcher", "xia-calm-companion", "ximena-calm-navigator", "yael-casual-presence", "yarden-trusted-advisor", "yardena-expert-facilitator", "yasmin-dialogue-anchor", "yonatan-measured-professional", "youssef-clear-communicator", "yuki-calm-woman", "yumiko-friendly-agent", "yuna-kind-unnie", "zack-sportsman", "zain-dynamic-presenter", "zander-energetic-announcer", "zanele-vibrant-advocate", "zeke-friendly-sidekick", "zoey-bright-voice", "zofia-audiobook-muse" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "speed": { "required": false, "type": "number", "minimum": 0.5, "maximum": 2.0, "default": 1.0, "description": "Speech rate multiplier (Telnyx ``voice_speed``). Range 0.5–2.0." }, "volume": { "required": false, "type": "number", "minimum": 0.0, "maximum": 2.0, "default": 1.0, "description": "Output volume for Ultra. Range 0.0–2.0." }, "emotion": { "required": false, "type": "string", "description": "Emotion for Ultra: neutral, happy, sad, angry, fearful, disgusted, surprised. Ultra also supports inline SSML ```` and ``[laughter]``." }, "language": { "required": false, "type": "string", "description": "Language hint / ``language_boost`` for Ultra (e.g. English, Spanish, Japanese)." }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "Audio format when the upstream accepts it (mp3, wav, pcm, …)." } } }, { "name": "xAI: TTS", "description": "xAI TTS voices (eve, ara, rex, sal, leo).", "id": "xai-tts", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 700, "pricing": { "type": "per_million_tokens", "input": 15 }, "endpoints": [ "/v1/audio/speech" ], "premium_model": false, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 700, "pricing": { "type": "per_million_tokens", "input": 15 } } ], "context_length": 700, "max_model_len": 700, "max_input_tokens": 700, "voices": [ "authoritative-strong", "confident-clear", "energetic-upbeat", "smooth-balanced", "warm-friendly" ], "parameters": { "input": { "required": true, "type": "string", "min_length": 1, "description": "Text to synthesize." }, "voice": { "required": false, "type": "string", "description": "Friendly voice slug for this model." }, "language": { "required": false, "type": "string", "default": "auto", "description": "Language code, or ``auto`` to detect." }, "response_format": { "required": false, "type": "string", "default": "mp3", "description": "mp3, wav, pcm, mulaw, or alaw." }, "sample_rate": { "required": false, "type": "integer", "default": 24000, "description": "Sample rate Hz: 8000, 16000, 22050, 24000, 44100, 48000." } } }, { "name": "Deepgram: Nova 3", "description": "Deepgram Nova-3 — multilingual speech-to-text with optional word-level timestamps, speaker diarization, smart formatting, and punctuation.", "id": "deepgram-nova-3", "object": "model", "created": 1788985190, "owned_by": "deepgram", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.0074 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "deepgram", "name": "Deepgram", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.0074 } } ], "parameters": { "language": { "required": false, "type": "string", "default": "auto", "description": "Language: Nova-3 playground accepts ``auto``. Official list includes ``en``, ``en-US``, ``en-GB``, ``en-AU``, ``en-NZ``, ``en-IN``, ``multi``. Nova-2 rejects ``auto`` — use ``en`` / ``multi`` or an ISO code." }, "prompt": { "required": false, "type": "string", "description": "Not used by Deepgram Nova-3 on Telnyx (ignored if sent)." }, "response_format": { "required": false, "type": "string", "default": "verbose_json", "description": "Prefer ``verbose_json`` for word timestamps / speaker labels." }, "smart_format": { "required": false, "type": "boolean", "description": "Deepgram model_config: capitalization, dates, numbers, currency." }, "punctuate": { "required": false, "type": "boolean", "description": "Deepgram model_config: add punctuation." }, "diarize": { "required": false, "type": "boolean", "description": "Deepgram model_config: speaker identification." }, "utterance": { "required": false, "type": "boolean", "description": "Deepgram model_config: segment transcript into utterances." }, "numerals": { "required": false, "type": "boolean", "description": "Deepgram model_config: convert spoken numbers to digits." } } }, { "name": "Deepgram: Nova 2", "description": "Deepgram Nova-2 — previous-generation multilingual speech-to-text. Prefer language=en or multi (not auto).", "id": "deepgram-nova-2", "object": "model", "created": 1788985190, "owned_by": "deepgram", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.0074 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "deepgram", "name": "Deepgram", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.0074 } } ], "parameters": { "language": { "required": false, "type": "string", "default": "en", "description": "Nova-2 rejects ``auto``. Use ``en``, ``multi``, or a listed ISO code (bg, ca, cs, da, de, el, en, es, …)." }, "prompt": { "required": false, "type": "string", "description": "Not used by Deepgram Nova-3 on Telnyx (ignored if sent)." }, "response_format": { "required": false, "type": "string", "default": "verbose_json", "description": "Prefer ``verbose_json`` for word timestamps / speaker labels." }, "smart_format": { "required": false, "type": "boolean", "description": "Deepgram model_config: capitalization, dates, numbers, currency." }, "punctuate": { "required": false, "type": "boolean", "description": "Deepgram model_config: add punctuation." }, "diarize": { "required": false, "type": "boolean", "description": "Deepgram model_config: speaker identification." }, "utterance": { "required": false, "type": "boolean", "description": "Deepgram model_config: segment transcript into utterances." }, "numerals": { "required": false, "type": "boolean", "description": "Deepgram model_config: convert spoken numbers to digits." } } }, { "name": "Deepgram: Flux", "description": "Deepgram Flux — turn-taking speech-to-text with built-in end-of-turn detection.", "id": "deepgram-flux", "object": "model", "created": 1788985190, "owned_by": "deepgram", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.0074 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "deepgram", "name": "Deepgram", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.0074 } } ], "parameters": { "language": { "required": false, "type": "string", "default": "auto", "description": "Language hint