{ "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": "2026-09-02T00:50:21.010Z", "sourceLastUpdated": "September 1, 2026", "sourceFiles": [ "src/data/pricing.json", "src/data/pricingSupplemental.js" ], "counts": { "pricedRows": 344, "numericPricingRows": 239 }, "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": null, "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": null, "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": null, "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": 49.29, "overallRank": 140, "scorePerOutputDollar": 30.806, "url": "https://benchlm.ai/models/aion-2-0", "markdownUrl": "https://benchlm.ai/md/models/aion-2-0.md" }, { "canonicalModelKey": "amazon-nova-2-sonic", "slug": "amazon-nova-2-sonic", "model": "Amazon Nova 2 Sonic", "creator": "Amazon", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/amazon-nova-2-sonic", "markdownUrl": "https://benchlm.ai/md/models/amazon-nova-2-sonic.md" }, { "canonicalModelKey": "apodex-1-1", "slug": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Apodex's web workbench uses dynamic credit billing based on model tokens and tool calls, while the release post says bare-model API access will roll out later. Apodex does not publish a comparable first-party input/output token rate or context limit for the full 397B model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 56.11, "overallRank": 99, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, { "canonicalModelKey": "apodex-1-1-mini", "slug": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Apodex publishes the Apache-2.0 Apodex 1.1 Mini checkpoint for self-hosted use and does not publish a first-party hosted token price for this exact model. The pricing catalog represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md" }, { "canonicalModelKey": "audio-flamingo-3-7b", "slug": "audio-flamingo-3-7b", "model": "Audio Flamingo 3 7B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/audio-flamingo-3-7b", "markdownUrl": "https://benchlm.ai/md/models/audio-flamingo-3-7b.md" }, { "canonicalModelKey": "baichuan-audio", "slug": "baichuan-audio", "model": "Baichuan-Audio", "creator": "Baichuan", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/baichuan-audio", "markdownUrl": "https://benchlm.ai/md/models/baichuan-audio.md" }, { "canonicalModelKey": "baichuan-omni-1-5", "slug": "baichuan-omni-1-5", "model": "Baichuan-Omni 1.5", "creator": "Baichuan", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/baichuan-omni-1-5", "markdownUrl": "https://benchlm.ai/md/models/baichuan-omni-1-5.md" }, { "canonicalModelKey": "blsp-7b", "slug": "blsp-7b", "model": "BLSP 7B", "creator": "BLSP authors", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/blsp-7b", "markdownUrl": "https://benchlm.ai/md/models/blsp-7b.md" }, { "canonicalModelKey": "btl-4", "slug": "btl-4", "model": "BTL-4", "creator": "Bad Theory Labs", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Bad Theory Labs publishes BTL-4 under Apache-2.0 on Hugging Face and does not publish a first-party hosted API token price. BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/btl-4", "markdownUrl": "https://benchlm.ai/md/models/btl-4.md" }, { "canonicalModelKey": "cartesia-ink-whisper", "slug": "cartesia-ink-whisper", "model": "Cartesia Ink-Whisper", "creator": "Cartesia", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/cartesia-ink-whisper", "markdownUrl": "https://benchlm.ai/md/models/cartesia-ink-whisper.md" }, { "canonicalModelKey": "cartesia-sonic-3", "slug": "cartesia-sonic-3", "model": "Cartesia Sonic 3", "creator": "Cartesia", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/cartesia-sonic-3", "markdownUrl": "https://benchlm.ai/md/models/cartesia-sonic-3.md" }, { "canonicalModelKey": "celeris-1", "slug": "celeris-1", "model": "Celeris-1", "creator": "Celeris", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.2, "outputPrice": 0.7, "cachedInputPrice": null, "trainingPrice": null, "note": "Celeris's official pricing guide lists $0.20 per million prompt tokens and $0.70 per million completion tokens. The official model guide lists a 131,072-token combined prompt and requested-output limit.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/celeris-1", "markdownUrl": "https://benchlm.ai/md/models/celeris-1.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": 20.86, "overallRank": 218, "scorePerOutputDollar": 16.688, "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": 40.57, "overallRank": 193, "scorePerOutputDollar": 0.541, "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": 48.36, "overallRank": 144, "scorePerOutputDollar": 3.224, "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": 42.07, "overallRank": 187, "scorePerOutputDollar": 2.805, "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": 45.05, "overallRank": 170, "scorePerOutputDollar": 0.601, "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": 35.27, "overallRank": 206, "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": 1, "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": 82.49, "overallRank": 2, "scorePerOutputDollar": 1.65, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, { "canonicalModelKey": "claude-fable-5-1", "slug": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 10, "outputPrice": 50, "cachedInputPrice": 0.25, "trainingPrice": null, "note": "Anthropic's September 2026 launch page lists `claude-fable-5-1` at $10 input / $50 output per million tokens and cuts cache reads to $0.25 per million tokens. Anthropic estimates that lower cache-read rate reduces typical usage-based Fable workloads by about 25% and highly agentic workloads by as much as 45%; cache-write and Batch rates are not inferred from those estimates.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 82.74, "overallRank": 1, "scorePerOutputDollar": 1.655, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.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": 0.1, "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": 57.35, "overallRank": 91, "scorePerOutputDollar": 11.47, "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": 1, "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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, { "canonicalModelKey": "claude-mythos-5-1", "slug": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic limits Claude Mythos 5.1 to vetted cyberdefenders and life scientists through trusted access programs. The launch page does not publish a separate generally available token-price row or callable public API ID for this restricted profile, so pricing remains unresolved rather than inheriting Fable 5.1's rate.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md" }, { "canonicalModelKey": "claude-mythos-preview", "slug": "claude-mythos-preview", "model": "Claude Mythos Preview", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": null, "contextWindowTokens": 0, "inputPrice": 25, "outputPrice": 125, "cachedInputPrice": null, "trainingPrice": null, "note": "Anthropic's April 7, 2026 Project Glasswing announcement states that usage credits covered the research preview and that participating organizations could later access Claude Mythos Preview at $25 input / $125 output per million tokens. The model was never generally available and was replaced by Claude Mythos 5.