{ "version": 1, "lastUpdated": "2026-07-24", "source": "https://openviglet.github.io/model-catalog", "capability": "tools", "vendors": { "anthropic": [ { "id": "claude-fable-5", "label": "Claude Fable 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-06-07", "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 59.9, "scores": { "coding": { "value": 76.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 58.886, "latencyTtftSec": 65.797, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-fable-5" }, { "id": "claude-haiku-4-5-20251001", "label": "Claude Haiku 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2025-10-15", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23.7, "scores": { "math": { "value": 39 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 101.992, "latencyTtftSec": 0.731, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-haiku-4-5-20251001" }, { "id": "claude-opus-4-1-20250805", "label": "Claude Opus 4.1", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2025-08-05", "pricing": { "inputPer1M": 15, "outputPer1M": 75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 28.2, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-1-20250805" }, { "id": "claude-opus-4-20250514", "label": "Claude Opus 4", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 25.5, "scores": { "math": { "value": 36.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-20250514" }, { "id": "claude-opus-4-5-20251101", "label": "Claude Opus 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2025-11-24", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 34.7, "scores": { "math": { "value": 62.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 67.692, "latencyTtftSec": 1.324, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-5-20251101" }, { "id": "claude-opus-4-6", "label": "Claude Opus 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-02-04", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 37.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 56.657, "latencyTtftSec": 2.197, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-6" }, { "id": "claude-opus-4-7", "label": "Claude Opus 4.7", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-04-14", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 53.5, "scores": { "coding": { "value": 73.6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 61.056, "latencyTtftSec": 23.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-7" }, { "id": "claude-opus-4-8", "label": "Claude Opus 4.8", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-05-28", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 55.7, "scores": { "coding": { "value": 74.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 60.714, "latencyTtftSec": 42.896, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-4-8" }, { "id": "claude-opus-5", "label": "Claude Opus 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-07-24", "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "anthropic-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-opus-5" }, { "id": "claude-sonnet-4-20250514", "label": "Claude Sonnet 4", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 25.5, "scores": { "math": { "value": 38 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-4-20250514" }, { "id": "claude-sonnet-4-5-20250929", "label": "Claude Sonnet 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2025-09-29", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 29.3, "scores": { "math": { "value": 37 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 66.906, "latencyTtftSec": 1.393, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-4-5-20250929" }, { "id": "claude-sonnet-4-6", "label": "Claude Sonnet 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-02-17", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 35.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 59.908, "latencyTtftSec": 1.102, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-4-6" }, { "id": "claude-sonnet-5", "label": "Claude Sonnet 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "releaseDate": "2026-06-29", "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 53.4, "scores": { "coding": { "value": 71.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 80.977, "latencyTtftSec": 103.777, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "anthropic-api", "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "anthropic", "ref": "anthropic/claude-sonnet-5" } ], "azure": [ { "id": "gpt-4.1", "label": "GPT-4.1 (Azure)", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "azure", "ref": "azure/gpt-4.1" }, { "id": "gpt-4o", "label": "GPT-4o (Azure)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "azure", "ref": "azure/gpt-4o" }, { "id": "gpt-4o-mini", "label": "GPT-4o mini (Azure)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.165, "outputPer1M": 0.66, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "azure", "ref": "azure/gpt-4o-mini" }, { "id": "gpt-5", "label": "GPT-5 (Azure)", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "azure", "ref": "azure/gpt-5" }, { "id": "o3", "label": "o3 (Azure)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "azure", "ref": "azure/o3" }, { "id": "o4-mini", "label": "o4-mini (Azure)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "azure", "ref": "azure/o4-mini" } ], "bedrock": [ { "id": "anthropic.claude-3-5-haiku-20241022-v1:0", "label": "Claude 3.5 Haiku", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "bedrock", "ref": "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0" }, { "id": "anthropic.claude-3-5-sonnet-20241022-v2:0", "label": "Claude 3.5 Sonnet v2", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "bedrock", "ref": "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0" }, { "id": "meta.llama3-1-70b-instruct-v1:0", "label": "Llama 3.1 70B Instruct", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 2048, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.99, "outputPer1M": 0.99, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "bedrock", "ref": "bedrock/meta.llama3-1-70b-instruct-v1:0" }, { "id": "mistral.mistral-large-2407-v1:0", "label": "Mistral Large", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8191, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "bedrock", "ref": "bedrock/mistral.mistral-large-2407-v1:0" } ], "cerebras": [ { "id": "gpt-oss-120b", "label": "GPT-OSS 120B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.35, "outputPer1M": 0.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23.8, "scores": { "coding": { "value": 30.4 }, "math": { "value": 93.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 272.018, "latencyTtftSec": 0.533, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "cerebras", "ref": "cerebras/gpt-oss-120b" }, { "id": "llama-3.3-70b", "label": "Llama 3.3 70B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.85, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "cerebras", "ref": "cerebras/llama-3.3-70b" }, { "id": "llama3.1-8b", "label": "Llama 3.1 8B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "cerebras", "ref": "cerebras/llama3.1-8b" }, { "id": "qwen-3-32b", "label": "Qwen3 32B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "cerebras", "ref": "cerebras/qwen-3-32b" }, { "id": "zai-glm-4.6", "label": "GLM-4.6", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.25, "outputPer1M": 2.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "cerebras", "ref": "cerebras/zai-glm-4.6" } ], "cohere": [ { "id": "command-a-03-2025", "label": "Command A", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "cohere", "ref": "cohere/command-a-03-2025" }, { "id": "command-r", "label": "Command R", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "cohere", "ref": "cohere/command-r" }, { "id": "command-r-plus", "label": "Command R+", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "cohere", "ref": "cohere/command-r-plus" } ], "deepseek": [ { "id": "deepseek-chat", "label": "DeepSeek-V3", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "parameters": 671000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.28, "outputPer1M": 0.42, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "deepseek", "ref": "deepseek/deepseek-chat" } ], "fireworks": [ { "id": "accounts/fireworks/models/glm-4p5-air", "label": "GLM-4.5 Air", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 96000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.22, "outputPer1M": 0.88, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "fireworks", "ref": "fireworks/accounts/fireworks/models/glm-4p5-air" }, { "id": "accounts/fireworks/models/glm-4p6", "label": "GLM-4.6", "kind": "CHAT", "contextWindow": 202800, "maxOutputTokens": 202800, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.19, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "fireworks", "ref": "fireworks/accounts/fireworks/models/glm-4p6" } ], "gemini": [ { "id": "gemini-2.0-flash", "label": "Gemini 2.0 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 12.3, "scores": { "math": { "value": 21.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.0-flash" }, { "id": "gemini-2.0-flash-001", "label": "Gemini 2.0 Flash 001", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.0-flash-001" }, { "id": "gemini-2.0-flash-lite", "label": "Gemini 2.0 Flash-Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 8.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.0-flash-lite" }, { "id": "gemini-2.0-flash-lite-001", "label": "Gemini 2.0 Flash-Lite 001", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.0-flash-lite-001" }, { "id": "gemini-2.5-computer-use-preview-10-2025", "label": "Gemini 2.5 Computer Use Preview 10-2025", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.5-computer-use-preview-10-2025" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.1, "scores": { "math": { "value": 60.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 227.181, "latencyTtftSec": 0.373, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash" }, { "id": "gemini-2.5-flash-image", "label": "Nano Banana", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-image" }, { "id": "gemini-2.5-flash-lite", "label": "Gemini 2.5 Flash-Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.9, "scores": { "math": { "value": 35.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.5-flash-lite" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 25.8, "scores": { "coding": { "value": 33.3 }, "math": { "value": 87.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 135.098, "latencyTtftSec": 22.712, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.5-pro" }, { "id": "gemini-2.5-pro-preview-tts", "label": "Gemini 2.5 Pro Preview TTS", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "audio" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-2.5-pro-preview-tts" }, { "id": "gemini-3-flash-preview", "label": "Gemini 3 Flash Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3-flash-preview" }, { "id": "gemini-3-pro-preview", "label": "Gemini 3 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3-pro-preview" }, { "id": "gemini-3.1-flash-lite", "label": "Gemini 3.1 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-lite" }, { "id": "gemini-3.1-flash-lite-preview", "label": "Gemini 3.1 Flash Lite Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 25, "scores": { "coding": { "value": 34.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 299.203, "latencyTtftSec": 5.15, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-lite-preview" }, { "id": "gemini-3.1-pro-preview", "label": "Gemini 3.1 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 46.5, "scores": { "coding": { "value": 68.8 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 127.824, "latencyTtftSec": 27.477, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.1-pro-preview" }, { "id": "gemini-3.1-pro-preview-customtools", "label": "Gemini 3.1 Pro Preview Custom Tools", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.1-pro-preview-customtools" }, { "id": "gemini-3.5-flash", "label": "Gemini 3.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 50.2, "scores": { "coding": { "value": 70.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 252.49, "latencyTtftSec": 16.141, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.5-flash" }, { "id": "gemini-3.5-flash-lite", "label": "Gemini 3.5 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 36.5, "scores": { "coding": { "value": 49.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 357.224, "latencyTtftSec": 7.898, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.5-flash-lite" }, { "id": "gemini-3.6-flash", "label": "Gemini 3.6 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 50.1, "scores": { "coding": { "value": 69.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 255.087, "latencyTtftSec": 16.311, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.6-flash" }, { "id": "gemini-flash-latest", "label": "Gemini Flash Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-flash-latest" }, { "id": "gemini-flash-lite-latest", "label": "Gemini Flash-Lite Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-flash-lite-latest" }, { "id": "gemini-pro-latest", "label": "Gemini Pro Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-pro-latest" }, { "id": "gemini-robotics-er-1.5-preview", "label": "Gemini Robotics-ER 1.5 Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-robotics-er-1.5-preview" }, { "id": "gemini-3.1-flash-live-preview", "label": "Gemini 3.1 Flash Live Preview", "kind": "UNKNOWN", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "gemini-api", "litellm" ], "lastVerified": "2026-07-24", "vendor": "gemini", "ref": "gemini/gemini-3.1-flash-live-preview" } ], "gemini-openai": [ { "id": "gemini-1.5-flash", "label": "Gemini 1.