for Flux (``auto`` or ISO / BCP-47)." }, "prompt": { "required": false, "type": "string", "description": "Not used by Flux (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Playground SSE returns plain text wrapped as JSON ``text``." } } }, { "name": "OpenAI: Whisper Large V3 Turbo", "description": "OpenAI Whisper Large V3 Turbo — multilingual speech-to-text.", "id": "whisper-large-v3-turbo", "object": "model", "created": 1788985190, "owned_by": "openai", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "openai", "name": "OpenAI", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "description": "Optional language hint (multilingual; omit for auto-detect)." }, "prompt": { "required": false, "type": "string", "description": "Optional text prompt to guide transcription style (Whisper-family)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "Distil-Whisper: Large V2", "description": "Distil-Whisper Large V2 — compressed Whisper speech-to-text (language parameter not supported).", "id": "distil-whisper-large-v2", "object": "model", "created": 1788985190, "owned_by": "distil-whisper", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "distil-whisper", "name": "Distil Whisper", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "description": "Not supported — Distil-Whisper rejects language (official ``language_not_found``). Leave unset." }, "prompt": { "required": false, "type": "string", "description": "Optional text prompt to guide transcription style (Whisper-family)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "xAI: Grok STT", "description": "xAI Grok STT — speech-to-text.", "id": "grok-stt", "object": "model", "created": 1788985190, "owned_by": "x-ai", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "x-ai", "name": "xAI", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "default": "auto", "description": "Language hint for Grok STT (``auto`` or ISO / BCP-47)." }, "prompt": { "required": false, "type": "string", "description": "Not used by Grok STT (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "AssemblyAI: Universal Streaming", "description": "AssemblyAI Universal Streaming — real-time speech-to-text. Use language=en/es/de/fr/pt/it (auto unsupported).", "id": "assemblyai-universal-streaming", "object": "model", "created": 1788985190, "owned_by": "assemblyai", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.007 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "assemblyai", "name": "Assemblyai", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.007 } } ], "parameters": { "language": { "required": false, "type": "string", "default": "en", "description": "Required for AssemblyAI on the playground. Supported: en, es, de, fr, pt, it. ``auto`` is rejected." }, "prompt": { "required": false, "type": "string", "description": "Not used (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "Speechmatics: Standard", "description": "Speechmatics Standard — speech-to-text.", "id": "speechmatics-standard", "object": "model", "created": 1788985190, "owned_by": "speechmatics", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "speechmatics", "name": "Speechmatics", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "default": "auto", "description": "Prefer ``auto`` for Speechmatics on the playground SSE." }, "prompt": { "required": false, "type": "string", "description": "Not used (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "Soniox: STT RT v4", "description": "Soniox STT RT v4 — real-time speech-to-text.", "id": "soniox-stt-rt-v4", "object": "model", "created": 1788985190, "owned_by": "soniox", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "soniox", "name": "Soniox", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "description": "Soniox auto-detects language. Omit language (do not send ``auto``) for best sticky-session reliability on the playground." }, "prompt": { "required": false, "type": "string", "description": "Not used (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "Google: Speech-to-Text (latest_long)", "description": "Google Cloud Speech-to-Text (latest_long) — long-form multilingual transcription.", "id": "google-latest-long", "object": "model", "created": 1788985190, "owned_by": "google", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "google", "name": "Google", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "description": "Optional BCP-47 language hint (e.g. ``en-US``). Omit or ``auto`` for engine default. Official WebSocket only." }, "prompt": { "required": false, "type": "string", "description": "Not used (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } }, { "name": "Azure: Speech (fast)", "description": "Microsoft Azure Speech (fast) — speech-to-text.", "id": "azure-fast", "object": "model", "created": 1788985190, "owned_by": "azure", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.027 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "azure", "name": "Azure", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.027 } } ], "parameters": { "language": { "required": false, "type": "string", "description": "Optional BCP-47 language hint (e.g. ``en-US``). Omit or ``auto`` for engine default. Official WebSocket only." }, "prompt": { "required": false, "type": "string", "description": "Not used (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." }, "region": { "required": false, "type": "string", "description": "Optional Azure Speech region (e.g. ``eastus``). Send as form field ``region`` or inside ``model_config`` JSON. Telnyx uses its default region when omitted." } } }, { "name": "NVIDIA: Parakeet v3", "description": "NVIDIA Parakeet v3 — speech-to-text.", "id": "nvidia-parakeet-v3", "object": "model", "created": 1788985190, "owned_by": "nvidia", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 }, "endpoints": [ "/v1/audio/transcriptions" ], "premium_model": false, "providers": [ { "id": "nvidia", "name": "Nvidia", "tokens": 0, "pricing": { "type": "per_minute", "coefficient": 0.017 } } ], "parameters": { "language": { "required": false, "type": "string", "description": "Ignored — Parakeet auto-detects language." }, "prompt": { "required": false, "type": "string", "description": "Not used (ignored)." }, "response_format": { "required": false, "type": "string", "default": "json", "description": "Transcript format: ``json`` or ``verbose_json`` (segments / timestamps)." } } } ] }