{ "schemaVersion": "1.0", "name": "BenchLM pricing", "description": "Model API pricing with linked BenchLM score and value fields when available.", "canonicalUrl": "https://benchlm.ai/data/pricing.json", "generatedAt": "2026-06-12T20:35:11.146Z", "sourceLastUpdated": "June 12, 2026", "sourceFiles": [ "src/data/pricing.json", "src/data/pricingSupplemental.js" ], "counts": { "pricedRows": 212, "numericPricingRows": 184 }, "items": [ { "canonicalModelKey": "bonsai-1-7b", "slug": "bonsai-1-7b", "model": "1-bit Bonsai 1.7B", "creator": "Prism ML", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 24, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/bonsai-1-7b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-1-7b.md" }, { "canonicalModelKey": "bonsai-4b", "slug": "bonsai-4b", "model": "1-bit Bonsai 4B", "creator": "Prism ML", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 17, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/bonsai-4b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-4b.md" }, { "canonicalModelKey": "bonsai-8b", "slug": "bonsai-8b", "model": "1-bit Bonsai 8B", "creator": "Prism ML", "sourceType": "Open Weight", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 23, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-8b.md" }, { "canonicalModelKey": "aion-2-0", "slug": "aion-2-0", "model": "Aion-2.0", "creator": "Aion Labs", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.8, "outputPrice": 1.6, "cachedInputPrice": null, "trainingPrice": null, "note": "Aion Labs' official API reference lists Aion-2.0 pricing at 0.0000008 prompt tokens and 0.0000016 completion tokens, equivalent to $0.80 input / $1.60 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 5, "overallRank": null, "scorePerOutputDollar": 3.125, "url": "https://benchlm.ai/models/aion-2-0", "markdownUrl": "https://benchlm.ai/md/models/aion-2-0.md" }, { "canonicalModelKey": "claude-3-haiku", "slug": "claude-3-haiku", "model": "Claude 3 Haiku", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 0.25, "outputPrice": 1.25, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's pricing docs list Claude Haiku 3 at $0.25 input / $1.25 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 23, "overallRank": 111, "scorePerOutputDollar": 18.4, "url": "https://benchlm.ai/models/claude-3-haiku", "markdownUrl": "https://benchlm.ai/md/models/claude-3-haiku.md" }, { "canonicalModelKey": "claude-3-opus", "slug": "claude-3-opus", "model": "Claude 3 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 15, "outputPrice": 75, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's pricing docs list Claude Opus 3 at $15 input / $75 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 34, "overallRank": 92, "scorePerOutputDollar": 0.453, "url": "https://benchlm.ai/models/claude-3-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-3-opus.md" }, { "canonicalModelKey": "claude-3-5-sonnet", "slug": "claude-3-5-sonnet", "model": "Claude 3.5 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 3, "outputPrice": 15, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's pricing docs list Claude Sonnet 3.5 at $3 input / $15 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 40, "overallRank": 84, "scorePerOutputDollar": 2.667, "url": "https://benchlm.ai/models/claude-3-5-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-3-5-sonnet.md" }, { "canonicalModelKey": "claude-4-sonnet", "slug": "claude-4-sonnet", "model": "Claude 4 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 3, "outputPrice": 15, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's pricing docs list Claude Sonnet 4 at $3 input / $15 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 50, "overallRank": 70, "scorePerOutputDollar": 3.333, "url": "https://benchlm.ai/models/claude-4-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-4-sonnet.md" }, { "canonicalModelKey": "claude-4-1-opus", "slug": "claude-4-1-opus", "model": "Claude 4.1 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 15, "outputPrice": 75, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's pricing docs list Claude Opus 4.1 at $15 input / $75 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 51, "overallRank": 67, "scorePerOutputDollar": 0.68, "url": "https://benchlm.ai/models/claude-4-1-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus.md" }, { "canonicalModelKey": "claude-4-1-opus-thinking", "slug": "claude-4-1-opus-thinking", "model": "Claude 4.1 Opus Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic documents extended thinking for Opus 4.1, but does not publish a separate priced `claude-4-1-opus-thinking` SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 43, "overallRank": 80, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/claude-4-1-opus-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus-thinking.md" }, { "canonicalModelKey": "claude-fable-5", "slug": "claude-fable", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M+", "contextWindowTokens": 1000000, "inputPrice": 10, "outputPrice": 50, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's June 9, 2026 Claude Fable 5 model page says Claude Fable 5 is available through the Claude API as `claude-fable-5` at $10 input / $50 output per million tokens, with a 90% input-token discount for prompt caching. US-only inference is available at 1.1x pricing.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 97, "overallRank": 2, "scorePerOutputDollar": 1.94, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, { "canonicalModelKey": "claude-haiku-4-5", "slug": "claude-haiku-4-5", "model": "Claude Haiku 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1, "outputPrice": 5, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic official public pricing for Claude Haiku 4.5 as referenced by Anthropic's April 2026 model pages.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 56, "overallRank": 60, "scorePerOutputDollar": 11.2, "url": "https://benchlm.ai/models/claude-haiku-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5.md" }, { "canonicalModelKey": "claude-mythos-5", "slug": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M+", "contextWindowTokens": 1000000, "inputPrice": 10, "outputPrice": 50, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's June 9, 2026 Claude Fable 5 and Claude Mythos 5 launch says both models are offered at $10 input / $50 output per million tokens. Mythos 5 is restricted to Glasswing partners and trusted access programs.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 99, "overallRank": 1, "scorePerOutputDollar": 1.98, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, { "canonicalModelKey": "claude-opus-4-5", "slug": "claude-opus-4-5", "model": "Claude Opus 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 5, "outputPrice": 25, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's Claude Opus 4.5 launch page lists Opus 4.5 at $5 input / $25 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 76, "overallRank": 28, "scorePerOutputDollar": 3.04, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md" }, { "canonicalModelKey": "claude-opus-4-6", "slug": "claude-opus-4-6", "model": "Claude Opus 4.6", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 25, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic public pricing updated for the current Opus tier; Anthropic's April 16, 2026 Claude Opus 4.7 announcement says pricing remains the same as Opus 4.6 at $5/$25 per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 86, "overallRank": 12, "scorePerOutputDollar": 3.44, "url": "https://benchlm.ai/models/claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6.md" }, { "canonicalModelKey": "claude-opus-4-7", "slug": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 25, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic official pricing from the Claude Opus 4.7 announcement dated April 16, 2026. Anthropic states pricing remains the same as Opus 4.6: $5 input / $25 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 23, "overallRank": null, "scorePerOutputDollar": 0.92, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, { "canonicalModelKey": "claude-opus-4-7-max", "slug": "claude-opus-4-7-adaptive", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 25, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic official pricing for Claude Opus 4.7 applies to the adaptive reasoning variant as the same API model with effort controls; launch announcement states pricing remains $5 input / $25 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 84, "overallRank": 16, "scorePerOutputDollar": 3.36, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, { "canonicalModelKey": "claude-opus-4-8", "slug": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 25, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's May 28, 2026 Claude Opus 4.8 launch announcement says Opus 4.8 is available at the same price as Opus 4.7. BenchLM maps that to the current Opus API rate of $5 input / $25 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 93, "overallRank": 3, "scorePerOutputDollar": 3.72, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, { "canonicalModelKey": "claude-sonnet-4-5", "slug": "claude-sonnet-4-5", "model": "Claude Sonnet 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 3, "outputPrice": 15, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's Claude Sonnet 4.6 announcement says pricing remains the same as Sonnet 4.5 at $3 input / $15 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 64, "overallRank": 46, "scorePerOutputDollar": 4.267, "url": "https://benchlm.ai/models/claude-sonnet-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5.md" }, { "canonicalModelKey": "claude-sonnet-4-6", "slug": "claude-sonnet-4-6", "model": "Claude Sonnet 4.6", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 3, "outputPrice": 15, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's Claude Sonnet 4.6 announcement says pricing remains the same as Sonnet 4.5 at $3 input / $15 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 82, "overallRank": 18, "scorePerOutputDollar": 5.467, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md" }, { "canonicalModelKey": "command-a-plus", "slug": "command-a-plus", "model": "Command A+", "creator": "Cohere", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 2.5, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "Cohere's current public docs list the `command-a-plus-05-2026` generative model at $2.50 input / $10.00 output per million tokens. Cohere's May 20, 2026 launch post and model card establish the exact Command A+ context as 128K input with 64K max generation; self-hosted or private deployment costs vary by infrastructure.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 39, "overallRank": null, "scorePerOutputDollar": 3.9, "url": "https://benchlm.ai/models/command-a-plus", "markdownUrl": "https://benchlm.ai/md/models/command-a-plus.md" }, { "canonicalModelKey": "composer-2", "slug": "composer-2", "model": "Composer 2", "creator": "Cursor", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 0.5, "outputPrice": 2.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Cursor's official Composer 2 API pricing. Cursor also documents a faster in-product variant at $1.50/$7.50 per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 73, "overallRank": null, "scorePerOutputDollar": 29.2, "url": "https://benchlm.ai/models/composer-2", "markdownUrl": "https://benchlm.ai/md/models/composer-2.md" }, { "canonicalModelKey": "composer-2-5", "slug": "composer-2-5", "model": "Composer 2.5", "creator": "Cursor", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 0.5, "outputPrice": 2.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Cursor's official Composer 2.5 docs list the standard tier at $0.50/$2.50 per million tokens and document a faster in-product variant with the same intelligence at $3/$15 per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 81, "overallRank": null, "scorePerOutputDollar": 32.4, "url": "https://benchlm.ai/models/composer-2-5", "markdownUrl": "https://benchlm.ai/md/models/composer-2-5.md" }, { "canonicalModelKey": "dbrx-instruct", "slug": "dbrx-instruct", "model": "DBRX Instruct", "creator": "Databricks", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted cost varies", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 32, "overallRank": 96, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/dbrx-instruct", "markdownUrl": "https://benchlm.ai/md/models/dbrx-instruct.md" }, { "canonicalModelKey": "deepseek-coder-2-0", "slug": "deepseek-coder-2-0", "model": "DeepSeek Coder 2.0", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek's current public API pricing pages price `deepseek-chat` and `deepseek-reasoner`, but do not publish a current standalone token rate for the exact DeepSeek Coder 2.0 SKU. BenchLM treats hosted pricing as unavailable for this exact row.