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-1.5-flash" }, { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-1.5-pro" }, { "id": "gemini-2.0-flash", "label": "Gemini 2.0 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-2.0-flash" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-2.5-flash" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "gemini-openai", "ref": "gemini-openai/gemini-2.5-pro" } ], "groq": [ { "id": "llama-3.1-8b-instant", "label": "Llama 3.1 8B Instant", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "parameters": 8000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.08, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/llama-3.1-8b-instant" }, { "id": "llama-3.3-70b-versatile", "label": "Llama 3.3 70B Versatile", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "openWeights": true, "parameters": 70000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.59, "outputPer1M": 0.79, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/llama-3.3-70b-versatile" }, { "id": "meta-llama/llama-4-maverick-17b-128e-instruct", "label": "Llama 4 Maverick 17B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": true, "parameters": 400000000000, "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/meta-llama/llama-4-maverick-17b-128e-instruct" }, { "id": "meta-llama/llama-4-scout-17b-16e-instruct", "label": "Llama 4 Scout 17B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "openWeights": true, "parameters": 109000000000, "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.11, "outputPer1M": 0.34, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/meta-llama/llama-4-scout-17b-16e-instruct" }, { "id": "moonshotai/kimi-k2-instruct-0905", "label": "Kimi K2 Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "openWeights": true, "parameters": 1000000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/moonshotai/kimi-k2-instruct-0905" }, { "id": "openai/gpt-oss-120b", "label": "GPT-OSS 120B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32766, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 117000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/openai/gpt-oss-120b" }, { "id": "openai/gpt-oss-20b", "label": "GPT-OSS 20B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 21000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.9, "scores": { "coding": { "value": 20.7 }, "math": { "value": 89.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 245.179, "latencyTtftSec": 0.422, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/openai/gpt-oss-20b" }, { "id": "qwen/qwen3-32b", "label": "Qwen3 32B", "kind": "CHAT", "contextWindow": 131000, "maxOutputTokens": 131000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "parameters": 32000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.29, "outputPer1M": 0.59, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "groq", "ref": "groq/qwen/qwen3-32b" } ], "minimax": [ { "id": "MiniMax-M2", "label": "MiniMax M2", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 28.3, "scores": { "math": { "value": 78.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 96.733, "latencyTtftSec": 1.169, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "minimax", "ref": "minimax/MiniMax-M2" }, { "id": "MiniMax-M3", "label": "MiniMax M3", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 44.4, "scores": { "coding": { "value": 58.6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 86.628, "latencyTtftSec": 1.351, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "minimax", "ref": "minimax/MiniMax-M3" } ], "mistral": [ { "id": "codestral-latest", "label": "Codestral", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8191, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "mistral", "ref": "mistral/codestral-latest" }, { "id": "mistral-large-latest", "label": "Mistral Large", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "mistral", "ref": "mistral/mistral-large-latest" }, { "id": "mistral-small-latest", "label": "Mistral Small", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.18, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "mistral", "ref": "mistral/mistral-small-latest" } ], "ollama": [ { "id": "athene-v2", "label": "athene-v2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/athene-v2" }, { "id": "aya-expanse", "label": "aya-expanse", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/aya-expanse" }, { "id": "cogito", "label": "cogito", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/cogito" }, { "id": "command-a", "label": "command-a", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/command-a" }, { "id": "command-r", "label": "command-r", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/command-r" }, { "id": "command-r-plus", "label": "command-r-plus", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/command-r-plus" }, { "id": "command-r7b", "label": "command-r7b", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/command-r7b" }, { "id": "command-r7b-arabic", "label": "command-r7b-arabic", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/command-r7b-arabic" }, { "id": "deepseek-r1", "label": "deepseek-r1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/deepseek-r1" }, { "id": "deepseek-v3.1", "label": "deepseek-v3.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 21, "scores": { "math": { "value": 49.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/deepseek-v3.1" }, { "id": "deepseek-v4-flash", "label": "deepseek-v4-flash", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/deepseek-v4-flash" }, { "id": "deepseek-v4-pro", "label": "deepseek-v4-pro", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/deepseek-v4-pro" }, { "id": "devstral", "label": "devstral", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/devstral" }, { "id": "devstral-2", "label": "devstral-2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 19.2, "scores": { "coding": { "value": 31.3 }, "math": { "value": 36.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 58.329, "latencyTtftSec": 0.781, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/devstral-2" }, { "id": "devstral-small-2", "label": "devstral-small-2", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 17.4, "scores": { "coding": { "value": 29.3 }, "math": { "value": 34.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 30.239, "latencyTtftSec": 0.654, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/devstral-small-2" }, { "id": "firefunction-v2", "label": "firefunction-v2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/firefunction-v2" }, { "id": "functiongemma", "label": "functiongemma", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/functiongemma" }, { "id": "gemini-3-flash-preview", "label": "gemini-3-flash-preview", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/gemini-3-flash-preview" }, { "id": "gemma4", "label": "gemma4", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/gemma4" }, { "id": "glm-4.7-flash", "label": "glm-4.7-flash", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/glm-4.7-flash" }, { "id": "glm-5.1", "label": "glm-5.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/glm-5.1" }, { "id": "glm-5.2", "label": "glm-5.2", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/glm-5.2" }, { "id": "glm-ocr", "label": "glm-ocr", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/glm-ocr" }, { "id": "gpt-oss", "label": "gpt-oss", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/gpt-oss" }, { "id": "gpt-oss-safeguard", "label": "gpt-oss-safeguard", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/gpt-oss-safeguard" }, { "id": "granite3-dense", "label": "granite3-dense", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3-dense" }, { "id": "granite3-moe", "label": "granite3-moe", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3-moe" }, { "id": "granite3.1-dense", "label": "granite3.1-dense", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3.1-dense" }, { "id": "granite3.1-moe", "label": "granite3.1-moe", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3.1-moe" }, { "id": "granite3.2", "label": "granite3.2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3.2" }, { "id": "granite3.2-vision", "label": "granite3.2-vision", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3.2-vision" }, { "id": "granite3.3", "label": "granite3.3", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite3.3" }, { "id": "granite4", "label": "granite4", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite4" }, { "id": "granite4.1", "label": "granite4.1", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite4.1" }, { "id": "granite4.1-guardian", "label": "granite4.1-guardian", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/granite4.1-guardian" }, { "id": "hermes3", "label": "hermes3", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/hermes3" }, { "id": "kimi-k2.5", "label": "kimi-k2.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/kimi-k2.5" }, { "id": "kimi-k2.6", "label": "kimi-k2.6", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/kimi-k2.6" }, { "id": "kimi-k2.7-code", "label": "kimi-k2.7-code", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/kimi-k2.7-code" }, { "id": "laguna-xs.2", "label": "laguna-xs.2", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/laguna-xs.2" }, { "id": "lfm2", "label": "lfm2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/lfm2" }, { "id": "lfm2.5", "label": "lfm2.5", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/lfm2.5" }, { "id": "lfm2.5-thinking", "label": "lfm2.5-thinking", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/lfm2.5-thinking" }, { "id": "llama3-groq-tool-use", "label": "llama3-groq-tool-use", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/llama3-groq-tool-use" }, { "id": "llama3.1", "label": "Llama 3.1", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/llama3.1" }, { "id": "llama3.2", "label": "Llama 3.2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/llama3.2" }, { "id": "llama3.3", "label": "llama3.3", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/llama3.3" }, { "id": "llama4", "label": "llama4", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/llama4" }, { "id": "magistral", "label": "magistral", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/magistral" }, { "id": "minimax-m2.5", "label": "minimax-m2.5", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/minimax-m2.5" }, { "id": "minimax-m2.7", "label": "minimax-m2.7", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/minimax-m2.7" }, { "id": "minimax-m3", "label": "minimax-m3", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/minimax-m3" }, { "id": "ministral-3", "label": "ministral-3", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/ministral-3" }, { "id": "mistral", "label": "Mistral", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral" }, { "id": "mistral-large", "label": "mistral-large", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-large" }, { "id": "mistral-large-3", "label": "mistral-large-3", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 15.9, "scores": { "coding": { "value": 20.1 }, "math": { "value": 38 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 63.772, "latencyTtftSec": 0.638, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-large-3" }, { "id": "mistral-medium-3.5", "label": "mistral-medium-3.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-medium-3.5" }, { "id": "mistral-nemo", "label": "mistral-nemo", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-nemo" }, { "id": "mistral-small", "label": "mistral-small", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 4.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-small" }, { "id": "mistral-small3.1", "label": "mistral-small3.1", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 14.7, "scores": { "coding": { "value": 26.3 }, "math": { "value": 3.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-small3.1" }, { "id": "mistral-small3.2", "label": "mistral-small3.2", "kind": "CHAT", "capabilities": [ "vision", "tools" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "benchmarks": { "intelligenceIndex": 10.6, "scores": { "coding": { "value": 12.5 }, "math": { "value": 27 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mistral-small3.2" }, { "id": "mixtral", "label": "mixtral", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/mixtral" }, { "id": "nemotron", "label": "nemotron", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron" }, { "id": "nemotron-3-nano", "label": "nemotron-3-nano", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron-3-nano" }, { "id": "nemotron-3-super", "label": "nemotron-3-super", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron-3-super" }, { "id": "nemotron-3-ultra", "label": "nemotron-3-ultra", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron-3-ultra" }, { "id": "nemotron-cascade-2", "label": "nemotron-cascade-2", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron-cascade-2" }, { "id": "nemotron-mini", "label": "nemotron-mini", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron-mini" }, { "id": "nemotron3", "label": "nemotron3", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "audio", "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/nemotron3" }, { "id": "north-mini-code-1.0", "label": "north-mini-code-1.0", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/north-mini-code-1.0" }, { "id": "olmo-3", "label": "olmo-3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/olmo-3" }, { "id": "olmo-3.1", "label": "olmo-3.1", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/olmo-3.1" }, { "id": "phi4-mini", "label": "phi4-mini", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "benchmarks": { "intelligenceIndex": 6, "scores": { "coding": { "value": 3.8 }, "math": { "value": 6.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 45.988, "latencyTtftSec": 0.345, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/phi4-mini" }, { "id": "qwen2", "label": "qwen2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen2" }, { "id": "qwen2.5", "label": "Qwen 2.5", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen2.5" }, { "id": "qwen2.5-coder", "label": "qwen2.5-coder", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen2.5-coder" }, { "id": "qwen3", "label": "qwen3", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3" }, { "id": "qwen3-coder", "label": "qwen3-coder", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3-coder" }, { "id": "qwen3-coder-next", "label": "qwen3-coder-next", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3-coder-next" }, { "id": "qwen3-next", "label": "qwen3-next", "kind": "CHAT", "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3-next" }, { "id": "qwen3-vl", "label": "qwen3-vl", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3-vl" }, { "id": "qwen3.5", "label": "qwen3.5", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3.5" }, { "id": "qwen3.6", "label": "qwen3.6", "kind": "CHAT", "capabilities": [ "vision", "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "image", "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwen3.6" }, { "id": "qwq", "label": "qwq", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/qwq" }, { "id": "rnj-1", "label": "rnj-1", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/rnj-1" }, { "id": "smollm2", "label": "smollm2", "kind": "CHAT", "capabilities": [ "tools" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "ollama-library" ], "lastVerified": "2026-07-24", "vendor": "ollama", "ref": "ollama/smollm2" } ], "openai": [ { "id": "gpt-3.5-turbo", "label": "gpt-3.5-turbo", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 3.6, "scores": { "coding": { "value": 10.