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/claude-mythos-preview", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-preview.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": 63.51, "overallRank": 46, "scorePerOutputDollar": 2.54, "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": 67.89, "overallRank": 23, "scorePerOutputDollar": 2.716, "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": 72.23, "overallRank": 15, "scorePerOutputDollar": 2.889, "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": 72.21, "overallRank": 16, "scorePerOutputDollar": 2.888, "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": 75.96, "overallRank": 9, "scorePerOutputDollar": 3.038, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, { "canonicalModelKey": "claude-opus-5", "slug": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 25, "cachedInputPrice": 0.5, "trainingPrice": null, "note": "Anthropic's July 24, 2026 Claude Opus 5 announcement lists the claude-opus-5 API model at $5 input / $25 output per million tokens, the same base price as Opus 4.8. Fast mode runs around 2.5× the default speed and is available at twice the base price.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 82.34, "overallRank": 3, "scorePerOutputDollar": 3.294, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.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": 54.48, "overallRank": 106, "scorePerOutputDollar": 3.632, "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": 64.47, "overallRank": 41, "scorePerOutputDollar": 4.298, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md" }, { "canonicalModelKey": "claude-sonnet-5", "slug": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 2, "outputPrice": 10, "cachedInputPrice": 0.2, "trainingPrice": null, "note": "Anthropic's June 30, 2026 Claude Sonnet 5 launch page lists introductory pricing of $2 input / $10 output per million tokens through August 31, 2026, then $3 input / $15 output per million tokens. The system card says standard configurations use 1M tokens, with BrowseComp using a 10M-token limit through compaction.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 64.72, "overallRank": 39, "scorePerOutputDollar": 6.472, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, { "canonicalModelKey": "cohere-transcribe-03-2026", "slug": "cohere-transcribe-03-2026", "model": "Cohere Transcribe 03-2026", "creator": "Cohere", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/cohere-transcribe-03-2026", "markdownUrl": "https://benchlm.ai/md/models/cohere-transcribe-03-2026.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": 47.57, "overallRank": 151, "scorePerOutputDollar": 4.757, "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": null, "overallRank": null, "scorePerOutputDollar": null, "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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/composer-2-5", "markdownUrl": "https://benchlm.ai/md/models/composer-2-5.md" }, { "canonicalModelKey": "cosmos3-edge", "slug": "cosmos3-edge", "model": "Cosmos3-Edge", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "NVIDIA publishes the Cosmos3-Edge 4B weights under OpenMDW-1.1 for self-hosted use and does not list a first-party hosted API token rate. BenchLM represents the checkpoint as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/cosmos3-edge", "markdownUrl": "https://benchlm.ai/md/models/cosmos3-edge.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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/dbrx-instruct", "markdownUrl": "https://benchlm.ai/md/models/dbrx-instruct.md" }, { "canonicalModelKey": "deepgram-aura-2", "slug": "deepgram-aura-2", "model": "Deepgram Aura-2", "creator": "Deepgram", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepgram-aura-2", "markdownUrl": "https://benchlm.ai/md/models/deepgram-aura-2.md" }, { "canonicalModelKey": "deepgram-nova-3", "slug": "deepgram-nova-3", "model": "Deepgram Nova-3", "creator": "Deepgram", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepgram-nova-3", "markdownUrl": "https://benchlm.ai/md/models/deepgram-nova-3.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": 50.93, "overallRank": 125, "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": 55.24, "overallRank": 103, "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": 0.14, "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": 50.96, "overallRank": 124, "scorePerOutputDollar": 23.269, "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": 42.89, "overallRank": 182, "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": 0.07, "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": 44.38, "overallRank": 174, "scorePerOutputDollar": 40.345, "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": 52.92, "overallRank": 116, "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": 52.74, "overallRank": 118, "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": 0.028, "trainingPrice": null, "note": "Historical DeepSeek V3.2 pricing for the former `deepseek-chat` alias: $0.28 input (cache miss) / $0.028 cache-hit input / $0.42 output per million tokens. DeepSeek's published July 24, 2026 deprecation date has passed; current requests should use the V4 model IDs.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 54.64, "overallRank": 105, "scorePerOutputDollar": 130.095, "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": 0.14, "trainingPrice": null, "note": "Historical DeepSeek V3.2 Thinking pricing for the former `deepseek-reasoner` alias: $0.55 input (cache miss) / $0.14 cache-hit input / $2.19 output per million tokens. DeepSeek's published July 24, 2026 deprecation date has passed; current requests should use the V4 model IDs.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 58.89, "overallRank": 82, "scorePerOutputDollar": 26.89, "url": "https://benchlm.ai/models/deepseek-v3-2-thinking", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2-thinking.md" }, { "canonicalModelKey": "deepseek-v4-flash-max", "slug": "deepseek-v4-flash-0731", "model": "DeepSeek V4 Flash 0731", "creator": "DeepSeek", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.14, "outputPrice": 0.28, "cachedInputPrice": 0.0028, "trainingPrice": null, "note": "DeepSeek V4 Flash 0731 uses the shared `deepseek-v4-flash` API ID. BenchLM represents the model at its highest published reasoning effort. DeepSeek lists $0.14 cache-miss input / $0.0028 cache-hit input / $0.28 output per million tokens. A future overall API price increase is planned, but the new rates and effective date remain unannounced.