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 51, "overallRank": 66, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-coder-2-0", "markdownUrl": "https://benchlm.ai/md/models/deepseek-coder-2-0.md" }, { "canonicalModelKey": "deepseek-llm-2-0", "slug": "deepseek-llm-2-0", "model": "DeepSeek LLM 2.0", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 50, "overallRank": 68, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-llm-2-0", "markdownUrl": "https://benchlm.ai/md/models/deepseek-llm-2-0.md" }, { "canonicalModelKey": "deepseek-r1", "slug": "deepseek-r1", "model": "DeepSeek R1", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.55, "outputPrice": 2.19, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek's official DeepSeek-R1 release page lists $0.55 input (cache miss) / $2.19 output per million tokens, with cache-hit input at $0.14.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 32, "overallRank": 94, "scorePerOutputDollar": 14.612, "url": "https://benchlm.ai/models/deepseek-r1", "markdownUrl": "https://benchlm.ai/md/models/deepseek-r1.md" }, { "canonicalModelKey": "deepseek-r1-distill-qwen-32b", "slug": "deepseek-r1-distill-qwen-32b", "model": "DeepSeek R1 Distill Qwen 32B", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted distilled open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 6, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-r1-distill-qwen-32b", "markdownUrl": "https://benchlm.ai/md/models/deepseek-r1-distill-qwen-32b.md" }, { "canonicalModelKey": "deepseek-v3", "slug": "deepseek-v3", "model": "DeepSeek V3", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.27, "outputPrice": 1.1, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek's official DeepSeek-V3 launch page lists $0.27 input (cache miss) / $1.10 output per million tokens, with cache-hit input at $0.07.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 34, "overallRank": 90, "scorePerOutputDollar": 30.909, "url": "https://benchlm.ai/models/deepseek-v3", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3.md" }, { "canonicalModelKey": "deepseek-v3-1", "slug": "deepseek-v3-1", "model": "DeepSeek V3.1", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 24, "overallRank": 106, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-v3-1", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-1.md" }, { "canonicalModelKey": "deepseek-v3-1-reasoning", "slug": "deepseek-v3-1-reasoning", "model": "DeepSeek V3.1 (Reasoning)", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 29, "overallRank": 98, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-v3-1-reasoning", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-1-reasoning.md" }, { "canonicalModelKey": "deepseek-v3-2", "slug": "deepseek-v3-2", "model": "DeepSeek V3.2", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.28, "outputPrice": 0.42, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek's current pricing page lists `deepseek-chat` as DeepSeek-V3.2 (non-thinking mode) at $0.28 input (cache miss) / $0.42 output per million tokens, with cache-hit input at $0.028.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 56, "overallRank": 59, "scorePerOutputDollar": 133.333, "url": "https://benchlm.ai/models/deepseek-v3-2", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2.md" }, { "canonicalModelKey": "deepseek-v3-2-thinking", "slug": "deepseek-v3-2-thinking", "model": "DeepSeek V3.2 (Thinking)", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.55, "outputPrice": 2.19, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek's current pricing page lists `deepseek-reasoner` as the hosted DeepSeek-V3.2 thinking-mode endpoint at $0.55 input (cache miss) / $2.19 output per million tokens, with cache-hit input at $0.14.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 60, "overallRank": 53, "scorePerOutputDollar": 27.397, "url": "https://benchlm.ai/models/deepseek-v3-2-thinking", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2-thinking.md" }, { "canonicalModelKey": "deepseek-v4-flash", "slug": "deepseek-v4-flash", "model": "DeepSeek V4 Flash", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.14, "outputPrice": 0.28, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek lists `deepseek-v4-flash` at $0.14 input (cache miss) / $0.28 output per million tokens, with cache-hit input at $0.028.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 57, "overallRank": 55, "scorePerOutputDollar": 203.571, "url": "https://benchlm.ai/models/deepseek-v4-flash", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash.md" }, { "canonicalModelKey": "deepseek-v4-flash-high", "slug": "deepseek-v4-flash-high", "model": "DeepSeek V4 Flash (High)", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.14, "outputPrice": 0.28, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek Table 7 reports this as the High reasoning-effort mode of DeepSeek V4 Flash. First-party token pricing is inherited from `deepseek-v4-flash`: $0.14 input (cache miss) / $0.28 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 71, "overallRank": 36, "scorePerOutputDollar": 253.571, "url": "https://benchlm.ai/models/deepseek-v4-flash-high", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-high.md" }, { "canonicalModelKey": "deepseek-v4-flash-max", "slug": "deepseek-v4-flash-max", "model": "DeepSeek V4 Flash (Max)", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.14, "outputPrice": 0.28, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek Table 7 reports this as the Max reasoning-effort mode of DeepSeek V4 Flash. First-party token pricing is inherited from `deepseek-v4-flash`: $0.14 input (cache miss) / $0.28 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 74, "overallRank": 33, "scorePerOutputDollar": 264.286, "url": "https://benchlm.ai/models/deepseek-v4-flash-max", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-max.md" }, { "canonicalModelKey": "deepseek-v4-flash-base", "slug": "deepseek-v4-flash-base", "model": "DeepSeek V4 Flash Base", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek publishes open weights for DeepSeek V4 Flash Base, but first-party API pricing is published for post-trained `deepseek-v4-flash` rather than this exact Base SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 29, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-v4-flash-base", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-base.md" }, { "canonicalModelKey": "deepseek-v4-pro", "slug": "deepseek-v4-pro", "model": "DeepSeek V4 Pro", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.74, "outputPrice": 3.48, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek lists `deepseek-v4-pro` at $1.74 input (cache miss) / $3.48 output per million tokens, with cache-hit input at $0.145.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 68, "overallRank": 39, "scorePerOutputDollar": 19.54, "url": "https://benchlm.ai/models/deepseek-v4-pro", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro.md" }, { "canonicalModelKey": "deepseek-v4-pro-high", "slug": "deepseek-v4-pro-high", "model": "DeepSeek V4 Pro (High)", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.74, "outputPrice": 3.48, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek Table 7 reports this as the High reasoning-effort mode of DeepSeek V4 Pro. First-party token pricing is inherited from `deepseek-v4-pro`: $1.74 input (cache miss) / $3.48 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 82, "overallRank": 19, "scorePerOutputDollar": 23.563, "url": "https://benchlm.ai/models/deepseek-v4-pro-high", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-high.md" }, { "canonicalModelKey": "deepseek-v4-pro-max", "slug": "deepseek-v4-pro-max", "model": "DeepSeek V4 Pro (Max)", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.74, "outputPrice": 3.48, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek Table 7 reports this as the Max reasoning-effort mode of DeepSeek V4 Pro. First-party token pricing is inherited from `deepseek-v4-pro`: $1.74 input (cache miss) / $3.48 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 86, "overallRank": 14, "scorePerOutputDollar": 24.713, "url": "https://benchlm.ai/models/deepseek-v4-pro-max", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-max.md" }, { "canonicalModelKey": "deepseek-v4-pro-base", "slug": "deepseek-v4-pro-base", "model": "DeepSeek V4 Pro Base", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepSeek publishes open weights for DeepSeek V4 Pro Base, but first-party API pricing is published for post-trained `deepseek-v4-pro` rather than this exact Base SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 41, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-v4-pro-base", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-base.md" }, { "canonicalModelKey": "deepseekmath-v2", "slug": "deepseekmath-v2", "model": "DeepSeekMath V2", "creator": "DeepSeek", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 49, "overallRank": 73, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseekmath-v2", "markdownUrl": "https://benchlm.ai/md/models/deepseekmath-v2.md" }, { "canonicalModelKey": "gemini-1-0-pro", "slug": "gemini-1-0-pro", "model": "Gemini 1.0 Pro", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's current first-party docs show Gemini 1.0 Pro is no longer supported, and we did not find a current public token-pricing row for the exact model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 24, "overallRank": 108, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemini-1-0-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-0-pro.md" }, { "canonicalModelKey": "gemini-1-5-pro", "slug": "gemini-1-5-pro", "model": "Gemini 1.5 Pro", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.25, "outputPrice": 5, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's Gemini pricing docs list Gemini 1.5 Pro at $1.25 input / $5.00 output per million tokens for prompts up to 128K tokens, rising to $2.50 / $10.00 above 128K.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 35, "overallRank": 89, "scorePerOutputDollar": 7, "url": "https://benchlm.ai/models/gemini-1-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-5-pro.md" }, { "canonicalModelKey": "gemini-2-5-flash", "slug": "gemini-2-5-flash", "model": "Gemini 2.5 Flash", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.3, "outputPrice": 2.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists Gemini 2.5 Flash Standard pricing at $0.30 input / $2.50 output per million tokens for text, image, and video; Batch pricing is lower.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 37, "overallRank": 88, "scorePerOutputDollar": 14.8, "url": "https://benchlm.ai/models/gemini-2-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash.md" }, { "canonicalModelKey": "gemini-2-5-pro", "slug": "gemini-2-5-pro", "model": "Gemini 2.5 Pro", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.25, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists Gemini 2.5 Pro Standard pricing at $1.25 input / $10.00 output per million tokens for prompts up to 200K tokens, rising to $2.50 / $15.00 above 200K. Batch and Flex pricing are lower.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 63, "overallRank": 49, "scorePerOutputDollar": 6.3, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md" }, { "canonicalModelKey": "gemini-3-flash", "slug": "gemini-3-flash", "model": "Gemini 3 Flash", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.5, "outputPrice": 3, "cachedInputPrice": null, "trainingPrice": null, "note": "Official Google Gemini API rate for Gemini 3 Flash.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 55, "overallRank": 63, "scorePerOutputDollar": 18.333, "url": "https://benchlm.ai/models/gemini-3-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-flash.md" }, { "canonicalModelKey": "gemini-3-pro", "slug": "gemini-3-pro", "model": "Gemini 3 Pro", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "2M", "contextWindowTokens": 2000000, "inputPrice": 2, "outputPrice": 12, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists Gemini 3 Pro Preview at $2.00 input / $12.00 output per million tokens for prompts up to 200K tokens, rising to $4.00 / $18.00 above 200K.