{ "generatedAt": "2026-11-11T18:18:17.018Z", "count": 128, "models": [ { "id": "amazon.nova-2-lite-v1-0", "providerId": "amazon", "displayName": "Nova 2 Lite", "status": "current", "contextWindow": 1000000, "pricing": { "input": 0.3, "output": 2.5, "cachedInput": 0.075 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Nova tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 64000, "capabilityIndex": 60 }, { "id": "amazon.nova-2-pro-preview-20251202-v1-0", "providerId": "amazon", "displayName": "Nova 2 Pro", "status": "current", "contextWindow": 1000000, "pricing": { "input": 1.25, "output": 10, "cachedInput": 0.3125 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Nova tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11", "lastChanged": "2026-10-03" }, "maxOutput": 64000, "capabilityIndex": 61 }, { "id": "amazon.nova-lite-v1-0", "providerId": "amazon", "displayName": "Nova Lite", "status": "current", "contextWindow": 300000, "pricing": { "input": 0.06, "output": 0.24, "cachedInput": 0.015 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Nova tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 10000 }, { "id": "amazon.nova-micro-v1-0", "providerId": "amazon", "displayName": "Nova Micro", "status": "current", "contextWindow": 128000, "pricing": { "input": 0.035, "output": 0.14, "cachedInput": 0.00875 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Nova tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 10000 }, { "id": "amazon.nova-pro-v1-0", "providerId": "amazon", "displayName": "Nova Pro", "status": "current", "contextWindow": 300000, "pricing": { "input": 0.8, "output": 3.2, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Nova tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 10000 }, { "id": "azure-ai-mai-thinking-1", "providerId": "microsoft", "displayName": "MAI-Thinking-1", "status": "current", "contextWindow": 256000, "pricing": { "input": 2, "output": 8, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — MAI tokenizer; Microsoft publishes no ratio" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/" }, "maxOutput": 64000 }, { "id": "claude-fable-5", "providerId": "anthropic", "displayName": "Claude Fable 5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 10, "output": 50, "cachedInput": 1, "cacheWrite": 12.5, "cacheWrite1h": 20, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 89 }, { "id": "claude-fable-5-1", "providerId": "anthropic", "displayName": "Claude Fable 5.1", "status": "current", "contextWindow": 1000000, "pricing": { "input": 10, "output": 50, "cachedInput": 0.25, "cacheWrite": 12.5, "cacheWrite1h": 20, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 90 }, { "id": "claude-fable-5-2", "providerId": "anthropic", "displayName": "Claude Fable 5 2", "status": "current", "contextWindow": 1000000, "pricing": { "input": 8, "output": 40, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 128000 }, { "id": "claude-haiku-4-5", "providerId": "anthropic", "displayName": "Claude Haiku 4.5", "status": "current", "contextWindow": 200000, "pricing": { "input": 1, "output": 5, "cachedInput": 0.1, "cacheWrite": 1.25, "cacheWrite1h": 2, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 64000, "capabilityIndex": 66 }, { "id": "claude-haiku-5-5", "providerId": "anthropic", "displayName": "Claude Haiku 5.5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 0.1, "output": 0.5, "cachedInput": 0.01 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 128000, "capabilityIndex": 86 }, { "id": "claude-opus-4-1", "providerId": "anthropic", "displayName": "Claude Opus 4.1", "status": "deprecated", "contextWindow": 200000, "pricing": { "input": 15, "output": 75, "cachedInput": 1.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-09-22", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 32000, "capabilityIndex": 80 }, { "id": "claude-opus-4-5", "providerId": "anthropic", "displayName": "Claude Opus 4.5", "status": "legacy", "contextWindow": 200000, "pricing": { "input": 5, "output": 25, "cachedInput": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 64000, "capabilityIndex": 79 }, { "id": "claude-opus-4-6", "providerId": "anthropic", "displayName": "Claude Opus 4.6", "status": "current", "contextWindow": 1000000, "pricing": { "input": 5, "output": 25, "cachedInput": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 82 }, { "id": "claude-opus-4-7", "providerId": "anthropic", "displayName": "Claude Opus 4.7", "status": "current", "contextWindow": 1000000, "pricing": { "input": 5, "output": 25, "cachedInput": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 85 }, { "id": "claude-opus-4-8", "providerId": "anthropic", "displayName": "Claude Opus 4.8", "status": "current", "contextWindow": 1000000, "pricing": { "input": 5, "output": 25, "cachedInput": 0.5, "cacheWrite": 6.25, "cacheWrite1h": 10, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 86 }, { "id": "claude-opus-5", "providerId": "anthropic", "displayName": "Claude Opus 5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 5, "output": 25, "cachedInput": 0.5, "cacheWrite": 6.25, "cacheWrite1h": 10, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 89 }, { "id": "claude-opus-5-5", "providerId": "anthropic", "displayName": "Claude Opus 5.5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 4, "output": 20, "cachedInput": 0.2, "cacheWrite": 5, "cacheWrite1h": 8, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 97 }, { "id": "claude-sonnet-4-5", "providerId": "anthropic", "displayName": "Claude Sonnet 4.5", "status": "legacy", "contextWindow": 200000, "pricing": { "input": 3, "output": 15, "cachedInput": 0.3 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 64000, "capabilityIndex": 69 }, { "id": "claude-sonnet-4-6", "providerId": "anthropic", "displayName": "Claude Sonnet 4.6", "status": "current", "contextWindow": 1000000, "pricing": { "input": 3, "output": 15, "cachedInput": 0.3 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 76 }, { "id": "claude-sonnet-5", "providerId": "anthropic", "displayName": "Claude Sonnet 5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 2, "output": 10, "cachedInput": 0.2, "cacheWrite": 2.5, "cacheWrite1h": 4, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-09-01", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 81 }, { "id": "claude-sonnet-5-5", "providerId": "anthropic", "displayName": "Claude Sonnet 5.5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 2, "output": 10, "cachedInput": 0.1, "cacheWrite": 2.5, "cacheWrite1h": 4, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.6, "cjkCharsPerToken": 1.5, "note": "Estimate — Anthropic's tokenizer is server-side; ratio calibrated on English prose" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-10-21", "verifiedUrl": "https://platform.claude.com/docs/en/about-claude/pricing" }, "maxOutput": 128000, "capabilityIndex": 91 }, { "id": "command-a-03-2025", "providerId": "cohere", "displayName": "Command A", "status": "current", "contextWindow": 256000, "pricing": { "input": 2.5, "output": 10 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.8, "note": "Estimate — Cohere tokenizer" }, "capabilities": { "reasoning": false, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 8000, "capabilityIndex": 55 }, { "id": "command-r-08-2024", "providerId": "cohere", "displayName": "Command R", "status": "current", "contextWindow": 128000, "pricing": { "input": 0.15, "output": 0.6 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.8, "note": "Estimate — Cohere tokenizer" }, "capabilities": { "reasoning": false, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 4096 }, { "id": "command-r-plus-08-2024", "providerId": "cohere", "displayName": "Command R+", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 2.5, "output": 10 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.8, "note": "Estimate — Cohere tokenizer" }, "capabilities": { "reasoning": false, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://cohere.com/pricing" }, "maxOutput": 4096 }, { "id": "dashscope-qwen3-next-80b-a3b-instruct", "providerId": "alibaba", "displayName": "Qwen3 Next 80B", "status": "deprecated", "contextWindow": 262144, "pricing": { "input": 0.15, "output": 1.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-09-17", "verifiedUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "maxOutput": 65536, "capabilityIndex": 70 }, { "id": "dashscope-qwen3-next-80b-a3b-thinking", "providerId": "alibaba", "displayName": "Qwen3 Next 80B Thinking", "status": "deprecated", "contextWindow": 262144, "pricing": { "input": 0.15, "output": 1.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-10-24" }, "maxOutput": 65536 }, { "id": "dashscope-qwen3-vl-235b-a22b-instruct", "providerId": "alibaba", "displayName": "Qwen3 VL 235B", "status": "deprecated", "contextWindow": 131072, "pricing": { "input": 0.4, "output": 1.6 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-09-17", "verifiedUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "maxOutput": 32768 }, { "id": "dashscope-qwen3.7-max", "providerId": "alibaba", "displayName": "Qwen 3.7 Max", "status": "current", "contextWindow": 991808, "pricing": { "input": 2.5, "output": 7.5, "cachedInput": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "maxOutput": 65536, "capabilityIndex": 74 }, { "id": "dashscope-qwen3.8-flash", "providerId": "alibaba", "displayName": "Qwen 3.8 Flash", "status": "current", "contextWindow": 991808, "pricing": { "input": 0.15, "output": 0.47, "cachedInput": 0.016 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://www.alibabacloud.com/help/en/model-studio/qwen3-8-flash" }, "maxOutput": 131072 }, { "id": "dashscope-qwen3.8-max", "providerId": "alibaba", "displayName": "Qwen 3.8 Max", "status": "current", "contextWindow": 991808, "pricing": { "input": 2, "output": 6, "cachedInput": 0.25 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://www.alibabacloud.com/help/en/model-studio/qwen3-8-max" }, "maxOutput": 131072, "capabilityIndex": 87 }, { "id": "dashscope-qwen3.8-omni-flash", "providerId": "alibaba", "displayName": "Qwen 3.8 Omni Flash", "status": "current", "contextWindow": 991808, "pricing": { "input": 0.15, "output": 0.47, "cachedInput": 0.016 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — Qwen tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing" }, "maxOutput": 131072 }, { "id": "deepseek-deepseek-r1", "providerId": "deepseek", "displayName": "DeepSeek R1", "status": "deprecated", "contextWindow": 65536, "pricing": { "input": 0.55, "output": 2.19, "cachedInput": 0.14 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.7, "note": "Estimate — DeepSeek's tokenizer handles Chinese far more densely than English" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-09-29" }, "maxOutput": 8192, "capabilityIndex": 70 }, { "id": "deepseek-deepseek-v3", "providerId": "deepseek", "displayName": "DeepSeek