{ "$schema": "https://openviglet.github.io/model-catalog/catalog.schema.json", "version": 1, "lastUpdated": "2026-07-22", "source": "https://openviglet.github.io/model-catalog", "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": "2026-07-22" }, "performance": { "throughputTps": 69.473, "latencyTtftSec": 58.275, "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": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 110.416, "latencyTtftSec": 0.788, "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": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "sources": [ "anthropic-api", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "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", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "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", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "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", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 64.336, "latencyTtftSec": 37.626, "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": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "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", "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "anthropic" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 87.842, "latencyTtftSec": 90.434, "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": "2026-07-22", "vendor": "anthropic" } ], "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": "2026-07-22", "vendor": "azure" }, { "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": "2026-07-22", "vendor": "azure" }, { "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": "2026-07-22", "vendor": "azure" }, { "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": "2026-07-22", "vendor": "azure" }, { "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": "2026-07-22", "vendor": "azure" }, { "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": "2026-07-22", "vendor": "azure" } ], "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": "2026-07-22", "vendor": "bedrock" }, { "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": "2026-07-22", "vendor": "bedrock" }, { "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": "2026-07-22", "vendor": "bedrock" }, { "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": "2026-07-22", "vendor": "bedrock" }, { "id": "amazon.titan-embed-text-v2:0", "label": "Titan Text Embeddings v2", "kind": "EMBEDDING", "contextWindow": 8192, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.02, "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": "2026-07-22", "vendor": "bedrock" } ], "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": "2026-07-22" }, "performance": { "throughputTps": 286.915, "latencyTtftSec": 0.506, "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": "2026-07-22", "vendor": "cerebras" }, { "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": "2026-07-22", "vendor": "cerebras" }, { "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": "2026-07-22", "vendor": "cerebras" }, { "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": "2026-07-22", "vendor": "cerebras" }, { "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": "2026-07-22", "vendor": "cerebras" } ], "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": "2026-07-22", "vendor": "cohere" }, { "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": "2026-07-22", "vendor": "cohere" }, { "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": "2026-07-22", "vendor": "cohere" }, { "id": "embed-multilingual-v3.0", "label": "Embed Multilingual v3", "kind": "EMBEDDING", "contextWindow": 1024, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 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" ], "lastVerified": "2026-07-22", "vendor": "cohere" }, { "id": "embed-v4.0", "label": "Embed v4", "kind": "EMBEDDING", "contextWindow": 128000, "embeddingDimensions": 1536, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.12, "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": "2026-07-22", "vendor": "cohere" }, { "id": "rerank-v3.5", "label": "Rerank v3.5", "kind": "RERANK", "contextWindow": 4096, "maxOutputTokens": 4096, "modalities": { "input": [ "text" ] }, "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "cohere" } ], "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": "2026-07-22", "vendor": "deepseek" }, { "id": "deepseek-reasoner", "label": "DeepSeek-R1", "kind": "CHAT", "contextWindow": 131072, "maxOutputTokens": 65536, "capabilities": [ "reasoning" ], "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": "2026-07-22", "vendor": "deepseek" } ], "fireworks": [ { "id": "accounts/fireworks/models/deepseek-r1", "label": "DeepSeek-R1", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 20480, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 3, "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", "overrides" ], "lastVerified": "2026-07-22", "vendor": "fireworks" }, { "id": "accounts/fireworks/models/deepseek-v3", "label": "DeepSeek-V3", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.9, "outputPer1M": 0.9, "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", "overrides" ], "lastVerified": "2026-07-22", "vendor": "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": "2026-07-22", "vendor": "fireworks" }, { "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": "2026-07-22", "vendor": "fireworks" } ], "gemini": [ { "id": "gemini-1.5-flash", "label": "Gemini 1.