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 151.701, "latencyTtftSec": 0.85, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-3.5-turbo" }, { "id": "gpt-3.5-turbo-0125", "label": "gpt-3.5-turbo-0125", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-3.5-turbo-0125" }, { "id": "gpt-3.5-turbo-1106", "label": "gpt-3.5-turbo-1106", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-3.5-turbo-1106" }, { "id": "gpt-4", "label": "gpt-4", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7, "scores": { "coding": { "value": 13.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 41.704, "latencyTtftSec": 1.152, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4" }, { "id": "gpt-4-0613", "label": "gpt-4-0613", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4-0613" }, { "id": "gpt-4-turbo", "label": "gpt-4-turbo", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7.9, "scores": { "coding": { "value": 21.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 39.876, "latencyTtftSec": 1.281, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4-turbo" }, { "id": "gpt-4-turbo-2024-04-09", "label": "gpt-4-turbo-2024-04-09", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4-turbo-2024-04-09" }, { "id": "gpt-4.1", "label": "GPT-4.1", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4.1" }, { "id": "gpt-4.1-2025-04-14", "label": "gpt-4.1-2025-04-14", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4.1-2025-04-14" }, { "id": "gpt-4.1-mini", "label": "GPT-4.1 mini", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.8, "scores": { "coding": { "value": 20.2 }, "math": { "value": 46.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 77.551, "latencyTtftSec": 0.58, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4.1-mini" }, { "id": "gpt-4.1-mini-2025-04-14", "label": "gpt-4.1-mini-2025-04-14", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4.1-mini-2025-04-14" }, { "id": "gpt-4.1-nano", "label": "GPT-4.1 nano", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 9.6, "scores": { "coding": { "value": 11.1 }, "math": { "value": 24 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 168.005, "latencyTtftSec": 0.412, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4.1-nano" }, { "id": "gpt-4.1-nano-2025-04-14", "label": "gpt-4.1-nano-2025-04-14", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4.1-nano-2025-04-14" }, { "id": "gpt-4o", "label": "GPT-4o", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 11.2, "scores": { "math": { "value": 6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 190.335, "latencyTtftSec": 0.527, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o" }, { "id": "gpt-4o-2024-05-13", "label": "gpt-4o-2024-05-13", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 8.6, "scores": { "coding": { "value": 24.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 99.119, "latencyTtftSec": 0.505, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-2024-05-13" }, { "id": "gpt-4o-2024-08-06", "label": "gpt-4o-2024-08-06", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 9.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 85.378, "latencyTtftSec": 0.485, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-2024-08-06" }, { "id": "gpt-4o-2024-11-20", "label": "gpt-4o-2024-11-20", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-2024-11-20" }, { "id": "gpt-4o-mini", "label": "GPT-4o mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 6.9, "scores": { "coding": { "value": 11.4 }, "math": { "value": 14.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 78.702, "latencyTtftSec": 0.574, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-mini" }, { "id": "gpt-4o-mini-2024-07-18", "label": "gpt-4o-mini-2024-07-18", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-mini-2024-07-18" }, { "id": "gpt-4o-mini-search-preview", "label": "gpt-4o-mini-search-preview", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-mini-search-preview" }, { "id": "gpt-4o-mini-search-preview-2025-03-11", "label": "gpt-4o-mini-search-preview-2025-03-11", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-mini-search-preview-2025-03-11" }, { "id": "gpt-4o-search-preview", "label": "gpt-4o-search-preview", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-search-preview" }, { "id": "gpt-4o-search-preview-2025-03-11", "label": "gpt-4o-search-preview-2025-03-11", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-4o-search-preview-2025-03-11" }, { "id": "gpt-5", "label": "gpt-5", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 34.7, "scores": { "coding": { "value": 37.8 }, "math": { "value": 94.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 113.659, "latencyTtftSec": 80.109, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5" }, { "id": "gpt-5-2025-08-07", "label": "gpt-5-2025-08-07", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-2025-08-07" }, { "id": "gpt-5-codex", "label": "gpt-5-codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 36.1, "scores": { "math": { "value": 98.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 173.495, "latencyTtftSec": 9.851, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-codex" }, { "id": "gpt-5-mini", "label": "gpt-5-mini", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 25.3, "scores": { "coding": { "value": 15.6 }, "math": { "value": 90.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 98.612, "latencyTtftSec": 104.724, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-mini" }, { "id": "gpt-5-mini-2025-08-07", "label": "gpt-5-mini-2025-08-07", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-mini-2025-08-07" }, { "id": "gpt-5-nano", "label": "gpt-5-nano", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 19.9, "scores": { "math": { "value": 83.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 169.486, "latencyTtftSec": 87.29, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-nano" }, { "id": "gpt-5-nano-2025-08-07", "label": "gpt-5-nano-2025-08-07", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-nano-2025-08-07" }, { "id": "gpt-5-pro", "label": "gpt-5-pro", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 120, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-pro" }, { "id": "gpt-5-pro-2025-10-06", "label": "gpt-5-pro-2025-10-06", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 120, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-pro-2025-10-06" }, { "id": "gpt-5-search-api", "label": "gpt-5-search-api", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-search-api" }, { "id": "gpt-5-search-api-2025-10-14", "label": "gpt-5-search-api-2025-10-14", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5-search-api-2025-10-14" }, { "id": "gpt-5.1", "label": "gpt-5.1", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 36.9, "scores": { "coding": { "value": 49.4 }, "math": { "value": 94 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 118.622, "latencyTtftSec": 39.497, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.1" }, { "id": "gpt-5.1-2025-11-13", "label": "gpt-5.1-2025-11-13", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.1-2025-11-13" }, { "id": "gpt-5.1-codex", "label": "gpt-5.1-codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 34.7, "scores": { "math": { "value": 95.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 228.409, "latencyTtftSec": 7.034, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.1-codex" }, { "id": "gpt-5.1-codex-max", "label": "gpt-5.1-codex-max", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.1-codex-max" }, { "id": "gpt-5.1-codex-mini", "label": "gpt-5.1-codex-mini", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 30.6, "scores": { "math": { "value": 91.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 210.408, "latencyTtftSec": 5.507, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.1-codex-mini" }, { "id": "gpt-5.2", "label": "gpt-5.2", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 42.2, "scores": { "math": { "value": 99 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 85.379, "latencyTtftSec": 104.091, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.2" }, { "id": "gpt-5.2-2025-12-11", "label": "gpt-5.2-2025-12-11", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.2-2025-12-11" }, { "id": "gpt-5.2-chat-latest", "label": "gpt-5.2-chat-latest", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.2-chat-latest" }, { "id": "gpt-5.2-codex", "label": "gpt-5.2-codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 40.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 162.362, "latencyTtftSec": 2.744, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.2-codex" }, { "id": "gpt-5.2-pro", "label": "gpt-5.2-pro", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 21, "outputPer1M": 168, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.2-pro" }, { "id": "gpt-5.2-pro-2025-12-11", "label": "gpt-5.2-pro-2025-12-11", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 21, "outputPer1M": 168, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.2-pro-2025-12-11" }, { "id": "gpt-5.3-chat-latest", "label": "gpt-5.3-chat-latest", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.3-chat-latest" }, { "id": "gpt-5.3-codex", "label": "gpt-5.3-codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 44.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 116.252, "latencyTtftSec": 53.33, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.3-codex" }, { "id": "gpt-5.4", "label": "gpt-5.4", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 51.4, "scores": { "coding": { "value": 71.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 152.148, "latencyTtftSec": 121.156, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4" }, { "id": "gpt-5.4-2026-03-05", "label": "gpt-5.4-2026-03-05", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-2026-03-05" }, { "id": "gpt-5.4-mini", "label": "gpt-5.4-mini", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 40, "scores": { "coding": { "value": 56.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 182.435, "latencyTtftSec": 8.23, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-mini" }, { "id": "gpt-5.4-mini-2026-03-17", "label": "gpt-5.4-mini-2026-03-17", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-mini-2026-03-17" }, { "id": "gpt-5.4-nano", "label": "gpt-5.4-nano", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 38.2, "scores": { "coding": { "value": 56.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 156.571, "latencyTtftSec": 3.62, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-nano" }, { "id": "gpt-5.4-nano-2026-03-17", "label": "gpt-5.4-nano-2026-03-17", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-nano-2026-03-17" }, { "id": "gpt-5.4-pro", "label": "gpt-5.4-pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-pro" }, { "id": "gpt-5.4-pro-2026-03-05", "label": "gpt-5.4-pro-2026-03-05", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.4-pro-2026-03-05" }, { "id": "gpt-5.5", "label": "gpt-5.5", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 54.8, "scores": { "coding": { "value": 74.9 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 92.434, "latencyTtftSec": 35.934, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.5" }, { "id": "gpt-5.5-2026-04-23", "label": "gpt-5.5-2026-04-23", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.5-2026-04-23" }, { "id": "gpt-5.5-pro", "label": "gpt-5.5-pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.5-pro" }, { "id": "gpt-5.5-pro-2026-04-23", "label": "gpt-5.5-pro-2026-04-23", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.5-pro-2026-04-23" }, { "id": "gpt-5.6-luna", "label": "gpt-5.6-luna", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 51.2, "scores": { "coding": { "value": 71.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 170.242, "latencyTtftSec": 88.017, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.6-luna" }, { "id": "gpt-5.6-sol", "label": "gpt-5.6-sol", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 58.9, "scores": { "coding": { "value": 77.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 61.573, "latencyTtftSec": 91.32, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.6-sol" }, { "id": "gpt-5.6-terra", "label": "gpt-5.6-terra", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 55, "scores": { "coding": { "value": 76.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 122.303, "latencyTtftSec": 118.567, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-5.6-terra" }, { "id": "gpt-audio", "label": "gpt-audio", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-audio" }, { "id": "o1", "label": "o1", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23.4, "scores": { "coding": { "value": 39.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o1" }, { "id": "o1-2024-12-17", "label": "o1-2024-12-17", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 15, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o1-2024-12-17" }, { "id": "o1-pro", "label": "o1-pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 150, "outputPer1M": 600, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 18.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o1-pro" }, { "id": "o1-pro-2025-03-19", "label": "o1-pro-2025-03-19", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 150, "outputPer1M": 600, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o1-pro-2025-03-19" }, { "id": "o3", "label": "o3", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 30.4, "scores": { "math": { "value": 88.