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 80, "overallRank": 22, "scorePerOutputDollar": 6.667, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md" }, { "canonicalModelKey": "gemini-3-pro-deep-think", "slug": "gemini-3-pro-deep-think", "model": "Gemini 3 Pro Deep Think", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "2M", "contextWindowTokens": 2000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Google prices `gemini-3-pro-preview`, but we did not find a separate first-party public price row for the exact Gemini 3 Pro Deep Think SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 89, "overallRank": 8, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemini-3-pro-deep-think", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro-deep-think.md" }, { "canonicalModelKey": "gemini-3-1-flash-lite", "slug": "gemini-3-1-flash-lite", "model": "Gemini 3.1 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.25, "outputPrice": 1.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists Gemini 3.1 Flash-Lite Preview at $0.25 input / $1.50 output per million tokens for text, image, and video inputs in Standard mode.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 47, "overallRank": 75, "scorePerOutputDollar": 31.333, "url": "https://benchlm.ai/models/gemini-3-1-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-lite.md" }, { "canonicalModelKey": "gemini-3-1-pro", "slug": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 2, "outputPrice": 12, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists Gemini 3.1 Pro Preview at $2.00 input / $12.00 output per million tokens for prompts up to 200K tokens, rising to $4.00 / $18.00 above 200K.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 91, "overallRank": 4, "scorePerOutputDollar": 7.583, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, { "canonicalModelKey": "gemini-3-5-flash", "slug": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.5, "outputPrice": 9, "cachedInputPrice": null, "trainingPrice": null, "note": "Artificial Analysis' May 19, 2026 Gemini 3.5 Flash model page lists Google's API at $1.50 input / $9.00 output per million tokens, with $0.15/M cache-hit pricing.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 86, "overallRank": 13, "scorePerOutputDollar": 9.556, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, { "canonicalModelKey": "gemma-3-27b", "slug": "gemma-3-27b", "model": "Gemma 3 27B", "creator": "Google", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 16, "overallRank": 118, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemma-3-27b", "markdownUrl": "https://benchlm.ai/md/models/gemma-3-27b.md" }, { "canonicalModelKey": "gemma-4-26b-a4b", "slug": "gemma-4-26b-a4b", "model": "Gemma 4 26B A4B", "creator": "Google", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 54, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemma-4-26b-a4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-26b-a4b.md" }, { "canonicalModelKey": "gemma-4-31b", "slug": "gemma-4-31b", "model": "Gemma 4 31B", "creator": "Google", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 64, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md" }, { "canonicalModelKey": "gemma-4-e2b", "slug": "gemma-4-e2b", "model": "Gemma 4 E2B", "creator": "Google", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 24, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemma-4-e2b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e2b.md" }, { "canonicalModelKey": "gemma-4-e4b", "slug": "gemma-4-e4b", "model": "Gemma 4 E4B", "creator": "Google", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 37, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemma-4-e4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e4b.md" }, { "canonicalModelKey": "glm-4-5", "slug": "glm-4-5", "model": "GLM-4.5", "creator": "Z.AI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.6, "outputPrice": 2.2, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI's official pricing page lists GLM-4.5 at $0.60 input / $2.20 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 25, "overallRank": 102, "scorePerOutputDollar": 11.364, "url": "https://benchlm.ai/models/glm-4-5", "markdownUrl": "https://benchlm.ai/md/models/glm-4-5.md" }, { "canonicalModelKey": "glm-4-5-air", "slug": "glm-4-5-air", "model": "GLM-4.5-Air", "creator": "Z.AI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.2, "outputPrice": 1.1, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI's official pricing page lists GLM-4.5-Air at $0.20 input / $1.10 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 18, "overallRank": 116, "scorePerOutputDollar": 16.364, "url": "https://benchlm.ai/models/glm-4-5-air", "markdownUrl": "https://benchlm.ai/md/models/glm-4-5-air.md" }, { "canonicalModelKey": "glm-4-7", "slug": "glm-4-7", "model": "GLM-4.7", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 68, "overallRank": 40, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-4-7", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7.md" }, { "canonicalModelKey": "glm-4-7-flash", "slug": "glm-4-7-flash", "model": "GLM-4.7-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 11, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-4-7-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7-flash.md" }, { "canonicalModelKey": "glm-5", "slug": "glm-5", "model": "GLM-5", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1, "outputPrice": 3.2, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI's official pricing page lists GLM-5 at $1.00 input / $3.20 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 67, "overallRank": 42, "scorePerOutputDollar": 20.938, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md" }, { "canonicalModelKey": "glm-5-reasoning", "slug": "glm-5-reasoning", "model": "GLM-5 (Reasoning)", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1, "outputPrice": 3.2, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI's model docs say GLM-5 supports thinking modes, and the official pricing page lists GLM-5 at $1.00 input / $3.20 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 79, "overallRank": 24, "scorePerOutputDollar": 24.688, "url": "https://benchlm.ai/models/glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/glm-5-reasoning.md" }, { "canonicalModelKey": "glm-5-turbo", "slug": "glm-5-turbo", "model": "GLM-5-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1.2, "outputPrice": 4, "cachedInputPrice": null, "trainingPrice": null, "note": "Official Z.AI pricing for GLM-5-Turbo. Benchmarks are tracked separately and currently coming soon.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 20, "overallRank": null, "scorePerOutputDollar": 5, "url": "https://benchlm.ai/models/glm-5-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5-turbo.md" }, { "canonicalModelKey": "glm-5-1", "slug": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "203K", "contextWindowTokens": 203000, "inputPrice": 1.4, "outputPrice": 4.4, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI's official pricing page lists GLM-5.1 at $1.40 input / $4.40 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 82, "overallRank": 17, "scorePerOutputDollar": 18.636, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, { "canonicalModelKey": "glm-5v-turbo", "slug": "glm-5v-turbo", "model": "GLM-5V-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1.2, "outputPrice": 4, "cachedInputPrice": null, "trainingPrice": null, "note": "Official Z.AI pricing for GLM-5V-Turbo from the April 1, 2026 pricing page. The model docs list video, image, text, and file inputs with a 128K max output window.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 62, "overallRank": null, "scorePerOutputDollar": 15.5, "url": "https://benchlm.ai/models/glm-5v-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5v-turbo.md" }, { "canonicalModelKey": "gpt-4-turbo", "slug": "gpt-4-turbo", "model": "GPT-4 Turbo", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 10, "outputPrice": 30, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-4 Turbo model page lists $10.00 input / $30.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 24, "overallRank": 107, "scorePerOutputDollar": 0.8, "url": "https://benchlm.ai/models/gpt-4-turbo", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-turbo.md" }, { "canonicalModelKey": "gpt-4-1", "slug": "gpt-4-1", "model": "GPT-4.1", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 2, "outputPrice": 8, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-4.1 model page lists $2.00 input / $8.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 57, "overallRank": 56, "scorePerOutputDollar": 7.125, "url": "https://benchlm.ai/models/gpt-4-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1.md" }, { "canonicalModelKey": "gpt-4-1-mini", "slug": "gpt-4-1-mini", "model": "GPT-4.1 mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.4, "outputPrice": 1.6, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-4.1 mini model page lists $0.40 input / $1.60 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 45, "overallRank": 77, "scorePerOutputDollar": 28.125, "url": "https://benchlm.ai/models/gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-mini.md" }, { "canonicalModelKey": "gpt-4-1-nano", "slug": "gpt-4-1-nano", "model": "GPT-4.1 nano", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.1, "outputPrice": 0.4, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-4.1 nano model page lists $0.10 input / $0.40 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 27, "overallRank": 101, "scorePerOutputDollar": 67.5, "url": "https://benchlm.ai/models/gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-nano.md" }, { "canonicalModelKey": "gpt-4o", "slug": "gpt-4o", "model": "GPT-4o", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 2.5, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-4o model page lists $2.50 input / $10.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 42, "overallRank": 81, "scorePerOutputDollar": 4.2, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md" }, { "canonicalModelKey": "gpt-4o-mini", "slug": "gpt-4o-mini", "model": "GPT-4o mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.15, "outputPrice": 0.6, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-4o mini model page lists $0.15 input / $0.60 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 49, "overallRank": 71, "scorePerOutputDollar": 81.667, "url": "https://benchlm.ai/models/gpt-4o-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini.md" }, { "canonicalModelKey": "gpt-5-high", "slug": "gpt-5-high", "model": "GPT-5 (high)", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.25, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5 model page lists GPT-5 at $1.25 input / $10.00 output per million tokens; the benchmark row uses the same GPT-5 model with high reasoning effort.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 76, "overallRank": 29, "scorePerOutputDollar": 7.6, "url": "https://benchlm.ai/models/gpt-5-high", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-high.md" }, { "canonicalModelKey": "gpt-5-medium", "slug": "gpt-5-medium", "model": "GPT-5 (medium)", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's first-party materials discuss GPT-5 medium as a reasoning setting under GPT-5, but do not publish a standalone `gpt-5-medium` API model pricing row.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 70, "overallRank": 37, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-5-medium", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-medium.md" }, { "canonicalModelKey": "gpt-5-mini", "slug": "gpt-5-mini", "model": "GPT-5 mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.25, "outputPrice": 2, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's pricing page lists GPT-5 mini at $0.25 input / $2.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/gpt-5-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-mini.md" }, { "canonicalModelKey": "gpt-5-nano", "slug": "gpt-5-nano", "model": "GPT-5 nano", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 0.05, "outputPrice": 0.4, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5 nano model page lists $0.05 input / $0.40 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/gpt-5-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-nano.md" }, { "canonicalModelKey": "gpt-5-1", "slug": "gpt-5-1", "model": "GPT-5.1", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.25, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.1 model page lists GPT-5.1 at $1.25 input / $10.