{ "schema_version": "1.0.0", "last_updated": "2026-08-02", "models": [ { "provider": "AI21 Labs", "model_id": "jamba-1-7-large", "model_name": "Jamba 1.7 Large", "input_per_1m_usd": 2.0, "output_per_1m_usd": 8.0, "context_window_k": 256, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Amazon Bedrock", "model_id": "amazon.nova-micro-v1", "model_name": "Nova Micro", "input_per_1m_usd": 0.035, "output_per_1m_usd": 0.14, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.0175, "batch_output_per_1m_usd": 0.07, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Amazon Bedrock", "model_id": "amazon.nova-lite-v1", "model_name": "Nova Lite", "input_per_1m_usd": 0.06, "output_per_1m_usd": 0.24, "context_window_k": 300, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.03, "batch_output_per_1m_usd": 0.12, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Amazon Bedrock", "model_id": "amazon.nova-pro-v1", "model_name": "Nova Pro", "input_per_1m_usd": 0.8, "output_per_1m_usd": 3.2, "context_window_k": 300, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": 0.4, "batch_output_per_1m_usd": 1.6, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Amazon Bedrock", "model_id": "amazon.nova-premier-v1", "model_name": "Nova Premier", "input_per_1m_usd": 2.0, "output_per_1m_usd": 8.0, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": 1.0, "batch_output_per_1m_usd": 4.0, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Anthropic", "model_id": "claude-haiku-4-5-20251001", "model_name": "Claude Haiku 4.5", "input_per_1m_usd": 1.0, "output_per_1m_usd": 5.0, "context_window_k": 200, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.5, "batch_output_per_1m_usd": 2.5, "cache_read_per_1m_usd": 0.1, "cache_write_per_1m_usd": 1.25 }, { "provider": "Anthropic", "model_id": "claude-sonnet-5", "model_name": "Claude Sonnet 5", "input_per_1m_usd": 2.0, "output_per_1m_usd": 10.0, "context_window_k": 200, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "Introductory pricing through August 31, 2026; standard rates are $3.00/$15.00.", "batch_input_per_1m_usd": 1.0, "batch_output_per_1m_usd": 5.0, "cache_read_per_1m_usd": 0.2, "cache_write_per_1m_usd": 2.5 }, { "provider": "Anthropic", "model_id": "claude-opus-5", "model_name": "Claude Opus 5", "input_per_1m_usd": 5.0, "output_per_1m_usd": 25.0, "context_window_k": 200, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": 2.5, "batch_output_per_1m_usd": 12.5, "cache_read_per_1m_usd": 0.5, "cache_write_per_1m_usd": 6.25 }, { "provider": "Anthropic", "model_id": "claude-fable-5", "model_name": "Claude Fable 5", "input_per_1m_usd": 10.0, "output_per_1m_usd": 50.0, "context_window_k": 200, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": 5.0, "batch_output_per_1m_usd": 25.0, "cache_read_per_1m_usd": 1.0, "cache_write_per_1m_usd": 12.5 }, { "provider": "Azure OpenAI", "model_id": "azure-gpt-5-4-nano", "model_name": "GPT-5.4 Nano", "input_per_1m_usd": 0.2, "output_per_1m_usd": 1.25, "context_window_k": 1100, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Azure OpenAI", "model_id": "azure-gpt-5-4-mini", "model_name": "GPT-5.4 Mini", "input_per_1m_usd": 0.75, "output_per_1m_usd": 4.5, "context_window_k": 1100, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.375, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": 0.075, "cache_write_per_1m_usd": null }, { "provider": "Azure OpenAI", "model_id": "azure-o4-mini", "model_name": "o4-mini", "input_per_1m_usd": 1.1, "output_per_1m_usd": 4.4, "context_window_k": 200, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.55, "batch_output_per_1m_usd": 2.2, "cache_read_per_1m_usd": 0.275, "cache_write_per_1m_usd": null }, { "provider": "Azure OpenAI", "model_id": "azure-gpt-5-1", "model_name": "GPT-5.1", "input_per_1m_usd": 1.25, "output_per_1m_usd": 10.0, "context_window_k": 410, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Azure OpenAI", "model_id": "azure-o3", "model_name": "o3", "input_per_1m_usd": 2.0, "output_per_1m_usd": 8.0, "context_window_k": 200, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Azure OpenAI", "model_id": "azure-gpt-5-4", "model_name": "GPT-5.4", "input_per_1m_usd": 2.5, "output_per_1m_usd": 15.0, "context_window_k": 1100, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "Price applies up to 272K context. Above 272K: $5.00 input / $22.50 output per 1M.