{ "schema_version": "1.0", "models": { "BAAI/bge-base-en-v1.5": { "mode": "embedding", "context_window": { "max_input": 512 }, "pricing": { "input_per_million_tokens": 0.008, "output_per_million_tokens": 0.0 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen2.5-72B-Instruct-Turbo": { "mode": "chat", "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen2.5-7B-Instruct-Turbo": { "mode": "chat", "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "mode": "chat", "context_window": { "max_input": 262000 }, "pricing": { "input_per_million_tokens": 0.2, "output_per_million_tokens": 6.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "mode": "chat", "context_window": { "max_input": 256000 }, "pricing": { "input_per_million_tokens": 0.65, "output_per_million_tokens": 3.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3-235B-A22B-fp8-tput": { "mode": "chat", "context_window": { "max_input": 40000 }, "pricing": { "input_per_million_tokens": 0.2, "output_per_million_tokens": 0.6 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "mode": "chat", "context_window": { "max_input": 256000 }, "pricing": { "input_per_million_tokens": 2.0, "output_per_million_tokens": 2.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "mode": "chat", "context_window": { "max_input": 262144 }, "pricing": { "input_per_million_tokens": 0.15, "output_per_million_tokens": 1.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3-Next-80B-A3B-Thinking": { "mode": "chat", "context_window": { "max_input": 262144 }, "pricing": { "input_per_million_tokens": 0.15, "output_per_million_tokens": 1.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "Qwen/Qwen3.5-397B-A17B": { "mode": "chat", "context_window": { "max_input": 262144 }, "pricing": { "input_per_million_tokens": 0.6, "output_per_million_tokens": 3.6 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "baai/bge-base-en-v1.5": { "mode": "embedding", "context_window": { "max_input": 512 }, "pricing": { "input_per_million_tokens": 0.008, "output_per_million_tokens": 0.0 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "deepseek-ai/DeepSeek-R1": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 20480, "max_tokens": 20480 }, "pricing": { "input_per_million_tokens": 3.0, "output_per_million_tokens": 7.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "deepseek-ai/DeepSeek-R1-0528-tput": { "mode": "chat", "context_window": { "max_input": 128000 }, "pricing": { "input_per_million_tokens": 0.55, "output_per_million_tokens": 2.19 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "deepseek-ai/DeepSeek-V3": { "mode": "chat", "context_window": { "max_input": 65536, "max_output": 8192, "max_tokens": 8192 }, "pricing": { "input_per_million_tokens": 1.25, "output_per_million_tokens": 1.25 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "deepseek-ai/DeepSeek-V3.1": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 16384, "max_tokens": 16384 }, "pricing": { "input_per_million_tokens": 0.6, "output_per_million_tokens": 1.7 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-27" }, "meta-llama/Llama-3.2-3B-Instruct-Turbo": { "mode": "chat", "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.88, "output_per_million_tokens": 0.88 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { "mode": "chat", "pricing": { "input_per_million_tokens": 0, "output_per_million_tokens": 0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.27, "output_per_million_tokens": 0.85 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Llama-4-Scout-17B-16E-Instruct": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.18, "output_per_million_tokens": 0.59 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { "mode": "chat", "pricing": { "input_per_million_tokens": 3.5, "output_per_million_tokens": 3.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.88, "output_per_million_tokens": 0.88 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.18, "output_per_million_tokens": 0.18 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "mistralai/Mistral-7B-Instruct-v0.1": { "mode": "chat", "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "mistralai/Mistral-Small-24B-Instruct-2501": { "mode": "chat", "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "mistralai/Mixtral-8x7B-Instruct-v0.1": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.6, "output_per_million_tokens": 0.6 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "moonshotai/Kimi-K2-Instruct": { "mode": "chat", "pricing": { "input_per_million_tokens": 1.0, "output_per_million_tokens": 3.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "moonshotai/Kimi-K2-Instruct-0905": { "mode": "chat", "context_window": { "max_input": 262144 }, "pricing": { "input_per_million_tokens": 1.0, "output_per_million_tokens": 3.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "moonshotai/Kimi-K2.5": { "mode": "chat", "context_window": { "max_input": 256000, "max_output": 256000, "max_tokens": 256000 }, "pricing": { "input_per_million_tokens": 0.5, "output_per_million_tokens": 2.8 }, "capabilities": { "function_calling": true, "vision": true, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "openai/gpt-oss-120b": { "mode": "chat", "context_window": { "max_input": 131072, "max_output": 131072, "max_tokens": 131072 }, "pricing": { "input_per_million_tokens": 0.15, "output_per_million_tokens": 0.6 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "openai/gpt-oss-20b": { "mode": "chat", "context_window": { "max_input": 128000 }, "pricing": { "input_per_million_tokens": 0.05, "output_per_million_tokens": 0.2 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "together-ai-21.1b-41b": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.8, "output_per_million_tokens": 0.8 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-4.1b-8b": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.2, "output_per_million_tokens": 0.2 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-41.1b-80b": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.9, "output_per_million_tokens": 0.9 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-8.1b-21b": { "mode": "chat", "context_window": { "max_tokens": 1000 }, "pricing": { "input_per_million_tokens": 0.3, "output_per_million_tokens": 0.3 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-81.1b-110b": { "mode": "chat", "pricing": { "input_per_million_tokens": 1.8, "output_per_million_tokens": 1.8 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-embedding-151m-to-350m": { "mode": "embedding", "pricing": { "input_per_million_tokens": 0.016, "output_per_million_tokens": 0.0 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-embedding-up-to-150m": { "mode": "embedding", "pricing": { "input_per_million_tokens": 0.008, "output_per_million_tokens": 0.0 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "together-ai-up-to-4b": { "mode": "chat", "pricing": { "input_per_million_tokens": 0.1, "output_per_million_tokens": 0.1 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "togethercomputer/CodeLlama-34b-Instruct": { "mode": "chat", "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "zai-org/GLM-4.5-Air-FP8": { "mode": "chat", "context_window": { "max_input": 128000 }, "pricing": { "input_per_million_tokens": 0.2, "output_per_million_tokens": 1.1 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": true }, "last_updated_at": "2026-04-24" }, "zai-org/GLM-4.6": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 200000, "max_tokens": 200000 }, "pricing": { "input_per_million_tokens": 0.6, "output_per_million_tokens": 2.2 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "zai-org/GLM-4.7": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 200000, "max_tokens": 200000 }, "pricing": { "input_per_million_tokens": 0.45, "output_per_million_tokens": 2.0 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" } } }