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseek-v4-flash-0731", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-0731.md" }, { "canonicalModelKey": "deepseek-v4-pro-max", "slug": "deepseek-v4-pro-0813", "model": "DeepSeek V4 Pro 0813", "creator": "DeepSeek", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.435, "outputPrice": 0.87, "cachedInputPrice": 0.003625, "trainingPrice": null, "note": "DeepSeek's pricing page checked August 12, 2026 identifies the current `deepseek-v4-pro` API version as DeepSeek-V4-Pro-0813 and lists $0.435 cache-miss input / $0.003625 cache-hit input / $0.87 output per million tokens. DeepSeek warns that an overall API price increase is planned but has not published the new rates or effective date. DeepSeek has not published weights for the 0813 hosted checkpoint.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 61.22, "overallRank": 57, "scorePerOutputDollar": 70.368, "url": "https://benchlm.ai/models/deepseek-v4-pro-0813", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-0813.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": 50.54, "overallRank": 133, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/deepseekmath-v2", "markdownUrl": "https://benchlm.ai/md/models/deepseekmath-v2.md" }, { "canonicalModelKey": "diva-llama-3-v0-8b", "slug": "diva-llama-3-v0-8b", "model": "DiVA Llama 3 8B", "creator": "DiVA authors", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/diva-llama-3-v0-8b", "markdownUrl": "https://benchlm.ai/md/models/diva-llama-3-v0-8b.md" }, { "canonicalModelKey": "dots3-note-preview", "slug": "dots3-note-preview", "model": "dots3-note Preview", "creator": "Dots Studio", "sourceType": "Open Weight", "contextWindow": "512K", "contextWindowTokens": 512000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Dots Studio publishes the BF16 and FP8 dots3-note Preview checkpoints under Apache-2.0 for self-hosting and does not publish a first-party hosted token rate for the exact model. BenchLM represents the open-weight row as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 68.69, "overallRank": 21, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/dots3-note-preview", "markdownUrl": "https://benchlm.ai/md/models/dots3-note-preview.md" }, { "canonicalModelKey": "elevenlabs-eleven-v3-conversational", "slug": "elevenlabs-eleven-v3-conversational", "model": "ElevenLabs Eleven v3 Conversational", "creator": "ElevenLabs", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "ElevenLabs documents Eleven v3 for hosted text-to-speech and dialogue generation, but does not publish a directly comparable text-token input/output rate for this conversational Audio Realism configuration.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/elevenlabs-eleven-v3-conversational", "markdownUrl": "https://benchlm.ai/md/models/elevenlabs-eleven-v3-conversational.md" }, { "canonicalModelKey": "sakana-fugu-cyber", "slug": "sakana-fugu-cyber", "model": "Fugu Cyber", "creator": "Sakana AI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 6, "outputPrice": 36, "cachedInputPrice": 0.6, "trainingPrice": null, "note": "Sakana AI prices fugu-cyber-v1.0 at $6.00 input / $36.00 output / $0.60 cached input per million tokens for requests at or below 272K context. Above 272K, rates rise to $12.00 / $54.00 / $1.20. Fugu Cyber is available only through the Token Plan.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sakana-fugu-cyber", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-cyber.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": 21.28, "overallRank": 217, "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": 35.14, "overallRank": 207, "scorePerOutputDollar": 7.028, "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": 0.03, "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": 47.56, "overallRank": 153, "scorePerOutputDollar": 19.024, "url": "https://benchlm.ai/models/gemini-2-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash.md" }, { "canonicalModelKey": "gemini-2-5-flash-native-audio-preview-12-2025", "slug": "gemini-2-5-flash-native-audio-preview-12-2025", "model": "Gemini 2.5 Flash Native Audio Preview (12-2025)", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemini-2-5-flash-native-audio-preview-12-2025", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash-native-audio-preview-12-2025.md" }, { "canonicalModelKey": "gemini-2-5-flash-lite", "slug": null, "model": "Gemini 2.5 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.1, "outputPrice": 0.4, "cachedInputPrice": 0.01, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists gemini-2.5-flash-lite at $0.10 input / $0.01 cached input / $0.40 output per million tokens for text, image, and video on the standard paid tier.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": null, "markdownUrl": null }, { "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": 0.125, "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": 56.77, "overallRank": 94, "scorePerOutputDollar": 5.677, "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": 0.05, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists gemini-3-flash-preview at $0.50 input / $0.05 cached input / $3.00 output per million tokens for text, image, and video on the standard paid tier.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 59.74, "overallRank": 73, "scorePerOutputDollar": 19.913, "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": 67.25, "overallRank": 26, "scorePerOutputDollar": 5.604, "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": 62.1, "overallRank": 52, "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-live-preview", "slug": "gemini-3-1-flash-live-preview", "model": "Gemini 3.1 Flash Live Preview", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemini-3-1-flash-live-preview", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-live-preview.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": 0.025, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists gemini-3.1-flash-lite at $0.25 input / $0.025 cached input / $1.50 output per million tokens for text, image, and video on the standard paid tier.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 50.82, "overallRank": 129, "scorePerOutputDollar": 33.88, "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": 0.2, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists gemini-3.1-pro-preview at $2.00 input / $0.20 cached input / $12.00 output per million tokens for prompts up to 200K tokens, rising to $4.00 / $0.40 / $18.00 above 200K.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 56.21, "overallRank": 98, "scorePerOutputDollar": 4.684, "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": 0.15, "trainingPrice": null, "note": "Google's official Gemini Developer API pricing page lists Gemini 3.5 Flash at $1.50 input / $0.15 cached input / $9.00 output per million tokens on the standard paid tier.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 64.2, "overallRank": 43, "scorePerOutputDollar": 7.133, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, { "canonicalModelKey": "gemini-3-5-flash-cyber", "slug": "gemini-3-5-flash-cyber", "model": "Gemini 3.5 Flash Cyber", "creator": "Google", "sourceType": "Proprietary", "contextWindow": null, "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Google DeepMind's July 21, 2026 launch page describes Gemini 3.5 Flash Cyber as a limited-access CodeMender pilot for governments and trusted partners. Google has not published a standalone API SKU, context window, or per-token price for this exact variant.