V3", "status": "deprecated", "contextWindow": 65536, "pricing": { "input": 0.27, "output": 1.1, "cachedInput": 0.07 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.7, "note": "Estimate — DeepSeek's tokenizer handles Chinese far more densely than English" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-09-29" }, "maxOutput": 8192 }, { "id": "deepseek-deepseek-v3.2", "providerId": "deepseek", "displayName": "DeepSeek V3.2", "status": "deprecated", "contextWindow": 163840, "pricing": { "input": 0.28, "output": 0.4, "cachedInput": 0.028 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.7, "note": "Estimate — DeepSeek's tokenizer handles Chinese far more densely than English" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-09-29" }, "maxOutput": 163840, "capabilityIndex": 74 }, { "id": "deepseek-deepseek-v4-flash", "providerId": "deepseek", "displayName": "DeepSeek V4 Flash", "status": "current", "contextWindow": 1000000, "pricing": { "input": 0.3, "output": 1.2, "cachedInput": 0.006 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.7, "note": "Estimate — DeepSeek's tokenizer handles Chinese far more densely than English" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-09-16", "verifiedUrl": "https://api-docs.deepseek.com/quick_start/pricing" }, "maxOutput": 384000, "capabilityIndex": 87 }, { "id": "deepseek-deepseek-v4-pro", "providerId": "deepseek", "displayName": "DeepSeek V4 Pro", "status": "current", "contextWindow": 1000000, "pricing": { "input": 1.32, "output": 3.96, "cachedInput": 0.044 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.7, "note": "Estimate — DeepSeek's tokenizer handles Chinese far more densely than English" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-08-16", "verifiedUrl": "https://api-docs.deepseek.com/quick_start/pricing" }, "maxOutput": 384000, "capabilityIndex": 79 }, { "id": "gemini-gemini-2.5-flash", "providerId": "google", "displayName": "Gemini 2.5 Flash", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.3, "output": 2.5, "cachedInput": 0.03, "cacheStoragePerMillionTokenHour": 1 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536 }, { "id": "gemini-gemini-2.5-flash-lite", "providerId": "google", "displayName": "Gemini 2.5 Flash-Lite", "status": "legacy", "contextWindow": 1048576, "pricing": { "input": 0.1, "output": 0.4, "cachedInput": 0.01, "cacheStoragePerMillionTokenHour": 1 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536 }, { "id": "gemini-gemini-2.5-pro", "providerId": "google", "displayName": "Gemini 2.5 Pro", "status": "legacy", "contextWindow": 1048576, "pricing": { "input": 1.25, "output": 10, "cachedInput": 0.125, "cacheStoragePerMillionTokenHour": 4.5, "longContext": { "thresholdTokens": 200000, "input": 2.5, "output": 15, "cachedInput": 0.25 } }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536, "capabilityIndex": 63 }, { "id": "gemini-gemini-3-flash-preview", "providerId": "google", "displayName": "Gemini 3 Flash Preview", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.5, "output": 3, "cachedInput": 0.05, "cacheStoragePerMillionTokenHour": 1 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536 }, { "id": "gemini-gemini-3-pro-preview", "providerId": "google", "displayName": "Gemini 3 Pro Preview", "status": "deprecated", "contextWindow": 1048576, "pricing": { "input": 2, "output": 12, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-09-22" }, "maxOutput": 65535 }, { "id": "gemini-gemini-3.1-flash-lite", "providerId": "google", "displayName": "Gemini 3.1 Flash Lite", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.25, "output": 1.5, "cachedInput": 0.025, "cacheStoragePerMillionTokenHour": 1 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536 }, { "id": "gemini-gemini-3.1-flash-lite-preview", "providerId": "google", "displayName": "Gemini 3.1 Flash Lite Preview", "status": "deprecated", "contextWindow": 1048576, "pricing": { "input": 0.25, "output": 1.5, "cachedInput": 0.025 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-10-29" }, "maxOutput": 65536 }, { "id": "gemini-gemini-3.1-pro-preview", "providerId": "google", "displayName": "Gemini 3.1 Pro", "status": "current", "contextWindow": 1048576, "pricing": { "input": 2, "output": 12, "cachedInput": 0.2, "longContext": { "thresholdTokens": 200000, "input": 4, "output": 18, "cachedInput": 0.4 } }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536, "capabilityIndex": 74 }, { "id": "gemini-gemini-3.5-flash", "providerId": "google", "displayName": "Gemini 3.5 Flash", "status": "deprecated", "contextWindow": 1048576, "pricing": { "input": 1.5, "output": 9, "cachedInput": 0.15 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-09", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536 }, { "id": "gemini-gemini-3.5-flash-lite", "providerId": "google", "displayName": "Gemini 3.5 Flash-Lite", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.3, "output": 2.5, "cachedInput": 0.03, "cacheStoragePerMillionTokenHour": 1 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536, "capabilityIndex": 66 }, { "id": "gemini-gemini-3.6-flash", "providerId": "google", "displayName": "Gemini 3.6 Flash", "status": "current", "contextWindow": 1048576, "pricing": { "input": 1.5, "output": 7.5, "cachedInput": 0.15, "cacheStoragePerMillionTokenHour": 1, "intro": { "input": 0.75, "output": 3.75, "cachedInput": 0.075, "until": "2026-12-31" } }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536, "capabilityIndex": 