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 135.98, "latencyTtftSec": 7.348, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3" }, { "id": "o3-2025-04-16", "label": "o3-2025-04-16", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-2025-04-16" }, { "id": "o3-deep-research", "label": "o3-deep-research", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 40, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-deep-research" }, { "id": "o3-deep-research-2025-06-26", "label": "o3-deep-research-2025-06-26", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 40, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-deep-research-2025-06-26" }, { "id": "o3-mini", "label": "o3-mini", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 19, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 196.709, "latencyTtftSec": 5.937, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-mini" }, { "id": "o3-mini-2025-01-31", "label": "o3-mini-2025-01-31", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-mini-2025-01-31" }, { "id": "o3-pro", "label": "o3-pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 20, "outputPer1M": 80, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 32.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-pro" }, { "id": "o3-pro-2025-06-10", "label": "o3-pro-2025-06-10", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 20, "outputPer1M": 80, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o3-pro-2025-06-10" }, { "id": "o4-mini", "label": "o4-mini", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 25.6, "scores": { "math": { "value": 90.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 166.47, "latencyTtftSec": 18.783, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o4-mini" }, { "id": "o4-mini-2025-04-16", "label": "o4-mini-2025-04-16", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o4-mini-2025-04-16" }, { "id": "o4-mini-deep-research", "label": "o4-mini-deep-research", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o4-mini-deep-research" }, { "id": "o4-mini-deep-research-2025-06-26", "label": "o4-mini-deep-research-2025-06-26", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/o4-mini-deep-research-2025-06-26" }, { "id": "gpt-audio-1.5", "label": "gpt-audio-1.5", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-audio-1.5" }, { "id": "gpt-audio-2025-08-28", "label": "gpt-audio-2025-08-28", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-audio-2025-08-28" }, { "id": "gpt-audio-mini", "label": "gpt-audio-mini", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-audio-mini" }, { "id": "gpt-audio-mini-2025-10-06", "label": "gpt-audio-mini-2025-10-06", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-audio-mini-2025-10-06" }, { "id": "gpt-audio-mini-2025-12-15", "label": "gpt-audio-mini-2025-12-15", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-audio-mini-2025-12-15" }, { "id": "gpt-realtime", "label": "gpt-realtime", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime" }, { "id": "gpt-realtime-1.5", "label": "gpt-realtime-1.5", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-1.5" }, { "id": "gpt-realtime-2", "label": "gpt-realtime-2", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-2" }, { "id": "gpt-realtime-2.1", "label": "gpt-realtime-2.1", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-2.1" }, { "id": "gpt-realtime-2.1-mini", "label": "gpt-realtime-2.1-mini", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-2.1-mini" }, { "id": "gpt-realtime-2025-08-28", "label": "gpt-realtime-2025-08-28", "kind": "SPEECH", "contextWindow": 32000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 4, "outputPer1M": 16, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-2025-08-28" }, { "id": "gpt-realtime-mini", "label": "gpt-realtime-mini", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-mini" }, { "id": "gpt-realtime-mini-2025-10-06", "label": "gpt-realtime-mini-2025-10-06", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-mini-2025-10-06" }, { "id": "gpt-realtime-mini-2025-12-15", "label": "gpt-realtime-mini-2025-12-15", "kind": "SPEECH", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-24", "vendor": "openai", "ref": "openai/gpt-realtime-mini-2025-12-15" } ], "openrouter": [ { "id": "~anthropic/claude-fable-latest", "label": "Anthropic: Claude Fable Latest", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-fable-latest" }, { "id": "~anthropic/claude-haiku-latest", "label": "Anthropic Claude Haiku Latest", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-haiku-latest" }, { "id": "~anthropic/claude-opus-latest", "label": "Anthropic: Claude Opus Latest", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-opus-latest" }, { "id": "~anthropic/claude-sonnet-latest", "label": "Anthropic Claude Sonnet Latest", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~anthropic/claude-sonnet-latest" }, { "id": "~google/gemini-flash-latest", "label": "Google Gemini Flash Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~google/gemini-flash-latest" }, { "id": "~google/gemini-pro-latest", "label": "Google Gemini Pro Latest", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~google/gemini-pro-latest" }, { "id": "~moonshotai/kimi-latest", "label": "MoonshotAI Kimi Latest", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~moonshotai/kimi-latest" }, { "id": "~openai/gpt-latest", "label": "OpenAI GPT Latest", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-latest" }, { "id": "~openai/gpt-mini-latest", "label": "OpenAI GPT Mini Latest", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~openai/gpt-mini-latest" }, { "id": "~x-ai/grok-latest", "label": "xAI: Grok Latest", "kind": "CHAT", "contextWindow": 500000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/~x-ai/grok-latest" }, { "id": "ai21/jamba-large-1.7", "label": "AI21: Jamba Large 1.7", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 5.3, "scores": { "math": { "value": 2.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 53.585, "latencyTtftSec": 0.923, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/ai21/jamba-large-1.7" }, { "id": "aion-labs/aion-2.0", "label": "AionLabs: Aion-2.0", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-2.0" }, { "id": "aion-labs/aion-3.0", "label": "AionLabs: Aion-3.0", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-3.0" }, { "id": "aion-labs/aion-3.0-mini", "label": "AionLabs: Aion-3.0-Mini", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.7, "outputPer1M": 1.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/aion-labs/aion-3.0-mini" }, { "id": "amazon/nova-2-lite-v1", "label": "Amazon: Nova 2 Lite", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/amazon/nova-2-lite-v1" }, { "id": "amazon/nova-lite-v1", "label": "Amazon: Nova Lite 1.0", "kind": "CHAT", "contextWindow": 300000, "maxOutputTokens": 5120, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10-31", "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/amazon/nova-lite-v1" }, { "id": "amazon/nova-micro-v1", "label": "Amazon: Nova Micro 1.0", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 5120, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10-31", "pricing": { "inputPer1M": 0.035, "outputPer1M": 0.14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/amazon/nova-micro-v1" }, { "id": "amazon/nova-premier-v1", "label": "Amazon: Nova Premier 1.0", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 12.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/amazon/nova-premier-v1" }, { "id": "amazon/nova-pro-v1", "label": "Amazon: Nova Pro 1.0", "kind": "CHAT", "contextWindow": 300000, "maxOutputTokens": 5120, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-10-31", "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/amazon/nova-pro-v1" }, { "id": "anthropic/claude-3-haiku", "label": "Claude 3 Haiku (via OpenRouter)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-08-31", "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 3.9, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api", "overrides" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-3-haiku" }, { "id": "anthropic/claude-fable-5", "label": "Anthropic: Claude Fable 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-fable-5" }, { "id": "anthropic/claude-haiku-4.5", "label": "Anthropic: Claude Haiku 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 200000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-haiku-4.5" }, { "id": "anthropic/claude-opus-4", "label": "Anthropic: Claude Opus 4", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 15, "outputPer1M": 75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4" }, { "id": "anthropic/claude-opus-4.1", "label": "Anthropic: Claude Opus 4.1", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 15, "outputPer1M": 75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.1" }, { "id": "anthropic/claude-opus-4.5", "label": "Anthropic: Claude Opus 4.5", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 34.7, "scores": { "math": { "value": 62.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.5" }, { "id": "anthropic/claude-opus-4.6", "label": "Anthropic: Claude Opus 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.6" }, { "id": "anthropic/claude-opus-4.7", "label": "Anthropic: Claude Opus 4.7", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.7" }, { "id": "anthropic/claude-opus-4.7-fast", "label": "Anthropic: Claude Opus 4.7 (Fast)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 150, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.7-fast" }, { "id": "anthropic/claude-opus-4.8", "label": "Anthropic: Claude Opus 4.8", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.8" }, { "id": "anthropic/claude-opus-4.8-fast", "label": "Anthropic: Claude Opus 4.8 (Fast)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-4.8-fast" }, { "id": "anthropic/claude-opus-5", "label": "Claude Opus 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-5" }, { "id": "anthropic/claude-opus-5-fast", "label": "Claude Opus 5 (Fast)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 50, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-opus-5-fast" }, { "id": "anthropic/claude-sonnet-4", "label": "Anthropic: Claude Sonnet 4", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4" }, { "id": "anthropic/claude-sonnet-4.5", "label": "Claude Sonnet 4.5 (via OpenRouter)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 1000000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openrouter-api", "overrides" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4.5" }, { "id": "anthropic/claude-sonnet-4.6", "label": "Anthropic: Claude Sonnet 4.6", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-4.6" }, { "id": "anthropic/claude-sonnet-5", "label": "Anthropic: Claude Sonnet 5", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/anthropic/claude-sonnet-5" }, { "id": "arcee-ai/trinity-large-thinking", "label": "Arcee AI: Trinity Large Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 80000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 18.2, "scores": { "coding": { "value": 25.8 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 141.761, "latencyTtftSec": 0.489, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/arcee-ai/trinity-large-thinking" }, { "id": "arcee-ai/virtuoso-large", "label": "Arcee AI: Virtuoso Large", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 64000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.75, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/arcee-ai/virtuoso-large" }, { "id": "bytedance-seed/seed-1.6", "label": "ByteDance Seed: Seed 1.6", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-1.6" }, { "id": "bytedance-seed/seed-1.6-flash", "label": "ByteDance Seed: Seed 1.6 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-1.6-flash" }, { "id": "bytedance-seed/seed-2.0-lite", "label": "ByteDance Seed: Seed-2.0-Lite", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-2.0-lite" }, { "id": "bytedance-seed/seed-2.0-mini", "label": "ByteDance Seed: Seed-2.0-Mini", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/bytedance-seed/seed-2.0-mini" }, { "id": "cohere/command-r-08-2024", "label": "Cohere: Command R (08-2024)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-03-31", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/cohere/command-r-08-2024" }, { "id": "cohere/command-r-plus-08-2024", "label": "Cohere: Command R+ (08-2024)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-03-31", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/cohere/command-r-plus-08-2024" }, { "id": "cohere/north-mini-code:free", "label": "Cohere: North Mini Code (free)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 64000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/cohere/north-mini-code:free" }, { "id": "deepseek/deepseek-chat", "label": "DeepSeek Chat (via OpenRouter)", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07-31", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "openrouter-api", "overrides" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-chat" }, { "id": "deepseek/deepseek-chat-v3-0324", "label": "DeepSeek: DeepSeek V3 0324", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07-31", "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-chat-v3-0324" }, { "id": "deepseek/deepseek-chat-v3.1", "label": "DeepSeek: DeepSeek V3.1", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 163840, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-chat-v3.1" }, { "id": "deepseek/deepseek-r1", "label": "DeepSeek: R1", "kind": "CHAT", "contextWindow": 65336, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-07-31", "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.19, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-r1" }, { "id": "deepseek/deepseek-r1-0528", "label": "DeepSeek: R1 0528", "kind": "CHAT", "contextWindow": 65336, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-r1-0528" }, { "id": "deepseek/deepseek-v3.1-terminus", "label": "DeepSeek: DeepSeek V3.1 Terminus", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.27, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 21.4, "scores": { "math": { "value": 53.