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 77, "overallRank": 27, "scorePerOutputDollar": 7.7, "url": "https://benchlm.ai/models/gpt-5-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1.md" }, { "canonicalModelKey": "gpt-5-1-codex-max", "slug": "gpt-5-1-codex-max", "model": "GPT-5.1-Codex-Max", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.25, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.1-Codex-Max model page lists GPT-5.1-Codex-Max at $1.25 input / $10.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 75, "overallRank": 32, "scorePerOutputDollar": 7.5, "url": "https://benchlm.ai/models/gpt-5-1-codex-max", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex-max.md" }, { "canonicalModelKey": "gpt-5-2", "slug": "gpt-5-2", "model": "GPT-5.2", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.75, "outputPrice": 14, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.2 model page lists GPT-5.2 at $1.75 input / $14.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 78, "overallRank": 25, "scorePerOutputDollar": 5.571, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md" }, { "canonicalModelKey": "gpt-5-2-instant", "slug": "gpt-5-2-instant", "model": "GPT-5.2 Instant", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 1.5, "outputPrice": 6, "cachedInputPrice": null, "trainingPrice": null, "note": "Derived from the GPT-5.2 family pricing tier for the instant variant.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 19, "overallRank": null, "scorePerOutputDollar": 3.167, "url": "https://benchlm.ai/models/gpt-5-2-instant", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-instant.md" }, { "canonicalModelKey": "gpt-5-2-pro", "slug": "gpt-5-2-pro", "model": "GPT-5.2 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 25, "outputPrice": 150, "cachedInputPrice": null, "trainingPrice": null, "note": "Derived from the GPT-5.2 family premium pricing tier for the pro variant.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 19, "overallRank": null, "scorePerOutputDollar": 0.127, "url": "https://benchlm.ai/models/gpt-5-2-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-pro.md" }, { "canonicalModelKey": "gpt-5-2-codex", "slug": "gpt-5-2-codex", "model": "GPT-5.2-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.75, "outputPrice": 14, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.2-Codex model page lists GPT-5.2-Codex at $1.75 input / $14.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 76, "overallRank": 30, "scorePerOutputDollar": 5.429, "url": "https://benchlm.ai/models/gpt-5-2-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-codex.md" }, { "canonicalModelKey": "gpt-5-3-codex", "slug": "gpt-5-3-codex", "model": "GPT-5.3 Codex", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.75, "outputPrice": 14, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.3-Codex model page lists GPT-5.3-Codex at $1.75 input / $14.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 85, "overallRank": 15, "scorePerOutputDollar": 6.071, "url": "https://benchlm.ai/models/gpt-5-3-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex.md" }, { "canonicalModelKey": "gpt-5-3-instant", "slug": "gpt-5-3-instant", "model": "GPT-5.3 Instant", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 1.75, "outputPrice": 14, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.3 Chat model page lists the GPT-5.3 Instant snapshot at $1.75 input / $14.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 18, "overallRank": null, "scorePerOutputDollar": 1.286, "url": "https://benchlm.ai/models/gpt-5-3-instant", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-instant.md" }, { "canonicalModelKey": "gpt-5-3-codex-spark", "slug": "gpt-5-3-codex-spark", "model": "GPT-5.3-Codex-Spark", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's public model docs price GPT-5.3-Codex, but we did not find a current first-party pricing page that explicitly lists the GPT-5.3-Codex-Spark SKU. BenchLM treats pricing as unavailable until OpenAI publishes an exact rate.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 17, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-5-3-codex-spark", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex-spark.md" }, { "canonicalModelKey": "gpt-5-4", "slug": "gpt-5-4", "model": "GPT-5.4", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "inputPrice": 2.5, "outputPrice": 15, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.4 model page lists $2.50 input / $15.00 output per million tokens, with higher pricing for sessions over 272K input tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 88, "overallRank": 10, "scorePerOutputDollar": 5.867, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md" }, { "canonicalModelKey": "gpt-5-4-mini", "slug": "gpt-5-4-mini", "model": "GPT-5.4 mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 0.75, "outputPrice": 4.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Official OpenAI model page and launch pricing for GPT-5.4 mini.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 68, "overallRank": null, "scorePerOutputDollar": 15.111, "url": "https://benchlm.ai/models/gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-mini.md" }, { "canonicalModelKey": "gpt-5-4-nano", "slug": "gpt-5-4-nano", "model": "GPT-5.4 nano", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 0.2, "outputPrice": 1.25, "cachedInputPrice": null, "trainingPrice": null, "note": "Official OpenAI model page and launch pricing for GPT-5.4 nano.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 59, "overallRank": null, "scorePerOutputDollar": 47.2, "url": "https://benchlm.ai/models/gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-nano.md" }, { "canonicalModelKey": "gpt-5-4-pro", "slug": "gpt-5-4-pro", "model": "GPT-5.4 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "inputPrice": 30, "outputPrice": 180, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.4 Pro model page lists $30.00 input / $180.00 output per million tokens, with higher pricing for sessions over 272K input tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 90, "overallRank": 6, "scorePerOutputDollar": 0.5, "url": "https://benchlm.ai/models/gpt-5-4-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-pro.md" }, { "canonicalModelKey": "gpt-5-5", "slug": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 30, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.5 launch page says gpt-5.5 will come to the API at $5.00 input / $30.00 output per million tokens with a 1M context window. Batch and Flex are available at half the standard rate, and Priority is 2.5x the standard rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 89, "overallRank": 7, "scorePerOutputDollar": 2.967, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, { "canonicalModelKey": "gpt-5-5-pro", "slug": "gpt-5-5-pro", "model": "GPT-5.5 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 30, "outputPrice": 180, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.5 launch page says gpt-5.5-pro will come to the API at $30.00 input / $180.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 100, "overallRank": null, "scorePerOutputDollar": 0.556, "url": "https://benchlm.ai/models/gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5-pro.md" }, { "canonicalModelKey": "gpt-oss-120b", "slug": "gpt-oss-120b", "model": "GPT-OSS 120B", "creator": "OpenAI", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 34, "overallRank": 91, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-oss-120b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-120b.md" }, { "canonicalModelKey": "gpt-oss-20b", "slug": "gpt-oss-20b", "model": "GPT-OSS 20B", "creator": "OpenAI", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 16, "overallRank": 119, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-oss-20b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-20b.md" }, { "canonicalModelKey": "granite-4-0-1b", "slug": "granite-4-0-1b", "model": "Granite-4.0-1B", "creator": "IBM", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 32, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/granite-4-0-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-1b.md" }, { "canonicalModelKey": "granite-4-0-350m", "slug": "granite-4-0-350m", "model": "Granite-4.0-350M", "creator": "IBM", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/granite-4-0-350m", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-350m.md" }, { "canonicalModelKey": "granite-4-0-h-1b", "slug": "granite-4-0-h-1b", "model": "Granite-4.0-H-1B", "creator": "IBM", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 9, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/granite-4-0-h-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-1b.md" }, { "canonicalModelKey": "granite-4-0-h-350m", "slug": "granite-4-0-h-350m", "model": "Granite-4.0-H-350M", "creator": "IBM", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/granite-4-0-h-350m", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-350m.md" }, { "canonicalModelKey": "grok-3-beta", "slug": "grok-3-beta", "model": "Grok 3 [Beta]", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI's launch materials refer to `grok-beta`, but we did not find a first-party public token-pricing row for the exact `grok-3-beta` SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 30, "overallRank": 97, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-3-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-3-beta.md" }, { "canonicalModelKey": "grok-3-mini", "slug": "grok-3-mini", "model": "Grok 3 Mini", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.3, "outputPrice": 0.5, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI's models and pricing page lists grok-3-mini at $0.30 input / $0.50 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 41, "overallRank": null, "scorePerOutputDollar": 82, "url": "https://benchlm.ai/models/grok-3-mini", "markdownUrl": "https://benchlm.ai/md/models/grok-3-mini.md" }, { "canonicalModelKey": "grok-4", "slug": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI says Grok 4 is available via API, but the current first-party pricing pages do not expose a clean standalone token-pricing row for the exact `grok-4` alias.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 63, "overallRank": 50, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, { "canonicalModelKey": "grok-4-1", "slug": "grok-4-1", "model": "Grok 4.1", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI's current public API pricing pages list Grok 4.20 and Grok 4.1 Fast, but do not publish a current API rate for Grok 4.1. BenchLM treats Grok 4.1 pricing as unavailable until xAI posts an official price.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 89, "overallRank": 9, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-4-1", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1.md" }, { "canonicalModelKey": "grok-4-1-fast", "slug": "grok-4-1-fast", "model": "Grok 4.1 Fast", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "2M", "contextWindowTokens": 2000000, "inputPrice": 0.2, "outputPrice": 0.5, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI's public API pricing pages list grok-4-1-fast at $0.20 input / $0.50 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 68, "overallRank": 41, "scorePerOutputDollar": 136, "url": "https://benchlm.ai/models/grok-4-1-fast", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1-fast.md" }, { "canonicalModelKey": "grok-4-20-beta", "slug": "grok-4-20-beta", "model": "Grok 4.20", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "2M", "contextWindowTokens": 2000000, "inputPrice": 2, "outputPrice": 6, "cachedInputPrice": null, "trainingPrice": null, "note": "Official xAI docs pricing for grok-4.20-0309-reasoning. xAI's current model docs present this row as Grok 4.20. A non-reasoning variant also exists at the same token price.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 71, "overallRank": 35, "scorePerOutputDollar": 11.833, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md" }, { "canonicalModelKey": "grok-4-20-multi-agent-beta", "slug": "grok-4-20-multi-agent-beta", "model": "Grok 4.20 Multi-agent", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "2M", "contextWindowTokens": 2000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI documents Grok 4.20 Multi-agent as a public API model, but the current public pricing pages do not publish a clean standalone token rate for this exact SKU. BenchLM treats pricing as unavailable until xAI posts an explicit list price.