77 }, { "id": "gemini-gemini-3.7-flash", "providerId": "google", "displayName": "Gemini 3.7 Flash", "status": "deprecated", "contextWindow": 1048576, "pricing": { "input": 1.5, "output": 7.5, "cachedInput": 0.15, "cacheStoragePerMillionTokenHour": 1, "intro": { "input": 0.75, "output": 3.75, "cachedInput": 0.075, "until": "2026-12-31" } }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-09", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 65536, "capabilityIndex": 81 }, { "id": "gemini-gemini-3.8-flash", "providerId": "google", "displayName": "Gemini 3.8 Flash", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.75, "output": 3.75, "cachedInput": 0.075 }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 65536, "capabilityIndex": 85 }, { "id": "gemini-gemini-4-argon", "providerId": "google", "displayName": "Gemini 4 Argon", "status": "current", "contextWindow": 1048576, "pricing": { "input": 4, "output": 20, "cachedInput": 0.2, "intro": { "input": 2, "output": 10, "cachedInput": 0.1, "until": "2026-11-30" } }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 1048576, "capabilityIndex": 90 }, { "id": "gemini-gemini-4-carbon", "providerId": "google", "displayName": "Gemini 4 Carbon", "status": "current", "contextWindow": 1048576, "pricing": { "input": 4, "output": 20, "cachedInput": 0.2, "intro": { "input": 2, "output": 10, "cachedInput": 0.1, "until": "2026-11-30" } }, "tokenizer": { "kind": "approx", "charsPerToken": 4, "cjkCharsPerToken": 1.6, "note": "Estimate — Gemini's tokenizer is server-side" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://ai.google.dev/gemini-api/docs/pricing" }, "maxOutput": 1048576 }, { "id": "gpt-4.1", "providerId": "openai", "displayName": "GPT-4.1", "status": "legacy", "contextWindow": 1047576, "pricing": { "input": 2, "output": 8, "cachedInput": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 32768 }, { "id": "gpt-4.1-mini", "providerId": "openai", "displayName": "GPT-4.1 Mini", "status": "legacy", "contextWindow": 1047576, "pricing": { "input": 0.4, "output": 1.6, "cachedInput": 0.1 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 32768 }, { "id": "gpt-4o", "providerId": "openai", "displayName": "GPT-4o", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 2.5, "output": 10, "cachedInput": 1.25 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 16384 }, { "id": "gpt-4o-mini", "providerId": "openai", "displayName": "GPT-4o Mini", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 0.15, "output": 0.6, "cachedInput": 0.075 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 16384 }, { "id": "gpt-5", "providerId": "openai", "displayName": "GPT-5", "status": "current", "contextWindow": 272000, "pricing": { "input": 1.25, "output": 10, "cachedInput": 0.125 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000 }, { "id": "gpt-5-mini", "providerId": "openai", "displayName": "GPT-5 Mini", "status": "current", "contextWindow": 272000, "pricing": { "input": 0.25, "output": 2, "cachedInput": 0.025 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000 }, { "id": "gpt-5-nano", "providerId": "openai", "displayName": "GPT-5 Nano", "status": "current", "contextWindow": 272000, "pricing": { "input": 0.05, "output": 0.4, "cachedInput": 0.005 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000 }, { "id": "gpt-5-pro", "providerId": "openai", "displayName": "GPT-5 Pro", "status": "legacy", "contextWindow": 400000, "pricing": { "input": 15, "output": 120, "batchDiscount": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 272000 }, { "id": "gpt-5.1", "providerId": "openai", "displayName": "GPT-5.1", "status": "current", "contextWindow": 272000, "pricing": { "input": 1.25, "output": 10, "cachedInput": 0.125 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 70 }, { "id": "gpt-5.2", "providerId": "openai", "displayName": "GPT-5.2", "status": "current", "contextWindow": 272000, "pricing": { "input": 1.75, "output": 14, "cachedInput": 0.175 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 74 }, { "id": "gpt-5.2-pro", "providerId": "openai", "displayName": "GPT-5.2 Pro", "status": "current", "contextWindow": 272000, "pricing": { "input": 21, "output": 168, "batchDiscount": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000 }, { "id": "gpt-5.4", "providerId": "openai", "displayName": "GPT-5.4", "status": "current", "contextWindow": 1050000, "pricing": { "input": 2.5, "output": 15, "cachedInput": 0.25, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 5, "output": 22.5, "cachedInput": 0.5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 81 }, { "id": "gpt-5.4-mini", "providerId": "openai", "displayName": "GPT-5.4 Mini", "status": "current", "contextWindow": 272000, "pricing": { "input": 0.75, "output": 4.5, "cachedInput": 0.075, "batchDiscount": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 69 }, { "id": "gpt-5.4-nano", "providerId": "openai", "displayName": "GPT-5.4 Nano", "status": "current", "contextWindow": 272000, "pricing": { "input": 0.2, "output": 1.25, "cachedInput": 0.02, "batchDiscount": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 67 }, { "id": "gpt-5.4-pro", "providerId": "openai", "displayName": "GPT-5.4 Pro", "status": "current", "contextWindow": 1050000, "pricing": { "input": 30, "output": 180, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 60, "output": 270 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000 }, { "id": "gpt-5.5", "providerId": "openai", "displayName": "GPT-5.5", "status": "current", "contextWindow": 1050000, "pricing": { "input": 5, "output": 30, "cachedInput": 0.5, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 10, "output": 45, "cachedInput": 1 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 81 }, { "id": "gpt-5.5-pro", "providerId": "openai", "displayName": "GPT-5.5 Pro", "status": "current", "contextWindow": 1050000, "pricing": { "input": 30, "output": 180, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 60, "output": 270 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000 }, { "id": "gpt-5.6-luna", "providerId": "openai", "displayName": "GPT-5.6 Luna", "status": "current", "contextWindow": 922000, "pricing": { "input": 0.2, "output": 1.2, "cachedInput": 0.02, "cacheWrite": 0.25, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 0.4, "output": 1.8, "cachedInput": 0.04, "cacheWrite": 0.5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 80 }, { "id": "gpt-5.6-sol", "providerId": "openai", "displayName": "GPT-5.6 Sol", "status": "current", "contextWindow": 922000, "pricing": { "input": 5, "output": 30, "cachedInput": 0.5, "cacheWrite": 6.25, "batchDiscount": 0.5, "intro": { "input": 4, "output": 20, "cachedInput": 0.4, "cacheWrite": 5, "until": "2026-11-21" }, "longContext": { "thresholdTokens": 272000, "input": 10, "output": 45, "cachedInput": 1, "cacheWrite": 12.5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 88 }, { "id": "gpt-5.6-terra", "providerId": "openai", "displayName": "GPT-5.6 Terra", "status": "current", "contextWindow": 922000, "pricing": { "input": 2, "output": 12, "cachedInput": 0.2, "cacheWrite": 2.5, "cacheStoragePerMillionTokenHour": 4.5, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 4, "output": 18, "cachedInput": 0.4, "cacheWrite": 5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 86 }, { "id": "gpt-6-astra", "providerId": "openai", "displayName": "GPT-6 Astra", "status": "current", "contextWindow": 922000, "pricing": { "input": 10, "output": 50, "cachedInput": 1, "cacheWrite": 12.5, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 20, "output": 75, "cachedInput": 2, "cacheWrite": 25 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 90 }, { "id": "gpt-6-luna", "providerId": "openai", "displayName": "GPT-6 Luna", "status": "current", "contextWindow": 922000, "pricing": { "input": 0.1, "output": 0.5, "cachedInput": 0.01, "cacheWrite": 0.125, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 0.2, "output": 0.75, "cachedInput": 0.02, "cacheWrite": 0.25 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 81 }, { "id": "gpt-6-sol", "providerId": "openai", "displayName": "GPT-6 Sol", "status": "current", "contextWindow": 922000, "pricing": { "input": 2, "output": 10, "cachedInput": 0.2, "cacheWrite": 2.5, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 4, "output": 15, "cachedInput": 0.4, "cacheWrite": 5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 89 }, { "id": "gpt-6.1-sol", "providerId": "openai", "displayName": "GPT-6.1 Sol", "status": "current", "contextWindow": 922000, "pricing": { "input": 2, "output": 10, "cachedInput": 0.1, "cacheWrite": 2.5, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 4, "output": 15, "cachedInput": 0.2, "cacheWrite": 5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 90 }, { "id": "gpt-6.1-terra", "providerId": "openai", "displayName": "GPT-6.1 Terra", "status": "current", "contextWindow": 922000, "pricing": { "input": 1, "output": 5, "cachedInput": 0.05, "cacheWrite": 1.25, "batchDiscount": 0.5, "longContext": { "thresholdTokens": 272000, "input": 2, "output": 7.5, "cachedInput": 0.1, "cacheWrite": 2.5 } }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 128000, "capabilityIndex": 88 }, { "id": "inception-mercury-2", "providerId": "inception", "displayName": "Mercury 2", "status": "current", "contextWindow": 128000, "pricing": { "input": 0.25, "output": 0.75, "cachedInput": 0.025 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Mercury tokenizer; Inception publishes no ratio" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.inceptionlabs.ai/get-started/models" }, "maxOutput": 50000 }, { "id": "inception-mercury-2.5", "providerId": "inception", "displayName": "Mercury 2.5", "status": "current", "contextWindow": 260000, "pricing": { "input": 0.2, "output": 0.75, "cachedInput": 0.02 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Mercury tokenizer; Inception publishes no ratio" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.inceptionlabs.ai/get-started/models" }, "maxOutput": 65536 }, { "id": "meta-muse-spark-1.3", "providerId": "meta", "displayName": "Muse Spark 1.3", "status": "current", "contextWindow": 1048576, "pricing": { "input": 1.25, "output": 4.25, "cachedInput": 0.15 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Muse tokenizer; Meta publishes no ratio" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://dev.meta.ai/docs/pricing-rate-limits" }, "maxOutput": 131072 }, { "id": "meta-muse-wonder-1.0", "providerId": "meta", "displayName": "Muse Wonder 1.0", "status": "current", "contextWindow": 1048576, "pricing": { "input": 4, "output": 20, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.8, "cjkCharsPerToken": 1.7, "note": "Estimate — Muse tokenizer; Meta publishes no ratio" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://dev.meta.ai/docs/pricing-rate-limits" }, "maxOutput": 131072, "capabilityIndex": 