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "embeddingDimensions": 3072, "capabilities": [ "vision", "tools" ], "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.075, "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, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini" }, { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "benchmarks": { "intelligenceIndex": 10, "scores": { "coding": { "value": 23.6 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed" ], "lastVerified": "2026-07-22", "vendor": "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "gemini" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "gemini" }, { "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" }, "benchmarks": { "intelligenceIndex": 14.1, "scores": { "math": { "value": 60.3 } }, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "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", "litellm" ], "lastVerified": "2026-07-22", "vendor": "gemini" }, { "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" }, "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": "2026-07-22" }, "performance": { "throughputTps": 136.211, "latencyTtftSec": 20.35, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "gemini" }, { "id": "gemini-embedding-001", "label": "gemini-embedding-001", "kind": "EMBEDDING", "contextWindow": 2048, "embeddingDimensions": 3072, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.15, "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" ], "lastVerified": "2026-07-22", "vendor": "gemini" }, { "id": "text-embedding-004", "label": "text-embedding-004", "kind": "EMBEDDING", "embeddingDimensions": 768, "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini" } ], "gemini-openai": [ { "id": "gemini-1.5-flash", "label": "Gemini 1.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini-openai" }, { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini-openai" }, { "id": "gemini-2.0-flash", "label": "Gemini 2.0 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini-openai" }, { "id": "gemini-2.5-flash", "label": "Gemini 2.5 Flash", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini-openai" }, { "id": "gemini-2.5-pro", "label": "Gemini 2.5 Pro", "kind": "CHAT", "contextWindow": 1048576, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "gemini-openai" } ], "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 243.28, "latencyTtftSec": 0.405, "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": "2026-07-22", "vendor": "groq" }, { "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": "2026-07-22", "vendor": "groq" } ], "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "minimax" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 100.356, "latencyTtftSec": 1.357, "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": "2026-07-22", "vendor": "minimax" } ], "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": "2026-07-22", "vendor": "mistral" }, { "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": "2026-07-22", "vendor": "mistral" }, { "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": "2026-07-22", "vendor": "mistral" }, { "id": "open-mistral-nemo", "label": "Mistral Nemo", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 128000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.3, "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" }, "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "mistral" }, { "id": "mistral-embed", "label": "Mistral Embed", "kind": "EMBEDDING", "contextWindow": 8192, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 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" ], "lastVerified": "2026-07-22", "vendor": "mistral" } ], "ollama": [ { "id": "gemma2", "label": "Gemma 2", "kind": "CHAT", "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "ollama" }, { "id": "llama3.1", "label": "Llama 3.1", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "ollama" }, { "id": "llama3.2", "label": "Llama 3.2", "kind": "CHAT", "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "ollama" }, { "id": "mistral", "label": "Mistral", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8192, "capabilities": [ "tools" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm" ], "lastVerified": "2026-07-22", "vendor": "ollama" }, { "id": "phi3", "label": "Phi-3", "kind": "CHAT", "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "ollama" }, { "id": "qwen2.5", "label": "Qwen 2.5", "kind": "CHAT", "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "ollama" }, { "id": "nomic-embed-text", "label": "nomic-embed-text", "kind": "EMBEDDING", "embeddingDimensions": 768, "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "ollama" } ], "openai": [ { "id": "babbage-002", "label": "babbage-002", "kind": "CHAT", "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "chat-latest", "label": "chat-latest", "kind": "CHAT", "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "davinci-002", "label": "davinci-002", "kind": "CHAT", "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-3.5-turbo-16k", "label": "gpt-3.5-turbo-16k", "kind": "CHAT", "contextWindow": 16385, "maxOutputTokens": 4096, "modalities": { "input": [ "text" ] }, "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": "2026-07-22" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-3.5-turbo-instruct", "label": "gpt-3.5-turbo-instruct", "kind": "CHAT", "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-3.5-turbo-instruct-0914", "label": "gpt-3.5-turbo-instruct-0914", "kind": "CHAT", "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-5-chat-latest", "label": "gpt-5-chat-latest", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-5.1-chat-latest", "label": "gpt-5.1-chat-latest", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 16384, "capabilities": [ "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 115.634, "latencyTtftSec": 41.56, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 201.659, "latencyTtftSec": 91.629, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 65.818, "latencyTtftSec": 87.94, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 137.56, "latencyTtftSec": 100.446, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 161.796, "latencyTtftSec": 4.524, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "id": "text-embedding-3-large", "label": "text-embedding-3-large", "kind": "EMBEDDING", "contextWindow": 8191, "embeddingDimensions": 