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 70, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-4-20-multi-agent-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-multi-agent-beta.md" }, { "canonicalModelKey": "grok-4-3", "slug": "grok-4-3", "model": "Grok 4.3", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.25, "outputPrice": 2.5, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenRouter's live models API lists `x-ai/grok-4.3` at 0.00000125 prompt tokens and 0.0000025 completion tokens, equivalent to $1.25 input / $2.50 output per million tokens, with 1M context and text+image input. OpenRouter's model page also shows a >200K total-token tier at $2.50 input / $5.00 output per million tokens, with cache reads rising from $0.20/M to $0.40/M.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 74, "overallRank": null, "scorePerOutputDollar": 29.6, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md" }, { "canonicalModelKey": "grok-build-0-1", "slug": "grok-build-0-1", "model": "Grok Build 0.1", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 1, "outputPrice": 2, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenRouter's May 20, 2026 model page and live models API list `x-ai/grok-build-0.1` with a 256K context window, text+image input, text output, and 0.000001 prompt / 0.000002 completion token pricing, equivalent to $1.00 input / $2.00 output per million tokens. OpenRouter also lists cache reads at $0.20/M.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/grok-build-0-1", "markdownUrl": "https://benchlm.ai/md/models/grok-build-0-1.md" }, { "canonicalModelKey": "grok-code-fast-1", "slug": "grok-code-fast-1", "model": "Grok Code Fast 1", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.2, "outputPrice": 1.5, "cachedInputPrice": null, "trainingPrice": null, "note": "xAI's official Grok Code Fast 1 launch post lists $0.20 input / $1.50 output per million tokens, with cached input at $0.02.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 39, "overallRank": 85, "scorePerOutputDollar": 26, "url": "https://benchlm.ai/models/grok-code-fast-1", "markdownUrl": "https://benchlm.ai/md/models/grok-code-fast-1.md" }, { "canonicalModelKey": "holo3-122b-a10b", "slug": "holo3-122b-a10b", "model": "Holo3-122B-A10B", "creator": "H Company", "sourceType": "Proprietary", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": 0.4, "outputPrice": 3, "cachedInputPrice": null, "trainingPrice": null, "note": "H Company's Holo Models API lists Holo3-122B-A10B at $0.40 input / $3.00 output per million tokens with a 65,536-token context limit, text+image input, a 5-image limit, and paid-tier access.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 94, "overallRank": null, "scorePerOutputDollar": 31.333, "url": "https://benchlm.ai/models/holo3-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/holo3-122b-a10b.md" }, { "canonicalModelKey": "holo3-35b-a3b", "slug": "holo3-35b-a3b", "model": "Holo3-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. H Company's current Holo Models API prices the successor Holo3.1 35B model under model ID holo3-1-35b-a3b; BenchLM has not found current first-party token pricing for this older exact Holo3-35B-A3B row.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 100, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-35b-a3b.md" }, { "canonicalModelKey": "holo3-1-0-8b", "slug": "holo3-1-0-8b", "model": "Holo3.1-0.8B", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted Apache 2.0 open-weight Holo3.1 model from H Company's Hugging Face collection. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-0-8b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-0-8b.md" }, { "canonicalModelKey": "holo3-1-35b-a3b", "slug": "holo3-1-35b-a3b", "model": "Holo3.1-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": 0.25, "outputPrice": 1.8, "cachedInputPrice": null, "trainingPrice": null, "note": "H Company's Holo Models API lists model ID holo3-1-35b-a3b at $0.25 input / $1.80 output per million tokens with a 65,536-token context limit, text+image input, a 5-image limit, Apache 2.0 weights, and rate-limited free-tier access.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/holo3-1-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b.md" }, { "canonicalModelKey": "holo3-1-35b-a3b-fp8", "slug": "holo3-1-35b-a3b-fp8", "model": "Holo3.1-35B-A3B-FP8", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted Apache 2.0 quantized Holo3.1 35B-A3B checkpoint from H Company's Hugging Face collection. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-fp8", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-fp8.md" }, { "canonicalModelKey": "holo3-1-35b-a3b-gguf", "slug": "holo3-1-35b-a3b-gguf", "model": "Holo3.1-35B-A3B-GGUF", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted Apache 2.0 quantized Holo3.1 35B-A3B checkpoint from H Company's Hugging Face collection. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-gguf", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-gguf.md" }, { "canonicalModelKey": "holo3-1-35b-a3b-nvfp4", "slug": "holo3-1-35b-a3b-nvfp4", "model": "Holo3.1-35B-A3B-NVFP4", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted Apache 2.0 quantized Holo3.1 35B-A3B checkpoint from H Company's Hugging Face collection. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-nvfp4", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-nvfp4.md" }, { "canonicalModelKey": "holo3-1-4b", "slug": "holo3-1-4b", "model": "Holo3.1-4B", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted Apache 2.0 open-weight Holo3.1 model from H Company's Hugging Face collection. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-4b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-4b.md" }, { "canonicalModelKey": "holo3-1-9b", "slug": "holo3-1-9b", "model": "Holo3.1-9B", "creator": "H Company", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted Apache 2.0 open-weight Holo3.1 model from H Company's Hugging Face collection. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-9b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-9b.md" }, { "canonicalModelKey": "hy3-preview", "slug": "hy3-preview", "model": "Hy3 Preview", "creator": "Tencent", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 58, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md" }, { "canonicalModelKey": "interfaze-beta", "slug": "interfaze-beta", "model": "Interfaze Beta", "creator": "Interfaze", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.5, "outputPrice": 3.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Interfaze's May 11, 2026 launch post lists Interfaze Beta at $1.50 input / $3.50 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 77, "overallRank": null, "scorePerOutputDollar": 22, "url": "https://benchlm.ai/models/interfaze-beta", "markdownUrl": "https://benchlm.ai/md/models/interfaze-beta.md" }, { "canonicalModelKey": "kimi-2-6", "slug": "kimi-2-6", "model": "Kimi 2.6", "creator": "Moonshot AI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.95, "outputPrice": 4, "cachedInputPrice": null, "trainingPrice": null, "note": "Moonshot's Kimi API platform homepage lists K2.6 at $0.95 input / $4.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 81, "overallRank": 21, "scorePerOutputDollar": 20.25, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md" }, { "canonicalModelKey": "kimi-k2", "slug": "kimi-k2", "model": "Kimi K2", "creator": "Moonshot AI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.6, "outputPrice": 2.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Moonshot's Kimi platform pricing page lists Kimi K2 at $0.60 input / $2.50 output per million tokens, with cache-hit input at $0.15.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 41, "overallRank": 82, "scorePerOutputDollar": 16.4, "url": "https://benchlm.ai/models/kimi-k2", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2.md" }, { "canonicalModelKey": "kimi-k2-5", "slug": "kimi-k2-5", "model": "Kimi K2.5", "creator": "Moonshot AI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.6, "outputPrice": 3, "cachedInputPrice": null, "trainingPrice": null, "note": "Moonshot's Kimi API platform lists K2.5 at $0.60 input / $3.00 output per million tokens and says the same model supports both thinking and non-thinking modes.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 63, "overallRank": 47, "scorePerOutputDollar": 21, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md" }, { "canonicalModelKey": "kimi-k2-5-reasoning", "slug": "kimi-k2-5-reasoning", "model": "Kimi K2.5 (Reasoning)", "creator": "Moonshot AI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.6, "outputPrice": 3, "cachedInputPrice": null, "trainingPrice": null, "note": "Moonshot's Kimi API platform lists K2.5 at $0.60 input / $3.00 output per million tokens; Moonshot says K2.5 supports both thinking and non-thinking modes under the same model family.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 75, "overallRank": 31, "scorePerOutputDollar": 25, "url": "https://benchlm.ai/models/kimi-k2-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5-reasoning.md" }, { "canonicalModelKey": "kimi-k2-7-code", "slug": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.95, "outputPrice": 4, "cachedInputPrice": null, "trainingPrice": null, "note": "Moonshot's Kimi API platform lists kimi-k2.7-code at $0.95 cache-miss input / $4.00 output per million tokens, with cache-hit input priced at $0.19 per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, { "canonicalModelKey": "laguna-m-1", "slug": "laguna-m-1", "model": "Laguna M.1", "creator": "Poolside", "sourceType": "Proprietary", "contextWindow": "131K", "contextWindowTokens": 131000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Poolside's April 28, 2026 Laguna launch post says Laguna M.1 is free to use for a limited time through the Poolside API and OpenRouter. No permanent paid token rate is published yet.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 51, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md" }, { "canonicalModelKey": "laguna-xs-2", "slug": "laguna-xs-2", "model": "Laguna XS.2", "creator": "Poolside", "sourceType": "Open Weight", "contextWindow": "131K", "contextWindowTokens": 131000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Poolside's April 28, 2026 Laguna launch post says Laguna XS.2 is free to use for a limited time through the Poolside API and OpenRouter; weights are also available under Apache 2.0 for self-hosting.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 37, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/models/laguna-xs-2.md" }, { "canonicalModelKey": "leanstral", "slug": "leanstral", "model": "Leanstral", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Leanstral labs model card lists the current price at $0 in Mistral AI Studio.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/leanstral", "markdownUrl": "https://benchlm.ai/md/models/leanstral.md" }, { "canonicalModelKey": "lfm2-24b-a2b", "slug": "lfm2-24b-a2b", "model": "LFM2-24B-A2B", "creator": "LiquidAI", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's public pricing page says Liquid foundation models are free to use self-service and that Liquid does not currently offer its own hosted API pricing for these models.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 2, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-24b-a2b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-24b-a2b.md" }, { "canonicalModelKey": "lfm2-5-1-2b-instruct", "slug": "lfm2-5-1-2b-instruct", "model": "LFM2.5-1.2B-Instruct", "creator": "LiquidAI", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's public pricing page says Liquid foundation models are free to use self-service and does not publish a separate hosted API token price for LFM2.5-1.2B-Instruct.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-1-2b-instruct", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-instruct.md" }, { "canonicalModelKey": "lfm2-5-1-2b-thinking", "slug": "lfm2-5-1-2b-thinking", "model": "LFM2.5-1.2B-Thinking", "creator": "LiquidAI", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's public pricing page says Liquid foundation models are free to use self-service and does not publish a separate hosted API token price for LFM2.5-1.2B-Thinking.