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemini-3-5-flash-cyber", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash-cyber.md" }, { "canonicalModelKey": "gemini-3-5-flash-lite", "slug": "gemini-3-5-flash-lite", "model": "Gemini 3.5 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.3, "outputPrice": 2.5, "cachedInputPrice": 0.03, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists gemini-3.5-flash-lite at $0.30 input / $0.03 cached input / $2.50 output per million tokens on the standard paid tier.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 65.04, "overallRank": 37, "scorePerOutputDollar": 26.016, "url": "https://benchlm.ai/models/gemini-3-5-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash-lite.md" }, { "canonicalModelKey": "gemini-3-6-flash", "slug": "gemini-3-6-flash", "model": "Gemini 3.6 Flash", "creator": "Google", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.5, "outputPrice": 7.5, "cachedInputPrice": 0.15, "trainingPrice": null, "note": "Google's Gemini Developer API pricing page lists gemini-3.6-flash at $1.50 input / $0.15 cached input / $7.50 output per million tokens on the standard paid tier.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 75.06, "overallRank": 10, "scorePerOutputDollar": 10.008, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md" }, { "canonicalModelKey": "gemini-3-7-flash", "slug": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "contextWindow": null, "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Google's public Gemini API pricing page had not published a Gemini 3.7 Flash rate when this release placeholder was added on August 13, 2026. The numeric fields remain unresolved; the row does not inherit Gemini 3.6 Flash pricing.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 61, "overallRank": 63, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-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": 41.26, "overallRank": 189, "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": 57.12, "overallRank": 93, "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": 60.08, "overallRank": 71, "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": 42.33, "overallRank": 184, "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": 43.37, "overallRank": 178, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gemma-4-e4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e4b.md" }, { "canonicalModelKey": "glm-realtime-air", "slug": "glm-realtime-air", "model": "GLM Realtime Air", "creator": "Zhipu AI", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-realtime-air", "markdownUrl": "https://benchlm.ai/md/models/glm-realtime-air.md" }, { "canonicalModelKey": "glm-realtime-flash", "slug": "glm-realtime-flash", "model": "GLM Realtime Flash", "creator": "Zhipu AI", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-realtime-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-realtime-flash.md" }, { "canonicalModelKey": "glm-4-voice", "slug": "glm-4-voice", "model": "GLM-4-Voice", "creator": "Zhipu AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-4-voice", "markdownUrl": "https://benchlm.ai/md/models/glm-4-voice.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": 58.32, "overallRank": 86, "scorePerOutputDollar": 26.509, "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": 47.08, "overallRank": 156, "scorePerOutputDollar": 42.8, "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": 60.62, "overallRank": 66, "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": 50.35, "overallRank": 137, "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": 65.49, "overallRank": 35, "scorePerOutputDollar": 20.466, "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": 60.55, "overallRank": 67, "scorePerOutputDollar": 18.922, "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": 65.82, "overallRank": 33, "scorePerOutputDollar": 16.455, "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": 66.68, "overallRank": 29, "scorePerOutputDollar": 15.155, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, { "canonicalModelKey": "glm-5-2", "slug": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.4, "outputPrice": 4.4, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI's official pricing page lists GLM-5.2 at $1.40 input / $4.40 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 62.88, "overallRank": 48, "scorePerOutputDollar": 14.291, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, { "canonicalModelKey": "glm-5-3", "slug": "glm-5-3", "model": "GLM-5.3", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI publishes the GLM-5.3 FP8 checkpoint under the custom GLM-5.3 License for self-hosting and does not publish a distinct first-party hosted per-token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs. The hosted Z.AI route and Coding Plan must not be read as free from this self-host placeholder.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 62.41, "overallRank": 50, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md" }, { "canonicalModelKey": "glm-5-3-flash", "slug": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Z.AI publishes GLM-5.3-Flash under MIT for self-hosting, so BenchLM represents the open checkpoint as self-host/free-per-token before infrastructure costs. The exact glm-5.3-flash model is also available through Z.AI services and the GLM Coding Plan, but Z.AI's public per-million-token pricing table does not yet list this SKU. The hosted API must not be read as free from this self-host placeholder.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 61.25, "overallRank": 56, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.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": 62.09, "overallRank": 53, "scorePerOutputDollar": 15.523, "url": "https://benchlm.ai/models/glm-5v-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5v-turbo.md" }, { "canonicalModelKey": "gpt-realtime", "slug": "gpt-realtime", "model": "GPT Realtime", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 4, "outputPrice": 16, "cachedInputPrice": 0.4, "trainingPrice": null, "note": "The linked provider model page publishes these text-token input and output rates per million tokens. Audio-token rates are separate and remain in the provider documentation.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-realtime", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime.md" }, { "canonicalModelKey": "gpt-realtime-1-5", "slug": "gpt-realtime-1-5", "model": "GPT Realtime 1.5", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 4, "outputPrice": 16, "cachedInputPrice": 0.4, "trainingPrice": null, "note": "The linked provider model page publishes these text-token input and output rates per million tokens. Audio-token rates are separate and remain in the provider documentation.