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v3.1-terminus" }, { "id": "deepseek/deepseek-v3.2", "label": "DeepSeek: DeepSeek V3.2", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 163840, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.28, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 24.7, "scores": { "math": { "value": 59 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v3.2" }, { "id": "deepseek/deepseek-v3.2-exp", "label": "DeepSeek: DeepSeek V3.2 Exp", "kind": "CHAT", "contextWindow": 163840, "maxOutputTokens": 163840, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-07-31", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v3.2-exp" }, { "id": "deepseek/deepseek-v4-flash", "label": "DeepSeek: DeepSeek V4 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.098, "outputPer1M": 0.196, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-flash" }, { "id": "deepseek/deepseek-v4-pro", "label": "DeepSeek: DeepSeek V4 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 384000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.435, "outputPer1M": 0.87, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/deepseek/deepseek-v4-pro" }, { "id": "google/gemini-2.0-flash-001", "label": "Gemini 2.0 Flash (via OpenRouter)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.0-flash-001" }, { "id": "google/gemini-2.5-flash", "label": "Google: Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-flash" }, { "id": "google/gemini-2.5-flash-lite", "label": "Google: Gemini 2.5 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-flash-lite" }, { "id": "google/gemini-2.5-pro", "label": "Google: Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-pro" }, { "id": "google/gemini-2.5-pro-preview", "label": "Google: Gemini 2.5 Pro Preview 06-05", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-pro-preview" }, { "id": "google/gemini-2.5-pro-preview-05-06", "label": "Google: Gemini 2.5 Pro Preview 05-06", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-31", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-2.5-pro-preview-05-06" }, { "id": "google/gemini-3-flash-preview", "label": "Google: Gemini 3 Flash Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3-flash-preview" }, { "id": "google/gemini-3-pro-image", "label": "Google: Nano Banana Pro (Gemini 3 Pro Image)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3-pro-image" }, { "id": "google/gemini-3.1-flash-lite", "label": "Google: Gemini 3.1 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-lite" }, { "id": "google/gemini-3.1-flash-lite-preview", "label": "Google: Gemini 3.1 Flash Lite Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-flash-lite-preview" }, { "id": "google/gemini-3.1-pro-preview", "label": "Google: Gemini 3.1 Pro Preview", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-pro-preview" }, { "id": "google/gemini-3.1-pro-preview-customtools", "label": "Google: Gemini 3.1 Pro Preview Custom Tools", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.1-pro-preview-customtools" }, { "id": "google/gemini-3.5-flash", "label": "Google: Gemini 3.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-01-01", "pricing": { "inputPer1M": 1.5, "outputPer1M": 9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.5-flash" }, { "id": "google/gemini-3.5-flash-lite", "label": "Google: Gemini 3.5 Flash Lite", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.5-flash-lite" }, { "id": "google/gemini-3.6-flash", "label": "Google: Gemini 3.6 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemini-3.6-flash" }, { "id": "google/gemma-3-12b-it", "label": "Google: Gemma 3 12B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemma-3-12b-it" }, { "id": "google/gemma-3-27b-it", "label": "Google: Gemma 3 27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.45, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemma-3-27b-it" }, { "id": "google/gemma-4-26b-a4b-it", "label": "Google: Gemma 4 26B A4B ", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.12, "outputPer1M": 0.35, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-26b-a4b-it" }, { "id": "google/gemma-4-26b-a4b-it:free", "label": "Google: Gemma 4 26B A4B (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-26b-a4b-it:free" }, { "id": "google/gemma-4-31b-it", "label": "Google: Gemma 4 31B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.14, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-31b-it" }, { "id": "google/gemma-4-31b-it:free", "label": "Google: Gemma 4 31B (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/google/gemma-4-31b-it:free" }, { "id": "ibm-granite/granite-4.1-8b", "label": "IBM: Granite 4.1 8B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.7, "scores": { "coding": { "value": 9.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 102.537, "latencyTtftSec": 0.449, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/ibm-granite/granite-4.1-8b" }, { "id": "inception/mercury-2", "label": "Inception: Mercury 2", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 50000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 0.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 21.4, "scores": { "coding": { "value": 31.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 1096.748, "latencyTtftSec": 3.583, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/inception/mercury-2" }, { "id": "inclusionai/ling-2.6-1t", "label": "inclusionAI: Ling-2.6-1T", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.625, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 26.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-2.6-1t" }, { "id": "inclusionai/ling-2.6-flash", "label": "inclusionAI: Ling-2.6-flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.01, "outputPer1M": 0.03, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 14.1, "scores": { "coding": { "value": 25.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 127.228, "latencyTtftSec": 0.667, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-2.6-flash" }, { "id": "inclusionai/ling-3.0-flash:free", "label": "Ling-3.0-flash (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/inclusionai/ling-3.0-flash:free" }, { "id": "inclusionai/ring-2.6-1t", "label": "inclusionAI: Ring-2.6-1T", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.625, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 30.6, "scores": { "coding": { "value": 42.8 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 127.165, "latencyTtftSec": 2.089, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/inclusionai/ring-2.6-1t" }, { "id": "kwaipilot/kat-coder-air-v2.5", "label": "Kwaipilot: KAT-Coder-Air V2.5", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 80000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/kwaipilot/kat-coder-air-v2.5" }, { "id": "kwaipilot/kat-coder-pro-v2", "label": "Kwaipilot: KAT-Coder-Pro V2", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 80000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.7, "scores": { "coding": { "value": 59.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 105.278, "latencyTtftSec": 1.109, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/kwaipilot/kat-coder-pro-v2" }, { "id": "kwaipilot/kat-coder-pro-v2.5", "label": "Kwaipilot: KAT-Coder-Pro V2.5", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 80000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.74, "outputPer1M": 2.96, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/kwaipilot/kat-coder-pro-v2.5" }, { "id": "meituan/longcat-2.0", "label": "Meituan: LongCat 2.0", "kind": "CHAT", "contextWindow": 1048756, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.5, "scores": { "coding": { "value": 45.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meituan/longcat-2.0" }, { "id": "meta-llama/llama-3.1-70b-instruct", "label": "Meta: Llama 3.1 70B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 0.4, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.8, "scores": { "math": { "value": 4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.1-70b-instruct" }, { "id": "meta-llama/llama-3.1-8b-instruct", "label": "Meta: Llama 3.1 8B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.08, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.6, "scores": { "coding": { "value": 5.4 }, "math": { "value": 4.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.1-8b-instruct" }, { "id": "meta-llama/llama-3.3-70b-instruct", "label": "Meta: Llama 3.3 70B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 0.13, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9.4, "scores": { "coding": { "value": 11.9 }, "math": { "value": 7.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 79.187, "latencyTtftSec": 0.648, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-3.3-70b-instruct" }, { "id": "meta-llama/llama-4-maverick", "label": "Meta: Llama 4 Maverick", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 14.3, "scores": { "coding": { "value": 16.3 }, "math": { "value": 19.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 101.626, "latencyTtftSec": 0.596, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-4-maverick" }, { "id": "meta-llama/llama-4-scout", "label": "Meta: Llama 4 Scout", "kind": "CHAT", "contextWindow": 1310720, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-08-31", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 10, "scores": { "coding": { "value": 8.2 }, "math": { "value": 14 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 88.556, "latencyTtftSec": 0.59, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meta-llama/llama-4-scout" }, { "id": "meta/muse-spark-1.1", "label": "Meta: Muse Spark 1.1", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 4.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 50.6, "scores": { "coding": { "value": 71.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 124.125, "latencyTtftSec": 0.925, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/meta/muse-spark-1.1" }, { "id": "minimax/minimax-m1", "label": "MiniMax: MiniMax M1", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 40000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.55, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m1" }, { "id": "minimax/minimax-m2", "label": "MiniMax: MiniMax M2", "kind": "CHAT", "contextWindow": 204800, "maxOutputTokens": 204800, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.255, "outputPer1M": 1.02, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m2" }, { "id": "minimax/minimax-m2.1", "label": "MiniMax: MiniMax M2.1", "kind": "CHAT", "contextWindow": 204000, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.27, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 31.4, "scores": { "math": { "value": 82.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m2.1" }, { "id": "minimax/minimax-m2.5", "label": "MiniMax: MiniMax M2.5", "kind": "CHAT", "contextWindow": 196608, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m2.5" }, { "id": "minimax/minimax-m2.7", "label": "MiniMax: MiniMax M2.7", "kind": "CHAT", "contextWindow": 204800, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m2.7" }, { "id": "minimax/minimax-m3", "label": "MiniMax: MiniMax M3", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 512000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/minimax/minimax-m3" }, { "id": "mistralai/codestral-2508", "label": "Mistral: Codestral 2508", "kind": "CHAT", "contextWindow": 256000, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/codestral-2508" }, { "id": "mistralai/devstral-2512", "label": "Mistral: Devstral 2 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/devstral-2512" }, { "id": "mistralai/ministral-14b-2512", "label": "Mistral: Ministral 3 14B 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/ministral-14b-2512" }, { "id": "mistralai/ministral-3b-2512", "label": "Mistral: Ministral 3 3B 2512", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/ministral-3b-2512" }, { "id": "mistralai/ministral-8b-2512", "label": "Mistral: Ministral 3 8B 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/ministral-8b-2512" }, { "id": "mistralai/mistral-large", "label": "Mistral Large", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8191, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-11-30", "pricing": { "inputPer1M": 8, "outputPer1M": 24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large" }, { "id": "mistralai/mistral-large-2407", "label": "Mistral Large 2407", "kind": "CHAT", "contextWindow": 131072, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-03-31", "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large-2407" }, { "id": "mistralai/mistral-large-2512", "label": "Mistral: Mistral Large 3 2512", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-large-2512" }, { "id": "mistralai/mistral-medium-3", "label": "Mistral: Mistral Medium 3", "kind": "CHAT", "contextWindow": 131072, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 12.5, "scores": { "math": { "value": 30.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3" }, { "id": "mistralai/mistral-medium-3-5", "label": "Mistral: Mistral Medium 3.5", "kind": "CHAT", "contextWindow": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.5, "outputPer1M": 7.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3-5" }, { "id": "mistralai/mistral-medium-3.1", "label": "Mistral: Mistral Medium 3.1", "kind": "CHAT", "contextWindow": 131072, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 14.7, "scores": { "coding": { "value": 20.5 }, "math": { "value": 38.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-medium-3.1" }, { "id": "mistralai/mistral-nemo", "label": "Mistral: Mistral Nemo", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04-30", "pricing": { "inputPer1M": 0.019, "outputPer1M": 0.03, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-nemo" }, { "id": "mistralai/mistral-saba", "label": "Mistral: Saba", "kind": "CHAT", "contextWindow": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 6.4, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-saba" }, { "id": "mistralai/mistral-small-2603", "label": "Mistral: Mistral Small 4", "kind": "CHAT", "contextWindow": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-small-2603" }, { "id": "mistralai/mistral-small-3.2-24b-instruct", "label": "Mistral: Mistral Small 3.2 24B", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mistral-small-3.2-24b-instruct" }, { "id": "mistralai/mixtral-8x22b-instruct", "label": "Mistral: Mixtral 8x22B Instruct", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-01-31", "pricing": { "inputPer1M": 0.65, "outputPer1M": 0.65, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/mixtral-8x22b-instruct" }, { "id": "mistralai/voxtral-small-24b-2507", "label": "Mistral: Voxtral Small 24B 2507", "kind": "CHAT", "contextWindow": 32000, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/mistralai/voxtral-small-24b-2507" }, { "id": "moonshotai/kimi-k2", "label": "MoonshotAI: Kimi K2 0711", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 100352, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "pricing": { "inputPer1M": 0.57, "outputPer1M": 2.