3072, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.13, "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", "openai-api", "overrides" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "text-embedding-3-small", "label": "text-embedding-3-small", "kind": "EMBEDDING", "contextWindow": 8191, "embeddingDimensions": 1536, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.02, "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", "openai-api", "overrides" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "text-embedding-ada-002", "label": "text-embedding-ada-002", "kind": "EMBEDDING", "contextWindow": 8191, "embeddingDimensions": 1536, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "chatgpt-image-latest", "label": "chatgpt-image-latest", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-image-1", "label": "gpt-image-1", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-image-1-mini", "label": "gpt-image-1-mini", "kind": "IMAGE", "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-image-1.5", "label": "gpt-image-1.5", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-image-2", "label": "gpt-image-2", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-image-2-2026-04-21", "label": "gpt-image-2-2026-04-21", "kind": "IMAGE", "capabilities": [ "vision" ], "modalities": { "input": [ "image", "pdf", "text" ] }, "pricing": { "inputPer1M": 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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-mini-transcribe", "label": "gpt-4o-mini-transcribe", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "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" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-mini-transcribe-2025-03-20", "label": "gpt-4o-mini-transcribe-2025-03-20", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "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" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-mini-transcribe-2025-12-15", "label": "gpt-4o-mini-transcribe-2025-12-15", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 1.25, "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" }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-transcribe", "label": "gpt-4o-transcribe", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-transcribe-diarize", "label": "gpt-4o-transcribe-diarize", "kind": "TRANSCRIPTION", "contextWindow": 16000, "maxOutputTokens": 2000, "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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-realtime-whisper", "label": "gpt-realtime-whisper", "kind": "TRANSCRIPTION", "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "whisper-1", "label": "whisper-1", "kind": "TRANSCRIPTION", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-mini-tts", "label": "gpt-4o-mini-tts", "kind": "SPEECH", "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-mini-tts-2025-03-20", "label": "gpt-4o-mini-tts-2025-03-20", "kind": "SPEECH", "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "gpt-4o-mini-tts-2025-12-15", "label": "gpt-4o-mini-tts-2025-12-15", "kind": "SPEECH", "modalities": { "input": [ "audio", "text" ], "output": [ "audio" ] }, "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", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "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": "2026-07-22", "vendor": "openai" }, { "id": "gpt-realtime-translate", "label": "gpt-realtime-translate", "kind": "SPEECH", "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "tts-1", "label": "tts-1", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "tts-1-1106", "label": "tts-1-1106", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "tts-1-hd", "label": "tts-1-hd", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "tts-1-hd-1106", "label": "tts-1-hd-1106", "kind": "SPEECH", "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "sora-2", "label": "sora-2", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "sora-2-pro", "label": "sora-2-pro", "kind": "VIDEO", "modalities": { "input": [ "image", "text" ], "output": [ "video" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "omni-moderation-2024-09-26", "label": "omni-moderation-2024-09-26", "kind": "MODERATION", "contextWindow": 32768, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" }, { "id": "omni-moderation-latest", "label": "omni-moderation-latest", "kind": "MODERATION", "contextWindow": 32768, "modalities": { "input": [ "text" ] }, "sources": [ "committed", "openai-api" ], "lastVerified": "2026-07-22", "vendor": "openai" } ], "openrouter": [ { "id": "anthropic/claude-3-haiku", "label": "Claude 3 Haiku (via OpenRouter)", "kind": "CHAT", "contextWindow": 200000, "maxOutputTokens": 4096, "capabilities": [ "tools", "vision" ], "modalities": { "input": [ "image", "text" ] }, "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "openrouter" }, { "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", "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", "overrides" ], "lastVerified": "2026-07-22", "vendor": "openrouter" }, { "id": "deepseek/deepseek-chat", "label": "DeepSeek Chat (via OpenRouter)", "kind": "CHAT", "contextWindow": 65536, "maxOutputTokens": 8192, "modalities": { "input": [ "text" ] }, "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", "overrides" ], "lastVerified": "2026-07-22", "vendor": "openrouter" }, { "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": "2026-07-22", "vendor": "openrouter" }, { "id": "meta-llama/llama-3-70b-instruct", "label": "Llama 3 70B Instruct (via OpenRouter)", "kind": "CHAT", "contextWindow": 8192, "maxOutputTokens": 8000, "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" }, "benchmarks": { "intelligenceIndex": 3.5, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "performance": { "throughputTps": 44.571, "latencyTtftSec": 0.614, "indicative": true, "note": "Cited third-party benchmark — verify at the source.", "source": "Artificial