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-realtime-1-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime-1-5.md" }, { "canonicalModelKey": "gpt-realtime-2", "slug": "gpt-realtime-2", "model": "GPT Realtime 2", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 4, "outputPrice": 24, "cachedInputPrice": 0.4, "trainingPrice": null, "note": "The linked provider model page publishes these text-token input and output rates per million tokens. Audio-token rates are separate and remain in the provider documentation.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-realtime-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime-2.md" }, { "canonicalModelKey": "gpt-realtime-mini", "slug": "gpt-realtime-mini", "model": "GPT Realtime mini", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0.6, "outputPrice": 2.4, "cachedInputPrice": 0.06, "trainingPrice": null, "note": "The linked provider model page publishes these text-token input and output rates per million tokens. Audio-token rates are separate and remain in the provider documentation.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-realtime-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime-mini.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": 26.85, "overallRank": 211, "scorePerOutputDollar": 0.895, "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": 50.83, "overallRank": 128, "scorePerOutputDollar": 6.354, "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": 44.4, "overallRank": 173, "scorePerOutputDollar": 27.75, "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": 42.38, "overallRank": 183, "scorePerOutputDollar": 105.95, "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": 40.96, "overallRank": 191, "scorePerOutputDollar": 4.096, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md" }, { "canonicalModelKey": "gpt-4o-audio", "slug": "gpt-4o-audio", "model": "GPT-4o Audio", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 2.5, "outputPrice": 10, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked provider model page publishes these text-token input and output rates per million tokens. Audio-token rates are separate and remain in the provider documentation.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-4o-audio", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-audio.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": 37.43, "overallRank": 204, "scorePerOutputDollar": 62.383, "url": "https://benchlm.ai/models/gpt-4o-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini.md" }, { "canonicalModelKey": "gpt-4o-mini-audio", "slug": "gpt-4o-mini-audio", "model": "GPT-4o mini Audio", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0.15, "outputPrice": 0.6, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked provider model page publishes these text-token input and output rates per million tokens. Audio-token rates are separate and remain in the provider documentation.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-4o-mini-audio", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini-audio.md" }, { "canonicalModelKey": "gpt-4o-mini-tts", "slug": "gpt-4o-mini-tts", "model": "GPT-4o mini TTS", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "2K", "contextWindowTokens": 2000, "inputPrice": 0.6, "outputPrice": 12, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI prices GPT-4o mini TTS at $0.60 per million text input tokens and $12.00 per million audio output tokens. The output rate is audio-token pricing, so it is not comparable to text-output model rates.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-4o-mini-tts", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini-tts.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": 59.4, "overallRank": 80, "scorePerOutputDollar": 5.94, "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": 54.06, "overallRank": 109, "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": 42.97, "overallRank": 180, "scorePerOutputDollar": 21.485, "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": 46.53, "overallRank": 159, "scorePerOutputDollar": 116.325, "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": 53.41, "overallRank": 114, "scorePerOutputDollar": 5.341, "url": "https://benchlm.ai/models/gpt-5-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1.md" }, { "canonicalModelKey": "gpt-5-1-codex", "slug": "gpt-5-1-codex", "model": "GPT-5.1-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "400K", "contextWindowTokens": 400000, "inputPrice": 1.25, "outputPrice": 10, "cachedInputPrice": 0.125, "trainingPrice": null, "note": "OpenAI's GPT-5.1-Codex model documentation lists $1.25 input / $0.125 cached input / $10.00 output per million text tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 52.63, "overallRank": 119, "scorePerOutputDollar": 5.263, "url": "https://benchlm.ai/models/gpt-5-1-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex.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": 0.125, "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": 55.19, "overallRank": 104, "scorePerOutputDollar": 5.519, "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": 57.95, "overallRank": 87, "scorePerOutputDollar": 4.139, "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": 59.77, "overallRank": 72, "scorePerOutputDollar": 9.962, "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": 21, "outputPrice": 168, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI's GPT-5.2 Pro model documentation lists $21.00 input and $168.00 output per million text tokens. OpenAI does not publish a cached-input rate for this SKU.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 67.19, "overallRank": 27, "scorePerOutputDollar": 0.4, "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": 57.86, "overallRank": 88, "scorePerOutputDollar": 4.133, "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": 65.6, "overallRank": 34, "scorePerOutputDollar": 4.686, "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": 59.67, "overallRank": 75, "scorePerOutputDollar": 4.262, "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": 57.65, "overallRank": 90, "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": 0.25, "trainingPrice": null, "note": "OpenAI's current API pricing page lists GPT-5.4 at $2.50 input / $0.25 cached input / $15.00 output per million tokens for short-context requests, with higher pricing for long-context requests.