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 1, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-1-2b-thinking", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-thinking.md" }, { "canonicalModelKey": "lfm2-5-350m", "slug": "lfm2-5-350m", "model": "LFM2.5-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's public pricing page says Liquid foundation models are free to use self-service and does not publish its own hosted API pricing for this open-weight model.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 11, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-350m.md" }, { "canonicalModelKey": "lfm2-5-8b-a1b", "slug": "lfm2-5-8b-a1b", "model": "LFM2.5-8B-A1B", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's May 28, 2026 launch post and Hugging Face model card publish open-weight LFM2.5-8B-A1B checkpoints for local/self-hosted use. Liquid does not publish a separate hosted API token price for this model, so BenchLM represents it as self-host/free-per-token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 42, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-8b-a1b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-8b-a1b.md" }, { "canonicalModelKey": "lfm2-5-vl-450m", "slug": "lfm2-5-vl-450m", "model": "LFM2.5-VL-450M", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's public pricing page says Liquid foundation models are free to use self-service and does not publish its own hosted API pricing for this open-weight multimodal model.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-vl-450m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-450m.md" }, { "canonicalModelKey": "ling-2-6-flash", "slug": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "We did not find a current first-party public pricing page for InclusionAI Ling 2.6 Flash. BenchLM treats hosted pricing as unavailable and only treats the model as open-weight/self-hostable.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 36, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, { "canonicalModelKey": "llama-3-70b", "slug": "llama-3-70b", "model": "Llama 3 70B", "creator": "Meta", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 25, "overallRank": 105, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-3-70b", "markdownUrl": "https://benchlm.ai/md/models/llama-3-70b.md" }, { "canonicalModelKey": "llama-3-1-405b", "slug": "llama-3-1-405b", "model": "Llama 3.1 405B", "creator": "Meta", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 40, "overallRank": 83, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-3-1-405b", "markdownUrl": "https://benchlm.ai/md/models/llama-3-1-405b.md" }, { "canonicalModelKey": "llama-4-behemoth", "slug": "llama-4-behemoth", "model": "Llama 4 Behemoth", "creator": "Meta", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 11, "overallRank": 120, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-4-behemoth", "markdownUrl": "https://benchlm.ai/md/models/llama-4-behemoth.md" }, { "canonicalModelKey": "llama-4-maverick", "slug": "llama-4-maverick", "model": "Llama 4 Maverick", "creator": "Meta", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted cost varies", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 17, "overallRank": 117, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-4-maverick", "markdownUrl": "https://benchlm.ai/md/models/llama-4-maverick.md" }, { "canonicalModelKey": "llama-4-scout", "slug": "llama-4-scout", "model": "Llama 4 Scout", "creator": "Meta", "sourceType": "Open Weight", "contextWindow": "10M", "contextWindowTokens": 10000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted cost varies", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 25, "overallRank": 103, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-4-scout", "markdownUrl": "https://benchlm.ai/md/models/llama-4-scout.md" }, { "canonicalModelKey": "mercury-2", "slug": "mercury-2", "model": "Mercury 2", "creator": "Inception", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.25, "outputPrice": 0.75, "cachedInputPrice": null, "trainingPrice": null, "note": "Inception's official API docs list Mercury 2 at $0.25 input / $0.75 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 11, "overallRank": null, "scorePerOutputDollar": 14.667, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md" }, { "canonicalModelKey": "mimo-v2-flash", "slug": "mimo-v2-flash", "model": "MiMo-V2-Flash", "creator": "Xiaomi", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 59, "overallRank": 54, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mimo-v2-flash", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-flash.md" }, { "canonicalModelKey": "mimo-v2-5", "slug": "mimo-v2-5", "model": "MiMo-V2.5", "creator": "Xiaomi", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "We did not find a current first-party public API pricing page for Xiaomi MiMo-V2.5. BenchLM treats pricing as unavailable until Xiaomi publishes one.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 71, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5.md" }, { "canonicalModelKey": "mimo-v2-5-pro", "slug": "mimo-v2-5-pro", "model": "MiMo-V2.5-Pro", "creator": "Xiaomi", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "We did not find a current first-party public API pricing page for Xiaomi MiMo-V2.5-Pro. BenchLM treats pricing as unavailable until Xiaomi publishes one.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 85, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5-pro.md" }, { "canonicalModelKey": "minimax-m1-80k", "slug": "minimax-m1-80k", "model": "MiniMax M1 80k", "creator": "MiniMax", "sourceType": "Proprietary", "contextWindow": "80K", "contextWindowTokens": 80000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "MiniMax's first-party M1 launch post prices the MiniMax-M1 family, but we did not find a current explicit per-token row for the exact M1-80K SKU. BenchLM treats this exact row as unavailable.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 4, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/minimax-m1-80k", "markdownUrl": "https://benchlm.ai/md/models/minimax-m1-80k.md" }, { "canonicalModelKey": "minimax-m2-5", "slug": "minimax-m2-5", "model": "MiniMax M2.5", "creator": "MiniMax", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.3, "outputPrice": 1.2, "cachedInputPrice": null, "trainingPrice": null, "note": "Official MiniMax pay-as-you-go rate for MiniMax-M2.5.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/minimax-m2-5", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-5.md" }, { "canonicalModelKey": "minimax-m2-7", "slug": "minimax-m2-7", "model": "MiniMax M2.7", "creator": "MiniMax", "sourceType": "Open Weight", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 0.3, "outputPrice": 1.2, "cachedInputPrice": null, "trainingPrice": null, "note": "Official MiniMax pay-as-you-go API rate for the open-weight MiniMax-M2.7 release ($0.3/$1.2 per 1M tokens; prompt caching read $0.06, write $0.375).", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 53, "overallRank": 65, "scorePerOutputDollar": 44.167, "url": "https://benchlm.ai/models/minimax-m2-7", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-7.md" }, { "canonicalModelKey": "minimax-m3", "slug": "minimax-m3", "model": "MiniMax M3", "creator": "MiniMax", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.3, "outputPrice": 1.2, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenRouter's MiniMax M3 page lists the current 50%-off effective price at $0.30 input / $1.20 output per million tokens, with a 1M-token context window. MiniMax's own model page says the M3 API supports up to 1M tokens, with a guaranteed minimum of 512K tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 79, "overallRank": 23, "scorePerOutputDollar": 65.833, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md" }, { "canonicalModelKey": "ministral-3-14b", "slug": "ministral-3-14b", "model": "Ministral 3 14B", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.2, "outputPrice": 0.2, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Ministral 3 14B model card lists $0.20 input / $0.20 output per million tokens in Mistral AI Studio.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 5, "overallRank": null, "scorePerOutputDollar": 25, "url": "https://benchlm.ai/models/ministral-3-14b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b.md" }, { "canonicalModelKey": "ministral-3-14b-reasoning", "slug": "ministral-3-14b-reasoning", "model": "Ministral 3 14B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.2, "outputPrice": 0.2, "cachedInputPrice": null, "trainingPrice": null, "note": "BenchLM maps the published Ministral 3 14B Studio price to the reasoning sibling because Mistral publishes the family under one priced model card at $0.20 input / $0.20 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 5, "overallRank": null, "scorePerOutputDollar": 25, "url": "https://benchlm.ai/models/ministral-3-14b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b-reasoning.md" }, { "canonicalModelKey": "ministral-3-3b", "slug": "ministral-3-3b", "model": "Ministral 3 3B", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.1, "outputPrice": 0.1, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Ministral 3 3B model card lists $0.10 input / $0.10 output per million tokens in Mistral AI Studio.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 1, "overallRank": null, "scorePerOutputDollar": 10, "url": "https://benchlm.ai/models/ministral-3-3b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b.md" }, { "canonicalModelKey": "ministral-3-3b-reasoning", "slug": "ministral-3-3b-reasoning", "model": "Ministral 3 3B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.1, "outputPrice": 0.1, "cachedInputPrice": null, "trainingPrice": null, "note": "BenchLM maps the published Ministral 3 3B Studio price to the reasoning sibling because Mistral publishes the family under one priced model card at $0.10 input / $0.10 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 1, "overallRank": null, "scorePerOutputDollar": 10, "url": "https://benchlm.ai/models/ministral-3-3b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b-reasoning.md" }, { "canonicalModelKey": "ministral-3-8b", "slug": "ministral-3-8b", "model": "Ministral 3 8B", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.15, "outputPrice": 0.15, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Ministral 3 8B model card lists $0.15 input / $0.15 output per million tokens in Mistral AI Studio.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 3, "overallRank": null, "scorePerOutputDollar": 20, "url": "https://benchlm.ai/models/ministral-3-8b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b.md" }, { "canonicalModelKey": "ministral-3-8b-reasoning", "slug": "ministral-3-8b-reasoning", "model": "Ministral 3 8B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.15, "outputPrice": 0.15, "cachedInputPrice": null, "trainingPrice": null, "note": "BenchLM maps the published Ministral 3 8B Studio price to the reasoning sibling because Mistral publishes the family under one priced model card at $0.15 input / $0.15 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 3, "overallRank": null, "scorePerOutputDollar": 20, "url": "https://benchlm.ai/models/ministral-3-8b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b-reasoning.md" }, { "canonicalModelKey": "mistral-7b-v0-3", "slug": "mistral-7b-v0-3", "model": "Mistral 7B v0.3", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 4, "overallRank": 122, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mistral-7b-v0-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-7b-v0-3.md" }, { "canonicalModelKey": "mistral-8x7b", "slug": "mistral-8x7b", "model": "Mistral 8x7B", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 23, "overallRank": 110, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mistral-8x7b", "markdownUrl": "https://benchlm.ai/md/models/mistral-8x7b.md" }, { "canonicalModelKey": "mistral-8x7b-v0-2", "slug": "mistral-8x7b-v0-2", "model": "Mistral 8x7B v0.2", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 1, "overallRank": 123, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mistral-8x7b-v0-2", "markdownUrl": "https://benchlm.ai/md/models/mistral-8x7b-v0-2.md" }, { "canonicalModelKey": "mistral-large-2", "slug": "mistral-large-2", "model": "Mistral Large 2", "creator": "Mistral", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Public API pricing is unavailable, unpublished, or not yet tracked by BenchLM.