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": 0.25, "cache_write_per_1m_usd": null }, { "provider": "Cerebras", "model_id": "cerebras-gpt-oss-120b", "model_name": "GPT-OSS 120B", "input_per_1m_usd": 0.35, "output_per_1m_usd": 0.75, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Cerebras", "model_id": "cerebras-gemma-4-31b", "model_name": "Gemma 4 31B Instruct", "input_per_1m_usd": 0.99, "output_per_1m_usd": 1.49, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Cerebras", "model_id": "cerebras-glm-4-7", "model_name": "GLM 4.7", "input_per_1m_usd": 2.25, "output_per_1m_usd": 2.75, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "Preview model.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Cohere", "model_id": "command-r7b-08-2024", "model_name": "Command R7B", "input_per_1m_usd": 0.0375, "output_per_1m_usd": 0.15, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Cohere", "model_id": "embed-english-v3.0", "model_name": "Embed English v3", "input_per_1m_usd": 0.1, "output_per_1m_usd": null, "context_window_k": 1, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "is_embedding": true, "tier": "efficient", "notes": "Embedding model. No output tokens.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Cohere", "model_id": "command-r-08-2024", "model_name": "Command R", "input_per_1m_usd": 0.15, "output_per_1m_usd": 0.6, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Cohere", "model_id": "command-r-plus-08-2024", "model_name": "Command R+", "input_per_1m_usd": 2.5, "output_per_1m_usd": 10.0, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "DeepSeek", "model_id": "deepseek-v4", "model_name": "DeepSeek V4", "input_per_1m_usd": 0.07, "output_per_1m_usd": 0.28, "context_window_k": 64, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": 0.018, "cache_write_per_1m_usd": null }, { "provider": "DeepSeek", "model_id": "deepseek-r2", "model_name": "DeepSeek R2", "input_per_1m_usd": 0.55, "output_per_1m_usd": 2.19, "context_window_k": 128, "supports_vision": false, "supports_function_calling": false, "is_reasoning": true, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": 0.14, "cache_write_per_1m_usd": null }, { "provider": "Fireworks AI", "model_id": "accounts/fireworks/models/deepseek-v4-flash", "model_name": "DeepSeek V4 Flash", "input_per_1m_usd": 0.14, "output_per_1m_usd": 0.28, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "Hosts open-source DeepSeek model.", "batch_input_per_1m_usd": 0.07, "batch_output_per_1m_usd": 0.14, "cache_read_per_1m_usd": 0.07, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "text-embedding-005", "model_name": "Text Embedding 005", "input_per_1m_usd": 0.006, "output_per_1m_usd": null, "context_window_k": 2, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "is_embedding": true, "tier": "efficient", "notes": "Embedding model. No output tokens.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "input_per_1m_usd": 0.1, "output_per_1m_usd": 0.4, "context_window_k": 1024, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.05, "batch_output_per_1m_usd": 0.2, "cache_read_per_1m_usd": 0.01, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "input_per_1m_usd": 0.3, "output_per_1m_usd": 2.5, "context_window_k": 1024, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "performance", "notes": "", "batch_input_per_1m_usd": 0.15, "batch_output_per_1m_usd": 1.25, "cache_read_per_1m_usd": 0.03, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash-Lite", "input_per_1m_usd": 0.3, "output_per_1m_usd": 2.5, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.15, "batch_output_per_1m_usd": 1.25, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "input_per_1m_usd": 1.25, "output_per_1m_usd": 10.0, "context_window_k": 2048, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "Input $2.50/1M and output $15.00/1M above 200K tokens.", "batch_input_per_1m_usd": 0.625, "batch_output_per_1m_usd": 5.0, "cache_read_per_1m_usd": 0.125, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "input_per_1m_usd": 1.5, "output_per_1m_usd": 9.0, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "performance", "notes": "", "batch_input_per_1m_usd": 0.75, "batch_output_per_1m_usd": 4.5, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Google", "model_id": "gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "input_per_1m_usd": 1.5, "output_per_1m_usd": 7.5, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "performance", "notes": "", "batch_input_per_1m_usd": 0.75, "batch_output_per_1m_usd": 3.75, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Groq", "model_id": "llama-4-scout-groq", "model_name": "Llama 4 Scout", "input_per_1m_usd": 0.05, "output_per_1m_usd": 0.08, "context_window_k": 128, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Groq", "model_id": "llama-4-maverick-groq", "model_name": "Llama 4 Maverick", "input_per_1m_usd": 0.2, "output_per_1m_usd": 0.6, "context_window_k": 128, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Groq", "model_id": "deepseek-r2-distill-llama-70b-groq", "model_name": "DeepSeek R2 Distill Llama 70B", "input_per_1m_usd": 0.5, "output_per_1m_usd": 0.75, "context_window_k": 32, "supports_vision": false, "supports_function_calling": false, "is_reasoning": true, "tier": "specialized", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Mistral", "model_id": "devstral-small-2", "model_name": "Devstral Small 2", "input_per_1m_usd": 0.1, "output_per_1m_usd": 0.3, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "Optimized for software engineering tasks.