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 73.04, "overallRank": 12, "scorePerOutputDollar": 4.869, "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": 0.075, "trainingPrice": null, "note": "OpenAI's current API pricing page lists gpt-5.4-mini at $0.75 input / $0.075 cached input / $4.50 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 56.69, "overallRank": 96, "scorePerOutputDollar": 12.598, "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": 0.02, "trainingPrice": null, "note": "OpenAI's current API pricing page lists gpt-5.4-nano at $0.20 input / $0.02 cached input / $1.25 output per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 66.39, "overallRank": 32, "scorePerOutputDollar": 53.112, "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 current API pricing page lists GPT-5.4 Pro at $30.00 input / $180.00 output per million tokens for short-context requests, with higher pricing for long-context requests and no cached-input rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 61.47, "overallRank": 54, "scorePerOutputDollar": 0.341, "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": 0.5, "trainingPrice": null, "note": "OpenAI's current API pricing page lists gpt-5.5 at $5.00 input / $0.50 cached input / $30.00 output per million tokens for short-context requests. Batch and Flex are available at half the standard rate, and Priority is 2.5x the standard rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 72.68, "overallRank": 13, "scorePerOutputDollar": 2.423, "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 current API pricing page lists gpt-5.5-pro at $30.00 input / $180.00 output per million tokens for short-context requests and does not list a cached-input rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 64.35, "overallRank": 42, "scorePerOutputDollar": 0.358, "url": "https://benchlm.ai/models/gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5-pro.md" }, { "canonicalModelKey": "gpt-5-6-cyber", "slug": "gpt-5-6-cyber", "model": "GPT-5.6 Cyber", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": null, "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenAI identifies GPT-5.6 Cyber as a separate GPT-5.6 Sol-based model available only through Daybreak Red trusted access. OpenAI has not published separate token pricing or a context-window specification for gpt-5.6-cyber.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-5-6-cyber", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-cyber.md" }, { "canonicalModelKey": "gpt-5-6-luna", "slug": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "inputPrice": 1, "outputPrice": 6, "cachedInputPrice": 0.1, "trainingPrice": null, "note": "OpenAI's API billing price sheet lists GPT-5.6 Luna at $1.00 input / $0.10 cached input / $6.00 output per million tokens for short-context requests. Prompts above 272K input tokens use the published $2.00 input / $0.20 cached input / $9.00 output long-context tier; cache writes cost $1.25 per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 66.93, "overallRank": 28, "scorePerOutputDollar": 11.155, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, { "canonicalModelKey": "gpt-5-6-sol", "slug": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "inputPrice": 5, "outputPrice": 30, "cachedInputPrice": 0.5, "trainingPrice": null, "note": "OpenAI's current GPT-5.6 Sol model page lists $5.00 input / $0.50 cached input / $30.00 output per million tokens and a 1.05M-token context window. Prompts above 272K input tokens are charged at 2x input and 1.5x output for the full request; cache writes cost 1.25x uncached input. OpenAI's July 30, 2026 price update left Sol unchanged.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 81.69, "overallRank": 4, "scorePerOutputDollar": 2.723, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, { "canonicalModelKey": "gpt-5-6-terra", "slug": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "inputPrice": 2.5, "outputPrice": 15, "cachedInputPrice": 0.25, "trainingPrice": null, "note": "OpenAI's API billing price sheet lists GPT-5.6 Terra at $2.50 input / $0.25 cached input / $15.00 output per million tokens for short-context requests. Prompts above 272K input tokens use the published $5.00 input / $0.50 cached input / $22.50 output long-context tier; cache writes cost $3.125 per million tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 72.5, "overallRank": 14, "scorePerOutputDollar": 4.833, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.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": 49.22, "overallRank": 141, "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": 42.25, "overallRank": 185, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/gpt-oss-20b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-20b.md" }, { "canonicalModelKey": "granite-4-2-8b", "slug": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "IBM publishes Granite 4.2 8B under Apache 2.0 for self-hosting and does not publish a first-party hosted token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs. OpenRouter currently exposes ibm-granite/granite-4.2-8b as a hosted route, but its third-party rate is not used as canonical pricing.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 46.32, "overallRank": 161, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.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": null, "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": 39, "overallRank": 201, "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": null, "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": 39, "overallRank": 202, "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": 40.33, "overallRank": 197, "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": null, "overallRank": null, "scorePerOutputDollar": null, "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": 59.42, "overallRank": 79, "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": 60.73, "overallRank": 65, "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": 50.66, "overallRank": 131, "scorePerOutputDollar": 101.32, "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": 55.42, "overallRank": 102, "scorePerOutputDollar": 9.237, "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": null, "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": 0.2, "trainingPrice": null, "note": "xAI's official July 2026 pricing page lists grok-4.3 at $1.25 input / $0.20 cached input / $2.50 output per million tokens below 200K tokens, with a 1M context window. Requests at or above 200K use the $2.50 / $0.40 / $5.00 long-context tier; BenchLM stores the short-context rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 63.82, "overallRank": 44, "scorePerOutputDollar": 25.528, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md" }, { "canonicalModelKey": "grok-4-5", "slug": "grok-4-5", "model": "Grok 4.5", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "500K", "contextWindowTokens": 500000, "inputPrice": 2, "outputPrice": 6, "cachedInputPrice": 0.3, "trainingPrice": null, "note": "xAI's official July 2026 pricing page lists grok-4.5 at $2.00 input / $0.30 cached input / $6.00 output per million tokens below 200K tokens, with a 500K context window. Requests at or above 200K use the published $4.00 / $0.60 / $12.00 long-context tier; BenchLM stores the short-context rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 74.9, "overallRank": 11, "scorePerOutputDollar": 12.483, "url": "https://benchlm.ai/models/grok-4-5", "markdownUrl": "https://benchlm.ai/md/models/grok-4-5.md" }, { "canonicalModelKey": "grok-4-6", "slug": "grok-4-6", "model": "Grok 4.6", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "500K", "contextWindowTokens": 500000, "inputPrice": 2, "outputPrice": 6, "cachedInputPrice": 0.5, "trainingPrice": null, "note": "xAI's August 12, 2026 release notes list grok-4.6 at $2.00 input / $0.50 cached input / $6.00 output per million tokens below 200K prompt tokens. Prompts above 200K use the published $4.00 / $1.00 / $12.00 long-context tier; BenchLM stores the short-context rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 62.98, "overallRank": 47, "scorePerOutputDollar": 10.497, "url": "https://benchlm.ai/models/grok-4-6", "markdownUrl": "https://benchlm.ai/md/models/grok-4-6.