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 38, "overallRank": 87, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mistral-large-2", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-2.md" }, { "canonicalModelKey": "mistral-large-3", "slug": "mistral-large-3", "model": "Mistral Large 3", "creator": "Mistral", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.5, "outputPrice": 1.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Mistral Large 3 model card lists $0.50 input / $1.50 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 48, "overallRank": 74, "scorePerOutputDollar": 32, "url": "https://benchlm.ai/models/mistral-large-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-3.md" }, { "canonicalModelKey": "mistral-medium-3", "slug": "mistral-medium-3", "model": "Mistral Medium 3", "creator": "Mistral", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.4, "outputPrice": 2, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Mistral Medium 3 model card lists $0.40 input / $2.00 output per million tokens in Mistral AI Studio.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 42, "overallRank": null, "scorePerOutputDollar": 21, "url": "https://benchlm.ai/models/mistral-medium-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3.md" }, { "canonicalModelKey": "mistral-medium-3-5-128b", "slug": "mistral-medium-3-5-128b", "model": "Mistral Medium 3.5 128B", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 1.5, "outputPrice": 7.5, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's April 29, 2026 launch post lists Mistral Medium 3.5 API pricing at $1.50 input / $7.50 output per million tokens and describes the 128B dense model as open weights under a modified MIT license.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 78, "overallRank": null, "scorePerOutputDollar": 10.4, "url": "https://benchlm.ai/models/mistral-medium-3-5-128b", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3-5-128b.md" }, { "canonicalModelKey": "mistral-small-4", "slug": "mistral-small-4", "model": "Mistral Small 4", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.15, "outputPrice": 0.6, "cachedInputPrice": null, "trainingPrice": null, "note": "Mistral's official Mistral Small 4 model card lists $0.15 input / $0.60 output per million tokens and describes Mistral Small 4 as a single hybrid model for instruct, reasoning, and coding.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 41, "overallRank": null, "scorePerOutputDollar": 68.333, "url": "https://benchlm.ai/models/mistral-small-4", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4.md" }, { "canonicalModelKey": "mistral-small-4-reasoning", "slug": "mistral-small-4-reasoning", "model": "Mistral Small 4 (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.15, "outputPrice": 0.6, "cachedInputPrice": null, "trainingPrice": null, "note": "BenchLM uses the published Mistral Small 4 Studio price for the reasoning sibling because Mistral describes Small 4 as one hybrid model covering instruct, reasoning, and coding at $0.15 input / $0.60 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 54, "overallRank": null, "scorePerOutputDollar": 90, "url": "https://benchlm.ai/models/mistral-small-4-reasoning", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4-reasoning.md" }, { "canonicalModelKey": "mixtral-8x22b-instruct-v0-1", "slug": "mixtral-8x22b-instruct-v0-1", "model": "Mixtral 8x22B Instruct v0.1", "creator": "Mistral", "sourceType": "Open Weight", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted cost varies", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 22, "overallRank": 112, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mixtral-8x22b-instruct-v0-1", "markdownUrl": "https://benchlm.ai/md/models/mixtral-8x22b-instruct-v0-1.md" }, { "canonicalModelKey": "moonshot-v1", "slug": "moonshot-v1", "model": "Moonshot v1", "creator": "Moonshot AI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Moonshot documents the Moonshot v1 family and exposes a dedicated pricing page, but we did not recover explicit token values for the exact family row from the current first-party public docs used for this audit.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 22, "overallRank": 114, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/moonshot-v1", "markdownUrl": "https://benchlm.ai/md/models/moonshot-v1.md" }, { "canonicalModelKey": "nemotron-3-nano-30b", "slug": "nemotron-3-nano-30b", "model": "Nemotron 3 Nano 30B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 25, "overallRank": 104, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-nano-30b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-nano-30b.md" }, { "canonicalModelKey": "nemotron-3-nano-omni-30b-a3b", "slug": "nemotron-3-nano-omni-30b-a3b", "model": "Nemotron 3 Nano Omni 30B A3B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 48, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-nano-omni-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-nano-omni-30b-a3b.md" }, { "canonicalModelKey": "nemotron-3-super-100b", "slug": "nemotron-3-super-100b", "model": "Nemotron 3 Super 100B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 43, "overallRank": 78, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-super-100b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-super-100b.md" }, { "canonicalModelKey": "nemotron-3-super-120b-a12b", "slug": "nemotron-3-super-120b-a12b", "model": "Nemotron 3 Super 120B A12B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted or free hosted routes vary by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 10, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-super-120b-a12b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-super-120b-a12b.md" }, { "canonicalModelKey": "nemotron-3-ultra-500b", "slug": "nemotron-3-ultra", "model": "Nemotron 3 Ultra", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 68, "overallRank": 38, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md" }, { "canonicalModelKey": "nemotron-ultra-253b", "slug": "nemotron-ultra-253b", "model": "Nemotron Ultra 253B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 22, "overallRank": 115, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-ultra-253b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-ultra-253b.md" }, { "canonicalModelKey": "nemotron-4-15b", "slug": "nemotron-4-15b", "model": "Nemotron-4 15B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 22, "overallRank": 113, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-4-15b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-4-15b.md" }, { "canonicalModelKey": "nova-pro", "slug": "nova-pro", "model": "Nova Pro", "creator": "Amazon", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "AWS confirms the exact Nova Pro Bedrock model ID and points to Bedrock pricing, but we did not recover an explicit first-party token-pricing row for the exact Nova Pro model from current public text output.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 10, "overallRank": 121, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nova-pro", "markdownUrl": "https://benchlm.ai/md/models/nova-pro.md" }, { "canonicalModelKey": "o1", "slug": "o1", "model": "o1", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 15, "outputPrice": 60, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o1 model page lists $15.00 input / $60.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 57, "overallRank": 58, "scorePerOutputDollar": 0.95, "url": "https://benchlm.ai/models/o1", "markdownUrl": "https://benchlm.ai/md/models/o1.md" }, { "canonicalModelKey": "o1-preview", "slug": "o1-preview", "model": "o1-preview", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 15, "outputPrice": 60, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o1-preview model page lists $15.00 input / $60.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 82, "overallRank": 20, "scorePerOutputDollar": 1.367, "url": "https://benchlm.ai/models/o1-preview", "markdownUrl": "https://benchlm.ai/md/models/o1-preview.md" }, { "canonicalModelKey": "o1-pro", "slug": "o1-pro", "model": "o1-pro", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 150, "outputPrice": 600, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o1-pro model page lists $150.00 input / $600.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 28, "overallRank": 99, "scorePerOutputDollar": 0.047, "url": "https://benchlm.ai/models/o1-pro", "markdownUrl": "https://benchlm.ai/md/models/o1-pro.md" }, { "canonicalModelKey": "o3", "slug": "o3", "model": "o3", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 2, "outputPrice": 8, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o3 model page lists $2.00 input / $8.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 56, "overallRank": 61, "scorePerOutputDollar": 7, "url": "https://benchlm.ai/models/o3", "markdownUrl": "https://benchlm.ai/md/models/o3.md" }, { "canonicalModelKey": "o3-mini", "slug": "o3-mini", "model": "o3-mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1.1, "outputPrice": 4.4, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o3-mini model page lists $1.10 input / $4.40 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 55, "overallRank": 64, "scorePerOutputDollar": 12.5, "url": "https://benchlm.ai/models/o3-mini", "markdownUrl": "https://benchlm.ai/md/models/o3-mini.md" }, { "canonicalModelKey": "o3-pro", "slug": "o3-pro", "model": "o3-pro", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 20, "outputPrice": 80, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o3-pro pricing page lists $20.00 input / $80.00 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 57, "overallRank": 57, "scorePerOutputDollar": 0.713, "url": "https://benchlm.ai/models/o3-pro", "markdownUrl": "https://benchlm.ai/md/models/o3-pro.md" }, { "canonicalModelKey": "o4-mini", "slug": null, "model": "o4-mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": 1.1, "outputPrice": 4.4, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's o4-mini model page lists $1.10 input / $4.40 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": null, "markdownUrl": null }, { "canonicalModelKey": "o4-mini-high", "slug": "o4-mini-high", "model": "o4-mini (high)", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "200K", "contextWindowTokens": 200000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI prices `o4-mini`; `high` is documented as a reasoning-effort setting rather than a separately priced API model SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 43, "overallRank": 79, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/o4-mini-high", "markdownUrl": "https://benchlm.ai/md/models/o4-mini-high.md" }, { "canonicalModelKey": "phi-4", "slug": "phi-4", "model": "Phi-4", "creator": "Microsoft", "sourceType": "Open Weight", "contextWindow": "16K", "contextWindowTokens": 16000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted cost varies", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 27, "overallRank": 100, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/phi-4", "markdownUrl": "https://benchlm.ai/md/models/phi-4.md" }, { "canonicalModelKey": "qwen2-5-coder-32b-instruct", "slug": "qwen2-5-coder-32b-instruct", "model": "Qwen2.5 Coder 32B Instruct", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 6, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-5-coder-32b-instruct", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-coder-32b-instruct.md" }, { "canonicalModelKey": "qwen2-5-1m", "slug": "qwen2-5-1m", "model": "Qwen2.5-1M", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 50, "overallRank": 69, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-5-1m", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-1m.md" }, { "canonicalModelKey": "qwen2-5-72b", "slug": "qwen2-5-72b", "model": "Qwen2.5-72B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 49, "overallRank": 72, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-5-72b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-72b.md" }, { "canonicalModelKey": "qwen2-5-vl-32b", "slug": "qwen2-5-vl-32b", "model": "Qwen2.5-VL-32B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 24, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-5-vl-32b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-vl-32b.md" }, { "canonicalModelKey": "qwen3-235b-2507", "slug": "qwen3-235b-2507", "model": "Qwen3 235B 2507", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted cost varies for the official Qwen3-235B-A22B-Instruct-2507 release.