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 19.4, "scores": { "math": { "value": 57 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2" }, { "id": "moonshotai/kimi-k2-0905", "label": "MoonshotAI: Kimi K2 0905", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 100352, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 23.5, "scores": { "math": { "value": 57.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2-0905" }, { "id": "moonshotai/kimi-k2-thinking", "label": "MoonshotAI: Kimi K2 Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 100352, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 32.7, "scores": { "math": { "value": 94.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2-thinking" }, { "id": "moonshotai/kimi-k2.5", "label": "MoonshotAI: Kimi K2.5", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2.5" }, { "id": "moonshotai/kimi-k2.6", "label": "MoonshotAI: Kimi K2.6", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.684, "outputPer1M": 3.42, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2.6" }, { "id": "moonshotai/kimi-k2.7-code", "label": "MoonshotAI: Kimi K2.7 Code", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.82, "outputPer1M": 3.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k2.7-code" }, { "id": "moonshotai/kimi-k3", "label": "MoonshotAI: Kimi K3", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 57.1, "scores": { "coding": { "value": 76.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 33.23, "latencyTtftSec": 9.893, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/moonshotai/kimi-k3" }, { "id": "nex-agi/nex-n2-mini", "label": "Nex AGI: Nex-N2-Mini", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.025, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nex-agi/nex-n2-mini" }, { "id": "nex-agi/nex-n2-pro", "label": "Nex AGI: Nex-N2-Pro", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 41, "scores": { "coding": { "value": 59.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 130.025, "latencyTtftSec": 0.961, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nex-agi/nex-n2-pro" }, { "id": "nvidia/nemotron-3-nano-30b-a3b", "label": "NVIDIA: Nemotron 3 Nano 30B A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 228000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-nano-30b-a3b" }, { "id": "nvidia/nemotron-3-nano-30b-a3b:free", "label": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", "kind": "CHAT", "contextWindow": 256000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-nano-30b-a3b:free" }, { "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "label": "NVIDIA: Nemotron 3 Nano Omni (free)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free" }, { "id": "nvidia/nemotron-3-super-120b-a12b", "label": "NVIDIA: Nemotron 3 Super", "kind": "CHAT", "contextWindow": 1000000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.45, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-super-120b-a12b" }, { "id": "nvidia/nemotron-3-super-120b-a12b:free", "label": "NVIDIA: Nemotron 3 Super (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-super-120b-a12b:free" }, { "id": "nvidia/nemotron-3-ultra-550b-a55b", "label": "NVIDIA: Nemotron 3 Ultra", "kind": "CHAT", "contextWindow": 512288, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.5, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-ultra-550b-a55b" }, { "id": "nvidia/nemotron-3-ultra-550b-a55b:free", "label": "NVIDIA: Nemotron 3 Ultra (free)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free" }, { "id": "nvidia/nemotron-nano-12b-v2-vl:free", "label": "NVIDIA: Nemotron Nano 12B 2 VL (free)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-nano-12b-v2-vl:free" }, { "id": "nvidia/nemotron-nano-9b-v2:free", "label": "NVIDIA: Nemotron Nano 9B V2 (free)", "kind": "CHAT", "contextWindow": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/nvidia/nemotron-nano-9b-v2:free" }, { "id": "openai/gpt-3.5-turbo", "label": "OpenAI: GPT-3.5 Turbo", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "pricing": { "inputPer1M": 1.5, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-3.5-turbo" }, { "id": "openai/gpt-3.5-turbo-0613", "label": "OpenAI: GPT-3.5 Turbo (older v0613)", "kind": "CHAT", "contextWindow": 4095, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-3.5-turbo-0613" }, { "id": "openai/gpt-3.5-turbo-16k", "label": "OpenAI: GPT-3.5 Turbo 16k", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "pricing": { "inputPer1M": 3, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-3.5-turbo-16k" }, { "id": "openai/gpt-4", "label": "OpenAI: GPT-4", "kind": "CHAT", "contextWindow": 8191, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2021-09-30", "pricing": { "inputPer1M": 30, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4" }, { "id": "openai/gpt-4-turbo", "label": "OpenAI: GPT-4 Turbo", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 10, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4-turbo" }, { "id": "openai/gpt-4-turbo-preview", "label": "OpenAI: GPT-4 Turbo Preview", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 10, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4-turbo-preview" }, { "id": "openai/gpt-4.1", "label": "OpenAI: GPT-4.1", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1" }, { "id": "openai/gpt-4.1-mini", "label": "OpenAI: GPT-4.1 Mini", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1-mini" }, { "id": "openai/gpt-4.1-nano", "label": "OpenAI: GPT-4.1 Nano", "kind": "CHAT", "contextWindow": 1047576, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4.1-nano" }, { "id": "openai/gpt-4o", "label": "GPT-4o (via OpenRouter)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "openrouter-api", "overrides" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o" }, { "id": "openai/gpt-4o-2024-05-13", "label": "OpenAI: GPT-4o (2024-05-13)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-2024-05-13" }, { "id": "openai/gpt-4o-2024-08-06", "label": "OpenAI: GPT-4o (2024-08-06)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-2024-08-06" }, { "id": "openai/gpt-4o-2024-11-20", "label": "OpenAI: GPT-4o (2024-11-20)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-2024-11-20" }, { "id": "openai/gpt-4o-mini", "label": "OpenAI: GPT-4o-mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-mini" }, { "id": "openai/gpt-4o-mini-2024-07-18", "label": "OpenAI: GPT-4o-mini (2024-07-18)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-4o-mini-2024-07-18" }, { "id": "openai/gpt-5", "label": "OpenAI: GPT-5", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5" }, { "id": "openai/gpt-5-codex", "label": "OpenAI: GPT-5 Codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-codex" }, { "id": "openai/gpt-5-mini", "label": "OpenAI: GPT-5 Mini", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-31", "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-mini" }, { "id": "openai/gpt-5-nano", "label": "OpenAI: GPT-5 Nano", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-05-31", "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-nano" }, { "id": "openai/gpt-5-pro", "label": "OpenAI: GPT-5 Pro", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-09-30", "pricing": { "inputPer1M": 15, "outputPer1M": 120, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5-pro" }, { "id": "openai/gpt-5.1", "label": "OpenAI: GPT-5.1", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1" }, { "id": "openai/gpt-5.1-chat", "label": "OpenAI: GPT-5.1 Chat", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-chat" }, { "id": "openai/gpt-5.1-codex", "label": "OpenAI: GPT-5.1-Codex", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-codex" }, { "id": "openai/gpt-5.1-codex-max", "label": "OpenAI: GPT-5.1-Codex-Max", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-codex-max" }, { "id": "openai/gpt-5.1-codex-mini", "label": "OpenAI: GPT-5.1-Codex-Mini", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.1-codex-mini" }, { "id": "openai/gpt-5.2", "label": "OpenAI: GPT-5.2", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2" }, { "id": "openai/gpt-5.2-chat", "label": "OpenAI: GPT-5.2 Chat", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-chat" }, { "id": "openai/gpt-5.2-codex", "label": "OpenAI: GPT-5.2-Codex", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "reasoning", "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-codex" }, { "id": "openai/gpt-5.2-pro", "label": "OpenAI: GPT-5.2 Pro", "kind": "CHAT", "contextWindow": 272000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 21, "outputPer1M": 168, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.2-pro" }, { "id": "openai/gpt-5.3-chat", "label": "OpenAI: GPT-5.3 Chat", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.3-chat" }, { "id": "openai/gpt-5.3-codex", "label": "OpenAI: GPT-5.3-Codex", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.75, "outputPer1M": 14, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.3-codex" }, { "id": "openai/gpt-5.4", "label": "OpenAI: GPT-5.4", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4" }, { "id": "openai/gpt-5.4-mini", "label": "OpenAI: GPT-5.4 Mini", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "pricing": { "inputPer1M": 0.75, "outputPer1M": 4.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-mini" }, { "id": "openai/gpt-5.4-nano", "label": "OpenAI: GPT-5.4 Nano", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-08-31", "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-nano" }, { "id": "openai/gpt-5.4-pro", "label": "OpenAI: GPT-5.4 Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.4-pro" }, { "id": "openai/gpt-5.5", "label": "OpenAI: GPT-5.5", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.5" }, { "id": "openai/gpt-5.5-pro", "label": "OpenAI: GPT-5.5 Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-12-01", "pricing": { "inputPer1M": 30, "outputPer1M": 180, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.5-pro" }, { "id": "openai/gpt-5.6-luna", "label": "OpenAI: GPT-5.6 Luna", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-luna" }, { "id": "openai/gpt-5.6-luna-pro", "label": "OpenAI: GPT-5.6 Luna Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 1, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-luna-pro" }, { "id": "openai/gpt-5.6-sol", "label": "OpenAI: GPT-5.6 Sol", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-sol" }, { "id": "openai/gpt-5.6-sol-pro", "label": "OpenAI: GPT-5.6 Sol Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-sol-pro" }, { "id": "openai/gpt-5.6-terra", "label": "OpenAI: GPT-5.6 Terra", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-terra" }, { "id": "openai/gpt-5.6-terra-pro", "label": "OpenAI: GPT-5.6 Terra Pro", "kind": "CHAT", "contextWindow": 1050000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2026-02-16", "pricing": { "inputPer1M": 2.5, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-5.6-terra-pro" }, { "id": "openai/gpt-audio", "label": "OpenAI: GPT Audio", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-audio" }, { "id": "openai/gpt-audio-mini", "label": "OpenAI: GPT Audio Mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-audio-mini" }, { "id": "openai/gpt-chat-latest", "label": "OpenAI: GPT Chat Latest", "kind": "CHAT", "contextWindow": 400000, "maxOutputTokens": 128000, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-chat-latest" }, { "id": "openai/gpt-oss-120b", "label": "OpenAI: gpt-oss-120b", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.18, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-120b" }, { "id": "openai/gpt-oss-20b", "label": "OpenAI: gpt-oss-20b", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.02, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-20b" }, { "id": "openai/gpt-oss-20b:free", "label": "OpenAI: gpt-oss-20b (free)", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-20b:free" }, { "id": "openai/gpt-oss-safeguard-20b", "label": "OpenAI: gpt-oss-safeguard-20b", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.075, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/gpt-oss-safeguard-20b" }, { "id": "openai/o1", "label": "OpenAI: o1", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 15, "outputPer1M": 60, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o1" }, { "id": "openai/o3", "label": "OpenAI: o3", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o3" }, { "id": "openai/o3-deep-research", "label": "OpenAI: o3 Deep Research", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 10, "outputPer1M": 40, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o3-deep-research" }, { "id": "openai/o3-mini", "label": "OpenAI: o3 Mini", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o3-mini" }, { "id": "openai/o3-mini-high", "label": "OpenAI: o3 Mini High", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-10-31", "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 15.6, "scores": { "coding": { "value": 16.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o3-mini-high" }, { "id": "openai/o3-pro", "label": "OpenAI: o3 Pro", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 20, "outputPer1M": 80, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o3-pro" }, { "id": "openai/o4-mini", "label": "OpenAI: o4 Mini", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o4-mini" }, { "id": "openai/o4-mini-deep-research", "label": "OpenAI: o4 Mini Deep Research", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o4-mini-deep-research" }, { "id": "openai/o4-mini-high", "label": "OpenAI: o4 Mini High", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 100000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 1.1, "outputPer1M": 4.