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": 0.2, "trainingPrice": null, "note": "xAI's official July 2026 pricing page lists grok-build-0.1 at $1.00 input / $0.20 cached input / $2.00 output per million tokens below 200K tokens, with a 256K context window. Requests at or above 200K use the $2.00 / $0.40 / $4.00 long-context tier; BenchLM stores the short-context rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "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": 37.73, "overallRank": 203, "scorePerOutputDollar": 25.153, "url": "https://benchlm.ai/models/grok-code-fast-1", "markdownUrl": "https://benchlm.ai/md/models/grok-code-fast-1.md" }, { "canonicalModelKey": "grok-realtime", "slug": "grok-realtime", "model": "Grok Realtime", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-realtime", "markdownUrl": "https://benchlm.ai/md/models/grok-realtime.md" }, { "canonicalModelKey": "grok-voice-think-fast-1-0", "slug": "grok-voice-think-fast-1-0", "model": "Grok Voice Think Fast 1.0", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-voice-think-fast-1-0", "markdownUrl": "https://benchlm.ai/md/models/grok-voice-think-fast-1-0.md" }, { "canonicalModelKey": "grok-voice-think-fast-2-0", "slug": "grok-voice-think-fast-2-0", "model": "Grok Voice Think Fast 2.0", "creator": "xAI", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/grok-voice-think-fast-2-0", "markdownUrl": "https://benchlm.ai/md/models/grok-voice-think-fast-2-0.md" }, { "canonicalModelKey": "hark-handoff", "slug": "hark-handoff", "model": "Hark Handoff", "creator": "Hark", "sourceType": "Proprietary", "contextWindow": null, "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Hark has introduced Handoff as an application-based research preview and has not published a public API SKU or token-pricing row for the exact system.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hark-handoff", "markdownUrl": "https://benchlm.ai/md/models/hark-handoff.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": null, "overallRank": null, "scorePerOutputDollar": null, "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": null, "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": null, "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": null, "overallRank": null, "scorePerOutputDollar": null, "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": null, "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": null, "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": null, "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": null, "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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/holo3-1-9b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-9b.md" }, { "canonicalModelKey": "hy-mt2-1-8b", "slug": "hy-mt2-1-8b", "model": "Hy-MT2-1.8B", "creator": "Tencent", "sourceType": "Open Weight", "contextWindow": "8K", "contextWindowTokens": 8000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Tencent publishes the Apache-2.0 Hy-MT2-1.8B checkpoint for self-hosting and does not publish a first-party hosted token price for this exact model. BenchLM represents the open-weight row as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hy-mt2-1-8b", "markdownUrl": "https://benchlm.ai/md/models/hy-mt2-1-8b.md" }, { "canonicalModelKey": "hy-mt2-30b-a3b", "slug": "hy-mt2-30b-a3b", "model": "Hy-MT2-30B-A3B", "creator": "Tencent", "sourceType": "Open Weight", "contextWindow": "8K", "contextWindowTokens": 8000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Tencent publishes the Apache-2.0 Hy-MT2-30B-A3B checkpoint for self-hosting and does not publish a first-party hosted token price for this exact model. BenchLM represents the open-weight row as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hy-mt2-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/hy-mt2-30b-a3b.md" }, { "canonicalModelKey": "hy3", "slug": "hy3", "model": "Hy3", "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": 67.65, "overallRank": 24, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hy3", "markdownUrl": "https://benchlm.ai/md/models/hy3.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": 43.71, "overallRank": 176, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md" }, { "canonicalModelKey": "hy4-preview", "slug": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Tencent publishes Hy4 preview under Apache 2.0 for self-hosting and does not publish a first-party hosted token rate for this exact checkpoint. We represent the open-weight row as self-host/free-per-token before infrastructure costs; the separate FP8 checkpoint is a quantization of the same model rather than a separately priced API SKU.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 78.3, "overallRank": 7, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, { "canonicalModelKey": "ichigo", "slug": "ichigo", "model": "Ichigo", "creator": "Jan", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ichigo", "markdownUrl": "https://benchlm.ai/md/models/ichigo.md" }, { "canonicalModelKey": "inkling", "slug": "inkling", "model": "Inkling", "creator": "Thinking Machines Lab", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.87, "outputPrice": 4.68, "cachedInputPrice": 0.374, "trainingPrice": null, "note": "Thinking Machines Lab's Tinker pricing docs list the 64K Inkling tier at $1.87 prefill / $0.374 cached prefill / $4.68 sample per million tokens during a limited-time 50% discount. The hosted 256K tier costs $3.74 / $0.748 cached / $9.36, while the released checkpoint supports up to 1M tokens when self-hosted. BenchLM stores the lower-context hosted tier as the headline API rate and the model's architectural context ceiling separately.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 66.51, "overallRank": 31, "scorePerOutputDollar": 14.212, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md" }, { "canonicalModelKey": "inkling-small", "slug": "inkling-small", "model": "Inkling-Small", "creator": "Thinking Machines Lab", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.58, "outputPrice": 1.44, "cachedInputPrice": 0.116, "trainingPrice": null, "note": "Thinking Machines Lab's Tinker pricing docs list the 64K Inkling-Small tier at $0.58 prefill / $0.116 cached prefill / $1.44 sample per million tokens during a limited-time 50% discount. The hosted 256K fine-tuning tier costs $1.16 / $0.232 cached / $2.89, while the beta 256K serverless endpoint costs $0.30 / $0.06 cached / $1.20. We store the lower-context fine-tuning tier as the headline Tinker rate and the open checkpoint's 1M-token ceiling separately.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 63.52, "overallRank": 45, "scorePerOutputDollar": 44.111, "url": "https://benchlm.ai/models/inkling-small", "markdownUrl": "https://benchlm.ai/md/models/inkling-small.