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 32, "overallRank": 95, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-235b-2507", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507.md" }, { "canonicalModelKey": "qwen3-235b-2507-reasoning", "slug": "qwen3-235b-2507-reasoning", "model": "Qwen3 235B 2507 (Reasoning)", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 45, "overallRank": 76, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-235b-2507-reasoning", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507-reasoning.md" }, { "canonicalModelKey": "qwen3-5-397b", "slug": "qwen3-5-397b", "model": "Qwen3.5 397B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.6, "outputPrice": 3.6, "cachedInputPrice": null, "trainingPrice": null, "note": "Alibaba Cloud Model Studio's pricing page lists qwen3.5-397b-a17b at $0.60 input / $3.60 output per million tokens in International deployment mode for prompts up to 256K tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 62, "overallRank": 51, "scorePerOutputDollar": 17.222, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md" }, { "canonicalModelKey": "qwen3-5-397b-reasoning", "slug": "qwen3-5-397b-reasoning", "model": "Qwen3.5 397B (Reasoning)", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.6, "outputPrice": 3.6, "cachedInputPrice": null, "trainingPrice": null, "note": "Alibaba Cloud Model Studio's pricing page lists qwen3.5-397b-a17b at $0.60 input / $3.60 output per million tokens in International deployment mode for prompts up to 256K tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 77, "overallRank": 26, "scorePerOutputDollar": 21.389, "url": "https://benchlm.ai/models/qwen3-5-397b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b-reasoning.md" }, { "canonicalModelKey": "qwen3-5-flash", "slug": "qwen3-5-flash", "model": "Qwen3.5 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.1, "outputPrice": 0.4, "cachedInputPrice": null, "trainingPrice": null, "note": "Alibaba Cloud Model Studio's official pricing page lists qwen3.5-flash at $0.10 input / $0.40 output per million tokens in International deployment mode.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 28, "overallRank": null, "scorePerOutputDollar": 70, "url": "https://benchlm.ai/models/qwen3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-flash.md" }, { "canonicalModelKey": "qwen3-5-plus", "slug": "qwen3-5-plus", "model": "Qwen3.5 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.4, "outputPrice": 2.4, "cachedInputPrice": null, "trainingPrice": null, "note": "Alibaba Cloud Model Studio's official pricing page lists qwen3.5-plus at $0.40 input / $2.40 output per million tokens in International deployment mode for prompts up to 256K tokens, rising to $0.50 / $3.00 above 256K.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/qwen3-5-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-plus.md" }, { "canonicalModelKey": "qwen3-5-122b-a10b", "slug": "qwen3-5-122b-a10b", "model": "Qwen3.5-122B-A10B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 63, "overallRank": 48, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md" }, { "canonicalModelKey": "qwen3-5-27b", "slug": "qwen3-5-27b", "model": "Qwen3.5-27B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 61, "overallRank": 52, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md" }, { "canonicalModelKey": "qwen3-5-35b-a3b", "slug": "qwen3-5-35b-a3b", "model": "Qwen3.5-35B-A3B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 55, "overallRank": 62, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md" }, { "canonicalModelKey": "qwen3-6-plus", "slug": "qwen3-6-plus", "model": "Qwen3.6 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Alibaba's public Model Studio page lists Qwen3.6 Plus with a public range of $0.50-$2.00 input and $3.00-$6.00 output per million tokens, but does not expose an exact per-tier table for the exact `qwen3.6-plus` SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 66, "overallRank": 43, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md" }, { "canonicalModelKey": "qwen3-6-27b", "slug": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Qwen published both the base weights and an FP8 checkpoint on April 21, 2026; public hosted pricing varies by provider.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 72, "overallRank": 34, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, { "canonicalModelKey": "qwen3-7-max", "slug": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Qwen's May 16, 2026 launch post says qwen3.7-max will be available soon through Alibaba Cloud Model Studio and shows API usage, but does not publish exact token pricing.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 91, "overallRank": 5, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, { "canonicalModelKey": "sarvam-105b", "slug": "sarvam-105b", "model": "Sarvam 105B", "creator": "Sarvam", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Sarvam's official API pricing page lists Sarvam 105B as free per token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 39, "overallRank": 86, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sarvam-105b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-105b.md" }, { "canonicalModelKey": "sarvam-30b", "slug": "sarvam-30b", "model": "Sarvam 30B", "creator": "Sarvam", "sourceType": "Open Weight", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Sarvam's official API pricing page lists Sarvam 30B as free per token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 40, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sarvam-30b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-30b.md" }, { "canonicalModelKey": "seed-1-6", "slug": "seed-1-6", "model": "Seed 1.6", "creator": "ByteDance", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Volcengine publishes first-party CNY pricing for Doubao-Seed-1.6 only: 0-32K input is ¥0.8 input and ¥2 or ¥8 output depending on output-length band; 32-128K is ¥1.2 / ¥16; 128-256K is ¥2.4 / ¥24 per million tokens. BenchLM leaves the USD fields unavailable.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 7, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/seed-1-6", "markdownUrl": "https://benchlm.ai/md/models/seed-1-6.md" }, { "canonicalModelKey": "seed-1-6-flash", "slug": "seed-1-6-flash", "model": "Seed 1.6 Flash", "creator": "ByteDance", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Volcengine publishes first-party CNY pricing for Doubao-Seed-1.6-flash only: 0-32K is ¥0.15 / ¥1.5, 32-128K is ¥0.3 / ¥3, and 128-256K is ¥0.6 / ¥6 per million tokens. BenchLM leaves the USD fields unavailable.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 4, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/seed-1-6-flash", "markdownUrl": "https://benchlm.ai/md/models/seed-1-6-flash.md" }, { "canonicalModelKey": "seed-2-0-lite", "slug": "seed-2-0-lite", "model": "Seed-2.0-Lite", "creator": "ByteDance", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Volcengine publishes first-party CNY pricing for doubao-seed-2.0-lite only: 0-32K is ¥0.6 / ¥3.6, 32-128K is ¥0.9 / ¥5.4, and 128-256K is ¥1.8 / ¥10.8 per million tokens. BenchLM leaves the USD fields unavailable.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 6, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/seed-2-0-lite", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-lite.md" }, { "canonicalModelKey": "seed-2-0-mini", "slug": "seed-2-0-mini", "model": "Seed-2.0-Mini", "creator": "ByteDance", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Volcengine publishes first-party CNY pricing for doubao-seed-2.0-mini only: 0-32K is ¥0.2 / ¥2, 32-128K is ¥0.4 / ¥4, and 128-256K is ¥0.8 / ¥8 per million tokens. BenchLM leaves the USD fields unavailable.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 3, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/seed-2-0-mini", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-mini.md" }, { "canonicalModelKey": "step-3-5-flash", "slug": "step-3-5-flash", "model": "Step 3.5 Flash", "creator": "StepFun", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.1, "outputPrice": 0.3, "cachedInputPrice": null, "trainingPrice": null, "note": "StepFun's official pricing page lists step-3.5-flash at $0.10 input / $0.30 output per million tokens, with a separate cached-input rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 0, "overallRank": null, "scorePerOutputDollar": 0, "url": "https://benchlm.ai/models/step-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-5-flash.md" }, { "canonicalModelKey": "step-3-7-flash", "slug": "step-3-7-flash", "model": "Step 3.7 Flash", "creator": "StepFun", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0.2, "outputPrice": 1.15, "cachedInputPrice": null, "trainingPrice": null, "note": "StepFun's official Step 3.7 Flash model card lists input cache-miss pricing at $0.20/M tokens, cache-hit pricing at $0.04/M tokens, and output pricing at $1.15/M tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 70, "overallRank": null, "scorePerOutputDollar": 60.87, "url": "https://benchlm.ai/models/step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-7-flash.md" }, { "canonicalModelKey": "ternary-bonsai-1-7b", "slug": "ternary-bonsai-1-7b", "model": "Ternary Bonsai 1.7B", "creator": "Prism ML", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 28, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ternary-bonsai-1-7b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-1-7b.md" }, { "canonicalModelKey": "ternary-bonsai-4b", "slug": "ternary-bonsai-4b", "model": "Ternary Bonsai 4B", "creator": "Prism ML", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 23, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ternary-bonsai-4b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-4b.md" }, { "canonicalModelKey": "ternary-bonsai-8b", "slug": "ternary-bonsai-8b", "model": "Ternary Bonsai 8B", "creator": "Prism ML", "sourceType": "Open Weight", "contextWindow": "64K", "contextWindowTokens": 64000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Self-hosted open-weight model. Public hosted pricing varies by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 44, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ternary-bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-8b.md" }, { "canonicalModelKey": "trinity-large-preview", "slug": "trinity-large-preview", "model": "Trinity-Large-Preview", "creator": "Arcee AI", "sourceType": "Open Weight", "contextWindow": "512K", "contextWindowTokens": 512000, "inputPrice": 0.25, "outputPrice": 1, "cachedInputPrice": null, "trainingPrice": null, "note": "Official Arcee AI Platform pricing docs list Trinity-Large-Preview at $0.25 / $1.00 per million input/output tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 12, "overallRank": null, "scorePerOutputDollar": 12, "url": "https://benchlm.ai/models/trinity-large-preview", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-preview.md" }, { "canonicalModelKey": "trinity-large-thinking", "slug": "trinity-large-thinking", "model": "Trinity-Large-Thinking", "creator": "Arcee AI", "sourceType": "Open Weight", "contextWindow": "512K", "contextWindowTokens": 512000, "inputPrice": 0.25, "outputPrice": 0.9, "cachedInputPrice": null, "trainingPrice": null, "note": "Arcee's public pricing page lists Trinity-Large-Thinking at $0.25 input / $0.90 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 12, "overallRank": null, "scorePerOutputDollar": 13.333, "url": "https://benchlm.ai/models/trinity-large-thinking", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-thinking.md" }, { "canonicalModelKey": "z-1", "slug": "z-1", "model": "Z-1", "creator": "Z", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Current Z.AI public pricing covers GLM-family models, and we did not find a first-party public pricing row for the exact Z-1 model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 23, "overallRank": 109, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/z-1", "markdownUrl": "https://benchlm.ai/md/models/z-1.md" }, { "canonicalModelKey": "zaya1-74b-preview", "slug": "zaya1-74b-preview", "model": "ZAYA1-74B-Preview", "creator": "Zyphra", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 54, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/zaya1-74b-preview", "markdownUrl": "https://benchlm.ai/md/models/zaya1-74b-preview.md" }, { "canonicalModelKey": "zaya1-8b", "slug": "zaya1-8b", "model": "ZAYA1-8B", "creator": "Zyphra", "sourceType": "Open Weight", "contextWindow": "131K", "contextWindowTokens": 131000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 57, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/zaya1-8b", "markdownUrl": "https://benchlm.ai/md/models/zaya1-8b.md" } ] }