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openai/o4-mini-high" }, { "id": "openrouter/auto", "label": "Auto Router", "kind": "CHAT", "contextWindow": 2000000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openrouter/auto" }, { "id": "openrouter/auto-beta", "label": "Auto Router (Beta)", "kind": "CHAT", "contextWindow": 2000000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openrouter/auto-beta" }, { "id": "openrouter/free", "label": "Free Models Router", "kind": "CHAT", "contextWindow": 200000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/openrouter/free" }, { "id": "poolside/laguna-m.1", "label": "Poolside: Laguna M.1", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/poolside/laguna-m.1" }, { "id": "poolside/laguna-m.1:free", "label": "Poolside: Laguna M.1 (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/poolside/laguna-m.1:free" }, { "id": "poolside/laguna-s-2.1", "label": "Poolside: Laguna S 2.1", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/poolside/laguna-s-2.1" }, { "id": "poolside/laguna-s-2.1:free", "label": "Poolside: Laguna S 2.1 (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/poolside/laguna-s-2.1:free" }, { "id": "poolside/laguna-xs-2.1", "label": "Poolside: Laguna XS 2.1", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.06, "outputPer1M": 0.12, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/poolside/laguna-xs-2.1" }, { "id": "poolside/laguna-xs-2.1:free", "label": "Poolside: Laguna XS 2.1 (free)", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/poolside/laguna-xs-2.1:free" }, { "id": "qwen/qwen-2.5-72b-instruct", "label": "Qwen2.5 72B Instruct", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.36, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 9.6, "scores": { "math": { "value": 14 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-2.5-72b-instruct" }, { "id": "qwen/qwen-2.5-7b-instruct", "label": "Qwen: Qwen2.5 7B Instruct", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-06-30", "pricing": { "inputPer1M": 0.04, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-2.5-7b-instruct" }, { "id": "qwen/qwen-plus", "label": "Qwen: Qwen-Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.26, "outputPer1M": 0.78, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-plus" }, { "id": "qwen/qwen-plus-2025-07-28", "label": "Qwen: Qwen Plus 0728", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.26, "outputPer1M": 0.78, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-plus-2025-07-28" }, { "id": "qwen/qwen-plus-2025-07-28:thinking", "label": "Qwen: Qwen Plus 0728 (thinking)", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.26, "outputPer1M": 0.78, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen-plus-2025-07-28:thinking" }, { "id": "qwen/qwen3-14b", "label": "Qwen: Qwen3 14B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.2275, "outputPer1M": 0.91, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-14b" }, { "id": "qwen/qwen3-235b-a22b", "label": "Qwen: Qwen3 235B A22B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.455, "outputPer1M": 1.82, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-235b-a22b" }, { "id": "qwen/qwen3-235b-a22b-2507", "label": "Qwen: Qwen3 235B A22B Instruct 2507", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.071, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-235b-a22b-2507" }, { "id": "qwen/qwen3-235b-a22b-thinking-2507", "label": "Qwen: Qwen3 235B A22B Thinking 2507", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.11, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-235b-a22b-thinking-2507" }, { "id": "qwen/qwen3-30b-a3b", "label": "Qwen: Qwen3 30B A3B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.13, "outputPer1M": 0.52, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-30b-a3b" }, { "id": "qwen/qwen3-30b-a3b-instruct-2507", "label": "Qwen: Qwen3 30B A3B Instruct 2507", "kind": "CHAT", "contextWindow": 262144, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-30b-a3b-instruct-2507" }, { "id": "qwen/qwen3-30b-a3b-thinking-2507", "label": "Qwen: Qwen3 30B A3B Thinking 2507", "kind": "CHAT", "contextWindow": 81920, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.13, "outputPer1M": 1.56, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-30b-a3b-thinking-2507" }, { "id": "qwen/qwen3-32b", "label": "Qwen: Qwen3 32B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.08, "outputPer1M": 0.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-32b" }, { "id": "qwen/qwen3-8b", "label": "Qwen: Qwen3 8B", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.117, "outputPer1M": 0.455, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-8b" }, { "id": "qwen/qwen3-coder", "label": "Qwen: Qwen3 Coder 480B A35B", "kind": "CHAT", "contextWindow": 262100, "maxOutputTokens": 262100, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.22, "outputPer1M": 0.95, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder" }, { "id": "qwen/qwen3-coder-30b-a3b-instruct", "label": "Qwen: Qwen3 Coder 30B A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.27, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 13.6, "scores": { "math": { "value": 29 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-30b-a3b-instruct" }, { "id": "qwen/qwen3-coder-flash", "label": "Qwen: Qwen3 Coder Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.195, "outputPer1M": 0.975, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-flash" }, { "id": "qwen/qwen3-coder-next", "label": "Qwen: Qwen3 Coder Next", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.11, "outputPer1M": 0.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-next" }, { "id": "qwen/qwen3-coder-plus", "label": "Qwen: Qwen3 Coder Plus", "kind": "CHAT", "contextWindow": 997952, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 1, "outputPer1M": 5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-coder-plus" }, { "id": "qwen/qwen3-max", "label": "Qwen: Qwen3 Max", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-06-30", "pricing": { "inputPer1M": 0.78, "outputPer1M": 3.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 24, "scores": { "math": { "value": 80.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-max" }, { "id": "qwen/qwen3-max-thinking", "label": "Qwen: Qwen3 Max Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.78, "outputPer1M": 3.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 31.7, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-max-thinking" }, { "id": "qwen/qwen3-next-80b-a3b-instruct", "label": "Qwen: Qwen3 Next 80B A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-30", "pricing": { "inputPer1M": 0.1, "outputPer1M": 1.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 13.7, "scores": { "math": { "value": 66.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 187.432, "latencyTtftSec": 1.025, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-next-80b-a3b-instruct" }, { "id": "qwen/qwen3-next-80b-a3b-thinking", "label": "Qwen: Qwen3 Next 80B A3B Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-30", "pricing": { "inputPer1M": 0.0975, "outputPer1M": 0.78, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-next-80b-a3b-thinking" }, { "id": "qwen/qwen3-vl-235b-a22b-instruct", "label": "Qwen: Qwen3 VL 235B A22B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.21, "outputPer1M": 1.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 14.3, "scores": { "math": { "value": 70.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-235b-a22b-instruct" }, { "id": "qwen/qwen3-vl-235b-a22b-thinking", "label": "Qwen: Qwen3 VL 235B A22B Thinking", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.26, "outputPer1M": 2.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-235b-a22b-thinking" }, { "id": "qwen/qwen3-vl-30b-a3b-instruct", "label": "Qwen: Qwen3 VL 30B A3B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 10, "scores": { "math": { "value": 72.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-30b-a3b-instruct" }, { "id": "qwen/qwen3-vl-30b-a3b-thinking", "label": "Qwen: Qwen3 VL 30B A3B Thinking", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.13, "outputPer1M": 1.56, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-30b-a3b-thinking" }, { "id": "qwen/qwen3-vl-32b-instruct", "label": "Qwen: Qwen3 VL 32B Instruct", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.104, "outputPer1M": 0.416, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 11.1, "scores": { "math": { "value": 68.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-32b-instruct" }, { "id": "qwen/qwen3-vl-8b-instruct", "label": "Qwen: Qwen3 VL 8B Instruct", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 32768, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.117, "outputPer1M": 0.455, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 8.4, "scores": { "math": { "value": 27.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-8b-instruct" }, { "id": "qwen/qwen3-vl-8b-thinking", "label": "Qwen: Qwen3 VL 8B Thinking", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.117, "outputPer1M": 1.365, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3-vl-8b-thinking" }, { "id": "qwen/qwen3.5-122b-a10b", "label": "Qwen: Qwen3.5-122B-A10B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 32.3, "scores": { "coding": { "value": 45.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 135.358, "latencyTtftSec": 1.023, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-122b-a10b" }, { "id": "qwen/qwen3.5-27b", "label": "Qwen: Qwen3.5-27B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.8, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-27b" }, { "id": "qwen/qwen3.5-35b-a3b", "label": "Qwen: Qwen3.5-35B-A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.25, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 29.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-35b-a3b" }, { "id": "qwen/qwen3.5-397b-a17b", "label": "Qwen: Qwen3.5 397B A17B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 3.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.7, "scores": { "coding": { "value": 48.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 65.024, "latencyTtftSec": 1.48, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-397b-a17b" }, { "id": "qwen/qwen3.5-9b", "label": "Qwen: Qwen3.5-9B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 21.4, "scores": { "coding": { "value": 28.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 50.343, "latencyTtftSec": 1.177, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-9b" }, { "id": "qwen/qwen3.5-flash-02-23", "label": "Qwen: Qwen3.5-Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-flash-02-23" }, { "id": "qwen/qwen3.5-plus-02-15", "label": "Qwen: Qwen3.5 Plus 2026-02-15", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-plus-02-15" }, { "id": "qwen/qwen3.5-plus-20260420", "label": "Qwen: Qwen3.5 Plus 2026-04-20", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.5-plus-20260420" }, { "id": "qwen/qwen3.6-27b", "label": "Qwen: Qwen3.6 27B", "kind": "CHAT", "contextWindow": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.288, "outputPer1M": 2.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 37.1, "scores": { "coding": { "value": 53.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 58.427, "latencyTtftSec": 1.44, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-27b" }, { "id": "qwen/qwen3.6-35b-a3b", "label": "Qwen: Qwen3.6 35B A3B", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 262144, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.14, "outputPer1M": 1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 31.6, "scores": { "coding": { "value": 41.9 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 149.207, "latencyTtftSec": 1.253, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-35b-a3b" }, { "id": "qwen/qwen3.6-flash", "label": "Qwen: Qwen3.6 Flash", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1875, "outputPer1M": 1.125, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-flash" }, { "id": "qwen/qwen3.6-max-preview", "label": "Qwen: Qwen3.6 Max Preview", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.04, "outputPer1M": 6.24, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-max-preview" }, { "id": "qwen/qwen3.6-plus", "label": "Qwen: Qwen3.6 Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.325, "outputPer1M": 1.95, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 39.6, "scores": { "coding": { "value": 54.5 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 52.808, "latencyTtftSec": 1.638, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.6-plus" }, { "id": "qwen/qwen3.7-max", "label": "Qwen: Qwen3.7 Max", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.475, "outputPer1M": 4.425, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 46, "scores": { "coding": { "value": 66 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 199.573, "latencyTtftSec": 1.579, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.7-max" }, { "id": "qwen/qwen3.7-plus", "label": "Qwen: Qwen3.7 Plus", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.32, "outputPer1M": 1.28, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 39, "scores": { "coding": { "value": 55.9 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 53.2, "latencyTtftSec": 1.714, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/qwen/qwen3.7-plus" }, { "id": "rekaai/reka-edge", "label": "Reka Edge", "kind": "CHAT", "contextWindow": 16384, "maxOutputTokens": 16384, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/rekaai/reka-edge" }, { "id": "relace/relace-search", "label": "Relace: Relace Search", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 128000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/relace/relace-search" }, { "id": "sakana/fugu-ultra", "label": "Sakana: Fugu Ultra", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 5, "outputPer1M": 30, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/sakana/fugu-ultra" }, { "id": "sao10k/l3.1-euryale-70b", "label": "Sao10K: Llama 3.1 Euryale 70B v2.2", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 16384, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2023-12-31", "pricing": { "inputPer1M": 0.85, "outputPer1M": 0.85, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/sao10k/l3.1-euryale-70b" }, { "id": "stepfun/step-3.5-flash", "label": "StepFun: Step 3.5 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 65536, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 26, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 294.218, "latencyTtftSec": 0.744, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/stepfun/step-3.5-flash" }, { "id": "stepfun/step-3.7-flash", "label": "StepFun: Step 3.7 Flash", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 30.3, "scores": { "coding": { "value": 39.6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 397.589, "latencyTtftSec": 0.614, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/stepfun/step-3.7-flash" }, { "id": "tencent/hy3", "label": "Tencent: Hy3", "kind": "CHAT", "contextWindow": 262144, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.132, "outputPer1M": 0.528, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 41.2, "scores": { "coding": { "value": 58.8 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 65.247, "latencyTtftSec": 1.868, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/tencent/hy3" }, { "id": "tencent/hy3-preview", "label": "Tencent: Hy3 preview", "kind": "CHAT", "contextWindow": 262144, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.063, "outputPer1M": 0.21, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.6, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 113.227, "latencyTtftSec": 1.685, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/tencent/hy3-preview" }, { "id": "thedrummer/unslopnemo-12b", "label": "TheDrummer: UnslopNemo 12B", "kind": "CHAT", "contextWindow": 32768, "maxOutputTokens": 32768, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-04-30", "pricing": { "inputPer1M": 0.4, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/thedrummer/unslopnemo-12b" }, { "id": "thinkingmachines/inkling", "label": "Thinking Machines: Inkling", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "audio", "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 4.05, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 40.7, "scores": { "coding": { "value": 52.1 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 57.334, "latencyTtftSec": 2.399, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/thinkingmachines/inkling" }, { "id": "upstage/solar-pro-3", "label": "Upstage: Solar Pro 3", "kind": "CHAT", "contextWindow": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 14.1, "scores": { "coding": { "value": 16.