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Mistral", "model_id": "mistral-small-4", "model_name": "Mistral Small 4", "input_per_1m_usd": 0.15, "output_per_1m_usd": 0.6, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Mistral", "model_id": "codestral", "model_name": "Codestral", "input_per_1m_usd": 0.3, "output_per_1m_usd": 0.9, "context_window_k": 256, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "specialized", "notes": "Optimized for code generation and completion.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Mistral", "model_id": "devstral-medium-2", "model_name": "Devstral Medium 2", "input_per_1m_usd": 0.4, "output_per_1m_usd": 2.0, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "Optimized for software engineering tasks.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Mistral", "model_id": "mistral-large-3", "model_name": "Mistral Large 3", "input_per_1m_usd": 0.5, "output_per_1m_usd": 1.5, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Mistral", "model_id": "mistral-medium-3-5", "model_name": "Mistral Medium 3.5", "input_per_1m_usd": 1.5, "output_per_1m_usd": 7.5, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "text-embedding-3-small", "model_name": "Text Embedding 3 Small", "input_per_1m_usd": 0.02, "output_per_1m_usd": null, "context_window_k": 8, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "is_embedding": true, "tier": "efficient", "notes": "Embedding model. No output tokens. Batch: $0.01/1M.", "batch_input_per_1m_usd": 0.01, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "gpt-5-nano", "model_name": "GPT-5 Nano", "input_per_1m_usd": 0.05, "output_per_1m_usd": 0.4, "context_window_k": 32, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.025, "batch_output_per_1m_usd": 0.2, "cache_read_per_1m_usd": 0.005, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "gpt-4.1-nano", "model_name": "GPT-4.1 Nano", "input_per_1m_usd": 0.1, "output_per_1m_usd": 0.4, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.05, "batch_output_per_1m_usd": 0.2, "cache_read_per_1m_usd": 0.025, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "text-embedding-3-large", "model_name": "Text Embedding 3 Large", "input_per_1m_usd": 0.13, "output_per_1m_usd": null, "context_window_k": 8, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "is_embedding": true, "tier": "performance", "notes": "Embedding model. No output tokens. Batch: $0.065/1M.", "batch_input_per_1m_usd": 0.065, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "gpt-4.1-mini", "model_name": "GPT-4.1 Mini", "input_per_1m_usd": 0.4, "output_per_1m_usd": 1.6, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.2, "batch_output_per_1m_usd": 0.8, "cache_read_per_1m_usd": 0.1, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "input_per_1m_usd": 1.0, "output_per_1m_usd": 6.0, "context_window_k": 272, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "Input $2.00/1M and output $9.00/1M above 272K tokens.", "batch_input_per_1m_usd": 0.5, "batch_output_per_1m_usd": 3.0, "cache_read_per_1m_usd": 0.5, "cache_write_per_1m_usd": 1.25 }, { "provider": "OpenAI", "model_id": "o4-mini", "model_name": "o4-mini", "input_per_1m_usd": 1.1, "output_per_1m_usd": 4.4, "context_window_k": 200, "supports_vision": false, "supports_function_calling": true, "is_reasoning": true, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": 0.55, "batch_output_per_1m_usd": 2.2, "cache_read_per_1m_usd": 0.55, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "o3", "model_name": "o3", "input_per_1m_usd": 2.0, "output_per_1m_usd": 8.0, "context_window_k": 200, "supports_vision": false, "supports_function_calling": true, "is_reasoning": true, "tier": "performance", "notes": "", "batch_input_per_1m_usd": 1.0, "batch_output_per_1m_usd": 4.0, "cache_read_per_1m_usd": 1.0, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "gpt-4.1", "model_name": "GPT-4.1", "input_per_1m_usd": 2.0, "output_per_1m_usd": 8.0, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": 1.0, "batch_output_per_1m_usd": 4.0, "cache_read_per_1m_usd": 0.5, "cache_write_per_1m_usd": null }, { "provider": "OpenAI", "model_id": "gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "input_per_1m_usd": 2.5, "output_per_1m_usd": 15.0, "context_window_k": 272, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "Input $5.00/1M and output $22.50/1M above 272K tokens.", "batch_input_per_1m_usd": 1.25, "batch_output_per_1m_usd": 7.5, "cache_read_per_1m_usd": 1.25, "cache_write_per_1m_usd": 3.13 }, { "provider": "OpenAI", "model_id": "gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "input_per_1m_usd": 5.0, "output_per_1m_usd": 30.0, "context_window_k": 272, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "Input $10.00/1M and output $45.00/1M above 272K tokens.", "batch_input_per_1m_usd": 2.5, "batch_output_per_1m_usd": 15.0, "cache_read_per_1m_usd": 0.5, "cache_write_per_1m_usd": 6.25 }, { "provider": "OpenAI", "model_id": "gpt-5.5", "model_name": "GPT-5.5", "input_per_1m_usd": 5.0, "output_per_1m_usd": 30.0, "context_window_k": 272, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": 2.5, "batch_output_per_1m_usd": 15.0, "cache_read_per_1m_usd": 0.5, "cache_write_per_1m_usd": null }, { "provider": "Perplexity", "model_id": "sonar", "model_name": "Sonar", "input_per_1m_usd": 1.0, "output_per_1m_usd": 1.0, "context_window_k": 128, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "tier": "efficient", "notes": "Online search model. Additional $5-12/1K request fee applies.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Perplexity", "model_id": "sonar-reasoning-pro", "model_name": "Sonar Reasoning Pro", "input_per_1m_usd": 2.0, "output_per_1m_usd": 8.0, "context_window_k": 128, "supports_vision": false, "supports_function_calling": false, "is_reasoning": true, "tier": "performance", "notes": "Online search model with reasoning. Additional $6-14/1K request fee applies.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Perplexity", "model_id": "sonar-pro", "model_name": "Sonar Pro", "input_per_1m_usd": 3.0, "output_per_1m_usd": 15.0, "context_window_k": 200, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "tier": "flagship", "notes": "Online search model. Additional $6-14/1K request fee applies.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Qwen", "model_id": "qwen3-turbo", "model_name": "Qwen3 Turbo", "input_per_1m_usd": 0.08, "output_per_1m_usd": 0.25, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Qwen", "model_id": "qwen3-plus", "model_name": "Qwen3 Plus", "input_per_1m_usd": 0.4, "output_per_1m_usd": 1.2, "context_window_k": 256, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Qwen", "model_id": "qwen3-max", "model_name": "Qwen3 Max", "input_per_1m_usd": 1.2, "output_per_1m_usd": 4.8, "context_window_k": 128, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "flagship", "notes": "", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Together AI", "model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout", "input_per_1m_usd": 0.18, "output_per_1m_usd": 0.59, "context_window_k": 128, "supports_vision": true, "supports_function_calling": true, "is_reasoning": false, "tier": "efficient", "notes": "Hosted open-source model (Meta).", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Together AI", "model_id": "deepseek-ai/DeepSeek-V3-1", "model_name": "DeepSeek V3.1", "input_per_1m_usd": 0.6, "output_per_1m_usd": 1.7, "context_window_k": 128, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "performance", "notes": "Hosted open-source model (DeepSeek).", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "Voyage AI", "model_id": "voyage-4-lite", "model_name": "Voyage 4 Lite", "input_per_1m_usd": 0.02, "output_per_1m_usd": null, "context_window_k": 32, "supports_vision": false, "supports_function_calling": false, "is_reasoning": false, "is_embedding": true, "tier": "efficient", "notes": "Embedding model. No output tokens.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "xAI", "model_id": "grok-build-0.1", "model_name": "Grok Build 0.1", "input_per_1m_usd": 1.0, "output_per_1m_usd": 2.0, "context_window_k": 256, "supports_vision": false, "supports_function_calling": true, "is_reasoning": false, "tier": "specialized", "notes": "Optimized for agentic coding tasks.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": null, "cache_write_per_1m_usd": null }, { "provider": "xAI", "model_id": "grok-4.3", "model_name": "Grok 4.3", "input_per_1m_usd": 1.25, "output_per_1m_usd": 2.5, "context_window_k": 1000, "supports_vision": true, "supports_function_calling": true, "is_reasoning": true, "tier": "performance", "notes": "Supports non-reasoning and reasoning modes.", "batch_input_per_1m_usd": null, "batch_output_per_1m_usd": null, "cache_read_per_1m_usd": 0.2, "cache_write_per_1m_usd": null } ] }