90 }, { "id": "minimax-minimax-m2", "providerId": "minimax", "displayName": "MiniMax M2", "status": "current", "contextWindow": 200000, "pricing": { "input": 0.3, "output": 1.2, "cachedInput": 0.03 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — MiniMax tokenizer" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 8192 }, { "id": "minimax-minimax-m2.1", "providerId": "minimax", "displayName": "MiniMax M2.1", "status": "current", "contextWindow": 1000000, "pricing": { "input": 0.3, "output": 1.2, "cachedInput": 0.03 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — MiniMax tokenizer" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 8192 }, { "id": "minimax-minimax-m2.5", "providerId": "minimax", "displayName": "MiniMax M2.5", "status": "current", "contextWindow": 1000000, "pricing": { "input": 0.3, "output": 1.2, "cachedInput": 0.03, "cacheWrite": 0.375 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — MiniMax tokenizer" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-10-19", "verifiedUrl": "https://platform.minimax.io/docs/guides/pricing-paygo" }, "maxOutput": 8192 }, { "id": "minimax-minimax-m3", "providerId": "minimax", "displayName": "MiniMax M3", "status": "current", "contextWindow": 1000000, "pricing": { "input": 0.3, "output": 1.2, "cachedInput": 0.06 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — MiniMax tokenizer" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 128000, "capabilityIndex": 72 }, { "id": "mistral-codestral-2508", "providerId": "mistral", "displayName": "Codestral 25.08", "status": "current", "contextWindow": 128000, "pricing": { "input": 0.3, "output": 0.9, "cachedInput": 0.03 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.8, "note": "Estimate — Mistral tokenizer" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.mistral.ai/inference/pricing" }, "maxOutput": 128000 }, { "id": "mistral-mistral-large-3", "providerId": "mistral", "displayName": "Mistral Large 3", "status": "current", "contextWindow": 262144, "pricing": { "input": 0.5, "output": 1.5, "cachedInput": 0.05 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.8, "note": "Estimate — Mistral tokenizer" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 262144, "capabilityIndex": 57 }, { "id": "mistral-mistral-large-4", "providerId": "mistral", "displayName": "Mistral Large 4", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.7, "output": 2.1, "cachedInput": 0.07 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.8, "note": "Estimate — Mistral tokenizer" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-11-11", "verifiedUrl": "https://docs.mistral.ai/models/mistral-large-4" }, "maxOutput": 1048576, "capabilityIndex": 81 }, { "id": "mistral-mistral-large-4-0", "providerId": "mistral", "displayName": "Mistral Large 4.0", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.7, "output": 2.1, "cachedInput": 0.07 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.8, "note": "Estimate — Mistral tokenizer" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-11-11", "verifiedUrl": "https://docs.mistral.ai/models/mistral-large-4" }, "maxOutput": 1048576 }, { "id": "mistral-mistral-medium-3", "providerId": "mistral", "displayName": "Mistral Medium 3", "status": "deprecated", "contextWindow": 262144, "pricing": { "input": 1.5, "output": 7.5, "cachedInput": 0.15 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.8, "note": "Estimate — Mistral tokenizer" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-09-29" }, "maxOutput": 262144 }, { "id": "mistral-mistral-medium-3-5", "providerId": "mistral", "displayName": "Mistral Medium 3.5", "status": "current", "contextWindow": 262144, "pricing": { "input": 1.5, "output": 7.5, "cachedInput": 0.15 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.8, "note": "Estimate — Mistral tokenizer" }, "capabilities": { "reasoning": false, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 262144, "capabilityIndex": 61 }, { "id": "moonshot-kimi-k2-thinking", "providerId": "moonshot", "displayName": "Kimi K2 Thinking", "status": "deprecated", "contextWindow": 262144, "pricing": { "input": 0.6, "output": 2.5, "cachedInput": 0.15 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.6, "note": "Estimate — Moonshot tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-09-22" }, "maxOutput": 262144 }, { "id": "moonshot-kimi-k2.5", "providerId": "moonshot", "displayName": "Kimi K2.5", "status": "deprecated", "contextWindow": 262144, "pricing": { "input": 0.6, "output": 3, "cachedInput": 0.1 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.6, "note": "Estimate — Moonshot tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-09-29" }, "maxOutput": 262144, "capabilityIndex": 78 }, { "id": "moonshot-kimi-k2.6", "providerId": "moonshot", "displayName": "Kimi K2.6", "status": "current", "contextWindow": 262144, "pricing": { "input": 0.95, "output": 4, "cachedInput": 0.16 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.6, "note": "Estimate — Moonshot tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-20", "verifiedUrl": "https://platform.kimi.ai/docs/pricing/chat-k26" }, "maxOutput": 262144, "capabilityIndex": 72 }, { "id": "moonshot-kimi-k2.7-code", "providerId": "moonshot", "displayName": "Kimi K2.7 Code", "status": "legacy", "contextWindow": 262144, "pricing": { "input": 0.95, "output": 4, "cachedInput": 0.19, "batchDiscount": 0.6 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.6, "note": "Estimate — Moonshot tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-29", "verifiedUrl": "https://platform.kimi.ai/docs/pricing/chat" }, "maxOutput": 262144 }, { "id": "moonshot-kimi-k3", "providerId": "moonshot", "displayName": "Kimi K3", "status": "current", "contextWindow": 1048576, "pricing": { "input": 3, "output": 15, "cachedInput": 0.3, "cacheWrite": 3, "cacheWrite1h": 6 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.6, "note": "Estimate — Moonshot tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-21", "verifiedUrl": "https://platform.kimi.ai/docs/pricing/chat" }, "maxOutput": 1048576 }, { "id": "moonshot-kimi-k3.1-pro", "providerId": "moonshot", "displayName": "Kimi K3.1 Pro", "status": "current", "contextWindow": 1048576, "pricing": { "input": 2, "output": 10, "cachedInput": 0.2, "cacheWrite": 2, "cacheWrite1h": 4 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.4, "cjkCharsPerToken": 1.6, "note": "Estimate — Moonshot tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-29", "verifiedUrl": "https://platform.kimi.ai/docs/pricing/chat" }, "maxOutput": 1048576, "capabilityIndex": 89 }, { "id": "o1", "providerId": "openai", "displayName": "o1", "status": "deprecated", "contextWindow": 200000, "pricing": { "input": 15, "output": 60, "cachedInput": 7.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-29", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 100000 }, { "id": "o1-pro", "providerId": "openai", "displayName": "o1-pro", "status": "deprecated", "contextWindow": 200000, "pricing": { "input": 150, "output": 600 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-10-29" }, "maxOutput": 100000 }, { "id": "o3", "providerId": "openai", "displayName": "o3", "status": "current", "contextWindow": 200000, "pricing": { "input": 2, "output": 8, "cachedInput": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 100000 }, { "id": "o3-mini", "providerId": "openai", "displayName": "o3-mini", "status": "deprecated", "contextWindow": 200000, "pricing": { "input": 1.1, "output": 4.4, "cachedInput": 0.55 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-29", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 100000 }, { "id": "o3-pro", "providerId": "openai", "displayName": "o3-pro", "status": "legacy", "contextWindow": 200000, "pricing": { "input": 20, "output": 80, "batchDiscount": 0.5 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 100000 }, { "id": "o4-mini", "providerId": "openai", "displayName": "o4-mini", "status": "deprecated", "contextWindow": 200000, "pricing": { "input": 1.1, "output": 4.4, "cachedInput": 0.275 }, "tokenizer": { "kind": "tiktoken", "encoding": "o200k_base" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-10-29", "verifiedUrl": "https://developers.openai.com/api/docs/pricing" }, "maxOutput": 100000, "capabilityIndex": 63 }, { "id": "xai-grok-2", "providerId": "xai", "displayName": "Grok 2", "status": "deprecated", "contextWindow": 131072, "pricing": { "input": 2, "output": 10 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-08-27" }, "maxOutput": 131072 }, { "id": "xai-grok-3", "providerId": "xai", "displayName": "Grok 3", "status": "legacy", "contextWindow": 131072, "pricing": { "input": 1.25, "output": 2.5, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-08-30", "verifiedUrl": "https://docs.x.ai/developers/migration/may-15-retirement" }, "maxOutput": 131072 }, { "id": "xai-grok-4", "providerId": "xai", "displayName": "Grok 4", "status": "legacy", "contextWindow": 256000, "pricing": { "input": 1.25, "output": 2.5, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-08-30", "verifiedUrl": "https://docs.x.ai/developers/migration/may-15-retirement" }, "maxOutput": 256000 }, { "id": "xai-grok-4-1-fast", "providerId": "xai", "displayName": "Grok 4.1 Fast", "status": "legacy", "contextWindow": 2000000, "pricing": { "input": 1.25, "output": 2.5, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "lastChanged": "2026-08-30", "verifiedUrl": "https://docs.x.ai/developers/migration/may-15-retirement" }, "maxOutput": 2000000, "capabilityIndex": 66 }, { "id": "xai-grok-4.20", "providerId": "xai", "displayName": "Grok 4.20", "status": "current", "contextWindow": 1000000, "pricing": { "input": 1.25, "output": 2.5, "cachedInput": 0.2, "longContext": { "thresholdTokens": 200000, "input": 2.5, "output": 5, "cachedInput": 0.4 } }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.x.ai/developers/pricing" }, "maxOutput": 1000000 }, { "id": "xai-grok-4.3", "providerId": "xai", "displayName": "Grok 4.3", "status": "current", "contextWindow": 1000000, "pricing": { "input": 1.25, "output": 2.5, "cachedInput": 0.2, "longContext": { "thresholdTokens": 200000, "input": 2.5, "output": 5, "cachedInput": 0.4 } }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.x.ai/developers/pricing" }, "maxOutput": 1000000, "capabilityIndex": 70 }, { "id": "xai-grok-4.5", "providerId": "xai", "displayName": "Grok 4.5", "status": "current", "contextWindow": 500000, "pricing": { "input": 2, "output": 6, "cachedInput": 0.3, "longContext": { "thresholdTokens": 200000, "input": 4, "output": 12, "cachedInput": 0.6 } }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.x.ai/developers/pricing" }, "maxOutput": 500000, "capabilityIndex": 84 }, { "id": "xai-grok-4.6", "providerId": "xai", "displayName": "Grok 4.6", "status": "current", "contextWindow": 500000, "pricing": { "input": 2, "output": 6, "cachedInput": 