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/upstage/solar-pro-3" }, { "id": "x-ai/grok-4.20", "label": "xAI: Grok 4.20", "kind": "CHAT", "contextWindow": 2000000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-09-01", "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 37, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.20" }, { "id": "x-ai/grok-4.3", "label": "xAI: Grok 4.3", "kind": "CHAT", "contextWindow": 1000000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 37.6, "scores": { "coding": { "value": 42.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.3" }, { "id": "x-ai/grok-4.5", "label": "xAI: Grok 4.5", "kind": "CHAT", "contextWindow": 500000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 53.8, "scores": { "coding": { "value": 72.4 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 55.991, "latencyTtftSec": 11.135, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-4.5" }, { "id": "x-ai/grok-build-0.1", "label": "xAI: Grok Build 0.1", "kind": "CHAT", "contextWindow": 256000, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/x-ai/grok-build-0.1" }, { "id": "xiaomi/mimo-v2.5", "label": "Xiaomi: MiMo-V2.5", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.5" }, { "id": "xiaomi/mimo-v2.5-pro", "label": "Xiaomi: MiMo-V2.5-Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1, "outputPer1M": 3, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 42.2, "scores": { "coding": { "value": 60.2 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 63.458, "latencyTtftSec": 2.209, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/xiaomi/mimo-v2.5-pro" }, { "id": "z-ai/glm-4.5", "label": "Z.ai: GLM 4.5", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 98304, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.5" }, { "id": "z-ai/glm-4.5-air", "label": "Z.ai: GLM 4.5 Air", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 98304, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "pricing": { "inputPer1M": 0.13, "outputPer1M": 0.85, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.5-air" }, { "id": "z-ai/glm-4.5v", "label": "Z.ai: GLM 4.5V", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2024-12-31", "pricing": { "inputPer1M": 0.6, "outputPer1M": 1.8, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 7, "scores": { "math": { "value": 15.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.5v" }, { "id": "z-ai/glm-4.6", "label": "Z.ai: GLM 4.6", "kind": "CHAT", "contextWindow": 202800, "maxOutputTokens": 131000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledgeCutoff": "2025-03-31", "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.75, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.6" }, { "id": "z-ai/glm-4.6v", "label": "Z.ai: GLM 4.6V", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.9, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 11, "scores": { "math": { "value": 26.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.6v" }, { "id": "z-ai/glm-4.7", "label": "Z.ai: GLM 4.7", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 64000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 33.7, "scores": { "coding": { "value": 45.3 }, "math": { "value": 95 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.7" }, { "id": "z-ai/glm-4.7-flash", "label": "Z.ai: GLM 4.7 Flash", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 32000, "capabilities": [ "tools", "vision", "reasoning" ], "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.07, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-4.7-flash" }, { "id": "z-ai/glm-5", "label": "Z.ai: GLM 5", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 2.56, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 39.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5" }, { "id": "z-ai/glm-5-turbo", "label": "Z.ai: GLM 5 Turbo", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.2, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 38.1, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5-turbo" }, { "id": "z-ai/glm-5.1", "label": "Z.ai: GLM 5.1", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 65535, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.05, "outputPer1M": 3.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.1" }, { "id": "z-ai/glm-5.2", "label": "Z.ai: GLM 5.2", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.791, "outputPer1M": 2.486, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "sources": [ "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5.2" }, { "id": "z-ai/glm-5v-turbo", "label": "Z.ai: GLM 5V Turbo", "kind": "CHAT", "contextWindow": 202752, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning", "vision" ], "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.2, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "openrouter", "lastVerified": "2026-07-24" }, "benchmarks": { "intelligenceIndex": 34.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "openrouter-api" ], "lastVerified": "2026-07-24", "vendor": "openrouter", "ref": "openrouter/z-ai/glm-5v-turbo" } ], "qwen": [ { "id": "qwen-coder", "label": "Qwen-Coder", "kind": "CHAT", "contextWindow": 1000000, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "qwen", "ref": "qwen/qwen-coder" }, { "id": "qwen-flash", "label": "Qwen-Flash", "kind": "CHAT", "contextWindow": 997952, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "qwen", "ref": "qwen/qwen-flash" }, { "id": "qwen-max", "label": "Qwen-Max", "kind": "CHAT", "contextWindow": 30720, "maxOutputTokens": 8192, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.6, "outputPer1M": 6.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "qwen", "ref": "qwen/qwen-max" }, { "id": "qwen-plus", "label": "Qwen-Plus", "kind": "CHAT", "contextWindow": 129024, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.4, "outputPer1M": 1.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "qwen", "ref": "qwen/qwen-plus" }, { "id": "qwen-turbo", "label": "Qwen-Turbo", "kind": "CHAT", "contextWindow": 129024, "maxOutputTokens": 16384, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "outputPer1M": 0.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 6.3, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 107.358, "latencyTtftSec": 1.04, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "qwen", "ref": "qwen/qwen-turbo" } ], "together": [ { "id": "deepseek-ai/DeepSeek-R1", "label": "DeepSeek-R1", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 20480, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 7, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "together", "ref": "together/deepseek-ai/DeepSeek-R1" }, { "id": "deepseek-ai/DeepSeek-V3", "label": "DeepSeek-V3", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 1.25, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 14.2, "scores": { "coding": { "value": 23 }, "math": { "value": 26 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "together", "ref": "together/deepseek-ai/DeepSeek-V3" }, { "id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "label": "Llama 3.3 70B Instruct Turbo", "kind": "CHAT", "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.88, "outputPer1M": 0.88, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "together", "ref": "together/meta-llama/Llama-3.3-70B-Instruct-Turbo" }, { "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "label": "Llama 4 Maverick 17B", "kind": "CHAT", "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.27, "outputPer1M": 0.85, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "together", "ref": "together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" }, { "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "label": "Qwen3 235B A22B Instruct", "kind": "CHAT", "contextWindow": 262000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "together", "ref": "together/Qwen/Qwen3-235B-A22B-Instruct-2507-tput" }, { "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "label": "Qwen3 Coder 480B", "kind": "CHAT", "contextWindow": 256000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2, "outputPer1M": 2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "together", "ref": "together/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8" } ], "vercel": [ { "id": "amazon/nova-pro", "label": "Amazon Nova Pro (via Vercel)", "kind": "CHAT", "contextWindow": 300000, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 3.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7.7, "scores": { "math": { "value": 7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "vercel", "ref": "vercel/amazon/nova-pro" }, { "id": "anthropic/claude-3.5-haiku", "label": "Claude 3.5 Haiku (via Vercel)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.8, "outputPer1M": 4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "vercel", "ref": "vercel/anthropic/claude-3.5-haiku" }, { "id": "cohere/command-a", "label": "Command A (via Vercel)", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 8000, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 2.5, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 7.7, "scores": { "math": { "value": 13 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 55.482, "latencyTtftSec": 0.494, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "vercel", "ref": "vercel/cohere/command-a" }, { "id": "google/gemini-2.0-flash", "label": "Gemini 2.0 Flash (via Vercel)", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.15, "outputPer1M": 0.6, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "vercel", "ref": "vercel/google/gemini-2.0-flash" } ], "vertex-ai": [ { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-24", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-1.5-pro" }, { "id": "gemini-2.0-flash", "label": "Gemini 2.0 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 8192, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "image", "text" ] }, "pricing": { "inputPer1M": 0.1, "outputPer1M": 0.4, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-2.0-flash" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 2.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-2.5-flash" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "maxOutputTokens": 65535, "capabilities": [ "vision", "tools", "reasoning" ], "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "outputPer1M": 10, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-24", "vendor": "vertex-ai", "ref": "vertex-ai/gemini-2.5-pro" } ], "xai": [ { "id": "grok-3", "label": "Grok 3", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 18.4, "scores": { "math": { "value": 58 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "xai", "ref": "xai/grok-3" }, { "id": "grok-3-mini", "label": "Grok 3 Mini", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 131072, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "outputPer1M": 0.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "xai", "ref": "xai/grok-3-mini" }, { "id": "grok-4", "label": "Grok 4", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "outputPer1M": 15, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 33.3, "scores": { "math": { "value": 92.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "xai", "ref": "xai/grok-4" }, { "id": "grok-code-fast-1", "label": "Grok Code Fast 1", "kind": "CHAT", "contextWindow": 256000, "maxOutputTokens": 256000, "capabilities": [ "tools", "reasoning" ], "openWeights": false, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.5, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 21.6, "scores": { "math": { "value": 43.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "xai", "ref": "xai/grok-code-fast-1" } ], "zai": [ { "id": "glm-4.5", "label": "GLM-4.5", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools" ], "openWeights": true, "parameters": 355000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 19.5, "scores": { "math": { "value": 73.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "zai", "ref": "zai/glm-4.5" }, { "id": "glm-4.5-air", "label": "GLM-4.5-Air", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 32000, "capabilities": [ "tools" ], "openWeights": true, "parameters": 106000000000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.2, "outputPer1M": 1.1, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 16.5, "scores": { "math": { "value": 80.7 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 78.49, "latencyTtftSec": 1.394, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "zai", "ref": "zai/glm-4.5-air" }, { "id": "glm-4.6", "label": "GLM-4.6", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 128000, "capabilities": [ "tools", "reasoning" ], "openWeights": true, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.6, "outputPer1M": 2.2, "currency": "USD", "unit": "per_1M_tokens", "indicative": true, "note": "Indicative US list price — verify with the vendor.", "source": "litellm", "lastVerified": "2026-07-22" }, "benchmarks": { "intelligenceIndex": 23, "scores": { "math": { "value": 44.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-24" }, "performance": { "throughputTps": 69.954, "latencyTtftSec": 0.893, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-24", "vendor": "zai", "ref": "zai/glm-4.6" } ] } }