Analysis", "lastVerified": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "overrides" ], "lastVerified": "2026-07-22", "vendor": "openrouter" }, { "id": "openai/gpt-4o", "label": "GPT-4o (via OpenRouter)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 4096, "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": "2026-07-22", "vendor": "openrouter" } ], "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": "2026-07-22", "vendor": "qwen" }, { "id": "qwen-flash", "label": "Qwen-Flash", "kind": "CHAT", "contextWindow": 997952, "maxOutputTokens": 32768, "capabilities": [ "tools", "reasoning" ], "modalities": { "input": [ "text" ] }, "sources": [ "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "qwen" }, { "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": "2026-07-22", "vendor": "qwen" }, { "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": "2026-07-22", "vendor": "qwen" }, { "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": "2026-07-22" }, "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": "2026-07-22", "vendor": "qwen" } ], "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": "2026-07-22", "vendor": "together" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "together" }, { "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": "2026-07-22", "vendor": "together" }, { "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": "2026-07-22", "vendor": "together" }, { "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": "2026-07-22", "vendor": "together" }, { "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": "2026-07-22", "vendor": "together" } ], "vercel": [ { "id": "alibaba/qwen-3-235b", "label": "Qwen3 235B (via Vercel)", "kind": "CHAT", "contextWindow": 40960, "maxOutputTokens": 16384, "modalities": { "input": [ "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", "overrides" ], "lastVerified": "2026-07-22", "vendor": "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "vercel" }, { "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": "2026-07-22", "vendor": "vercel" }, { "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": "2026-07-22" }, "performance": { "throughputTps": 59.799, "latencyTtftSec": 0.41, "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": "2026-07-22", "vendor": "vercel" }, { "id": "deepseek/deepseek-r1", "label": "DeepSeek-R1 (via Vercel)", "kind": "CHAT", "contextWindow": 128000, "maxOutputTokens": 8192, "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", "overrides" ], "lastVerified": "2026-07-22", "vendor": "vercel" }, { "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": "2026-07-22", "vendor": "vercel" } ], "vertex-ai": [ { "id": "gemini-1.5-pro", "label": "Gemini 1.5 Pro", "kind": "CHAT", "contextWindow": 2097152, "capabilities": [ "vision", "tools" ], "sources": [ "committed" ], "lastVerified": "2026-07-22", "vendor": "vertex-ai" }, { "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": "2026-07-22", "vendor": "vertex-ai" }, { "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": "2026-07-22", "vendor": "vertex-ai" }, { "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": "2026-07-22", "vendor": "vertex-ai" }, { "id": "text-embedding-005", "label": "text-embedding-005", "kind": "EMBEDDING", "contextWindow": 2048, "embeddingDimensions": 768, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 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" ], "lastVerified": "2026-07-22", "vendor": "vertex-ai" } ], "voyage": [ { "id": "voyage-3", "label": "voyage-3", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.06, "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": "2026-07-22", "vendor": "voyage" }, { "id": "voyage-3-large", "label": "voyage-3-large", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 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" ], "lastVerified": "2026-07-22", "vendor": "voyage" }, { "id": "voyage-3-lite", "label": "voyage-3-lite", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 512, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.02, "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": "2026-07-22", "vendor": "voyage" }, { "id": "voyage-code-3", "label": "voyage-code-3", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 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" ], "lastVerified": "2026-07-22", "vendor": "voyage" }, { "id": "voyage-multimodal-3", "label": "voyage-multimodal-3", "kind": "EMBEDDING", "contextWindow": 32000, "embeddingDimensions": 1024, "capabilities": [ "multimodal" ], "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "pricing": { "inputPer1M": 0.12, "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": "2026-07-22", "vendor": "voyage" }, { "id": "rerank-2", "label": "rerank-2", "kind": "RERANK", "contextWindow": 16000, "maxOutputTokens": 16000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.05, "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": "2026-07-22", "vendor": "voyage" }, { "id": "rerank-2-lite", "label": "rerank-2-lite", "kind": "RERANK", "contextWindow": 8000, "maxOutputTokens": 8000, "modalities": { "input": [ "text" ] }, "pricing": { "inputPer1M": 0.02, "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": "2026-07-22", "vendor": "voyage" } ], "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "xai" }, { "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": "2026-07-22", "vendor": "xai" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "xai" }, { "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "xai" } ], "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": "2026-07-22" }, "sources": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "zai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "zai" }, { "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": "2026-07-22" }, "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": [ "artificial-analysis", "committed", "litellm", "overrides" ], "lastVerified": "2026-07-22", "vendor": "zai" } ] } }