0.5, "longContext": { "thresholdTokens": 200000, "input": 4, "output": 12, "cachedInput": 1 } }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.x.ai/developers/pricing" }, "maxOutput": 500000, "capabilityIndex": 85 }, { "id": "xai-grok-4.7", "providerId": "xai", "displayName": "Grok 4.7", "status": "current", "contextWindow": 500000, "pricing": { "input": 2, "output": 6, "cachedInput": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 500000, "capabilityIndex": 87 }, { "id": "xai-grok-build-0.1", "providerId": "xai", "displayName": "Grok Build 0.1", "status": "current", "contextWindow": 256000, "pricing": { "input": 1, "output": 2, "cachedInput": 0.2, "longContext": { "thresholdTokens": 200000, "input": 2, "output": 4, "cachedInput": 0.4 } }, "tokenizer": { "kind": "approx", "charsPerToken": 3.7, "cjkCharsPerToken": 1.6, "note": "Estimate — Grok tokenizer" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.x.ai/developers/pricing" }, "maxOutput": 256000 }, { "id": "xiaomi-mimo-mimo-v2.6-flash", "providerId": "xiaomi", "displayName": "MiMo V2.6 Flash", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.14, "output": 0.28, "cachedInput": 0.0028, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — MiMo tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://mimo.mi.com/docs/en-US/price/pay-as-you-go" }, "maxOutput": 131072, "capabilityIndex": 81 }, { "id": "xiaomi-mimo-mimo-v2.6-pro", "providerId": "xiaomi", "displayName": "MiMo V2.6 Pro", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.435, "output": 0.87, "cachedInput": 0.0036, "batchDiscount": 0.5 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.5, "note": "Estimate — MiMo tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": true }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://mimo.mi.com/docs/en-US/price/pay-as-you-go" }, "maxOutput": 131072, "capabilityIndex": 87 }, { "id": "zai-glm-4-32b-0414-128k", "providerId": "zai", "displayName": "GLM-4 32B", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 0.1, "output": 0.1 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 32000 }, { "id": "zai-glm-4.5", "providerId": "zai", "displayName": "GLM-4.5", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 0.6, "output": 2.2, "cachedInput": 0.11 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 32000 }, { "id": "zai-glm-4.5-air", "providerId": "zai", "displayName": "GLM-4.5-Air", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 0.2, "output": 1.1, "cachedInput": 0.03 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 32000 }, { "id": "zai-glm-4.5-airx", "providerId": "zai", "displayName": "GLM-4.5-AirX", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 1.1, "output": 4.5, "cachedInput": 0.22 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 32000 }, { "id": "zai-glm-4.5-x", "providerId": "zai", "displayName": "GLM-4.5-X", "status": "legacy", "contextWindow": 128000, "pricing": { "input": 2.2, "output": 8.9, "cachedInput": 0.45 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 32000 }, { "id": "zai-glm-4.6", "providerId": "zai", "displayName": "GLM-4.6", "status": "current", "contextWindow": 200000, "pricing": { "input": 0.6, "output": 2.2, "cachedInput": 0.11 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000 }, { "id": "zai-glm-4.7", "providerId": "zai", "displayName": "GLM-4.7", "status": "current", "contextWindow": 200000, "pricing": { "input": 0.6, "output": 2.2, "cachedInput": 0.11 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000 }, { "id": "zai-glm-5", "providerId": "zai", "displayName": "GLM-5", "status": "current", "contextWindow": 200000, "pricing": { "input": 1, "output": 3.2, "cachedInput": 0.2 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000, "capabilityIndex": 71 }, { "id": "zai-glm-5-code", "providerId": "zai", "displayName": "GLM-5 Code", "status": "current", "contextWindow": 200000, "pricing": { "input": 1.2, "output": 5, "cachedInput": 0.3 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "litellm", "lastVerified": "2026-11-11" }, "maxOutput": 128000, "capabilityIndex": 71 }, { "id": "zai-glm-5.1", "providerId": "zai", "displayName": "GLM-5.1", "status": "current", "contextWindow": 200000, "pricing": { "input": 1.4, "output": 4.4, "cachedInput": 0.26 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000, "capabilityIndex": 71 }, { "id": "zai-glm-5.2", "providerId": "zai", "displayName": "GLM-5.2", "status": "current", "contextWindow": 1000000, "pricing": { "input": 1.4, "output": 4.4, "cachedInput": 0.26 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000, "capabilityIndex": 79 }, { "id": "zai-glm-5.3", "providerId": "zai", "displayName": "GLM-5.3", "status": "current", "contextWindow": 1000000, "pricing": { "input": 1.4, "output": 4.4, "cachedInput": 0.26 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000, "capabilityIndex": 87 }, { "id": "zai-glm-5.3-flash", "providerId": "zai", "displayName": "GLM-5.3 Flash", "status": "current", "contextWindow": 1048576, "pricing": { "input": 0.15, "output": 0.5, "cachedInput": 0.03 }, "tokenizer": { "kind": "approx", "charsPerToken": 3.5, "cjkCharsPerToken": 1.6, "note": "Estimate — GLM tokenizer, calibrated for mixed English/Chinese" }, "capabilities": { "reasoning": true, "vision": false }, "provenance": { "source": "vendor", "lastVerified": "2026-11-11", "verifiedUrl": "https://docs.z.ai/guides/overview/pricing" }, "maxOutput": 128000, "capabilityIndex": 86 } ] }