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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/interfaze-beta", "markdownUrl": "https://benchlm.ai/md/models/interfaze-beta.md" }, { "canonicalModelKey": "kalpa-tts-beta-v0-1", "slug": "kalpa-tts-beta-v0-1", "model": "Kalpa TTS Beta v0.1", "creator": "Kalpa Labs", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Kalpa documents the `kalpa-tts-beta-v0.1` early-access API model but does not publish a directly comparable text-token input/output rate. Speech usage is metered in characters and audio seconds, so token pricing remains unresolved.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/kalpa-tts-beta-v0-1", "markdownUrl": "https://benchlm.ai/md/models/kalpa-tts-beta-v0-1.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": 59.09, "overallRank": 81, "scorePerOutputDollar": 14.773, "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": 26.24, "overallRank": 213, "scorePerOutputDollar": 10.496, "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": 58.74, "overallRank": 84, "scorePerOutputDollar": 19.58, "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": 60.12, "overallRank": 70, "scorePerOutputDollar": 20.04, "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": 54.01, "overallRank": 110, "scorePerOutputDollar": 13.503, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, { "canonicalModelKey": "kimi-3", "slug": "kimi-k3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "inputPrice": 3, "outputPrice": 15, "cachedInputPrice": 0.3, "trainingPrice": null, "note": "Moonshot AI's official Kimi K3 pricing page lists $0.30 cache-hit input, $3.00 cache-miss input, and $15.00 output per million tokens for model ID kimi-k3, with an exact 1,048,576-token context window. OpenRouter independently lists route moonshotai/kimi-k3 with one Moonshot AI INT4 endpoint at the same rates and context length. Prices exclude applicable taxes. Moonshot schedules the full weight release for July 27, 2026, so source type remains pending until the files are public.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 79.92, "overallRank": 5, "scorePerOutputDollar": 5.328, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, { "canonicalModelKey": "kimi-audio-7b", "slug": "kimi-audio-7b", "model": "Kimi-Audio 7B", "creator": "Moonshot AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/kimi-audio-7b", "markdownUrl": "https://benchlm.ai/md/models/kimi-audio-7b.md" }, { "canonicalModelKey": "kokoro-82m", "slug": "kokoro-82m", "model": "Kokoro 82M", "creator": "hexgrad", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/kokoro-82m", "markdownUrl": "https://benchlm.ai/md/models/kokoro-82m.md" }, { "canonicalModelKey": "laguna-m-1", "slug": "laguna-m-1", "model": "Laguna M.1", "creator": "Poolside", "sourceType": "Proprietary", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Poolside says Laguna M.1 is available through the Poolside API and was free for a limited time, but BenchLM did not find a current first-party permanent token-pricing row for the exact hosted model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md" }, { "canonicalModelKey": "laguna-s-2-1", "slug": "laguna-s-2-1", "model": "Laguna S 2.1", "creator": "Poolside", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.1, "outputPrice": 0.2, "cachedInputPrice": 0.01, "trainingPrice": null, "note": "Poolside's July 21, 2026 launch post lists the dedicated 1M-context OpenRouter endpoint at $0.10 input / $0.20 output / $0.01 cache-read per million tokens. A separate free endpoint is limited to 256K context.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/laguna-s-2-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-s-2-1.md" }, { "canonicalModelKey": "laguna-xs-2", "slug": "laguna-xs-2", "model": "Laguna XS.2", "creator": "Poolside", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Poolside and the Hugging Face Laguna XS.2 collection list open weights under Apache 2.0. Poolside does not publish a separate first-party hosted API token price for the exact row, so BenchLM represents the open-weight self-host row as free per token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/leanstral", "markdownUrl": "https://benchlm.ai/md/models/leanstral.md" }, { "canonicalModelKey": "lfg-1", "slug": "lfg-1", "model": "LFG-1", "creator": "glenn2", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfg-1", "markdownUrl": "https://benchlm.ai/md/models/lfg-1.md" }, { "canonicalModelKey": "lfg-2", "slug": "lfg-2", "model": "LFG-2", "creator": "glenn2", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfg-2", "markdownUrl": "https://benchlm.ai/md/models/lfg-2.md" }, { "canonicalModelKey": "lfg-3", "slug": "lfg-3", "model": "LFG-3", "creator": "glenn2", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfg-3", "markdownUrl": "https://benchlm.ai/md/models/lfg-3.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": 18.29, "overallRank": 221, "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": 14.99, "overallRank": 224, "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": 15.71, "overallRank": 223, "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": "lfm2-5-2-6b", "slug": "lfm2-5-2-6b", "model": "LFM2.5-2.6B", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI's August 4, 2026 launch post and Hugging Face model card publish LFM2.5-2.6B under the LFM Open License v1.0 for local, on-device, and self-hosted use. Liquid does not publish a separate hosted API token price for this checkpoint, so BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 42.9, "overallRank": 181, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-2-6b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-2-6b.md" }, { "canonicalModelKey": "lfm2-5-230m", "slug": "lfm2-5-230m", "model": "LFM2.5-230M", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI publishes LFM2.5-230M on Hugging Face under the LFM Open License v1.0 for local/self-hosted use. Liquid does not publish a separate hosted API token price for this checkpoint, so BenchLM represents it as self-host/free-per-token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-230m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-230m.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": null, "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": 41.78, "overallRank": 188, "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-colbert-350m", "slug": "lfm2-5-colbert-350m", "model": "LFM2.5-ColBERT-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI publishes LFM2.5 retriever checkpoints on Hugging Face under the LFM Open License v1.0 for local/self-hosted retrieval use. Liquid does not publish a separate hosted API token price for these retrieval-only models, so BenchLM represents them as self-host/free-per-token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-colbert-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-colbert-350m.md" }, { "canonicalModelKey": "lfm2-5-embedding-350m", "slug": "lfm2-5-embedding-350m", "model": "LFM2.5-Embedding-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "contextWindow": "32K", "contextWindowTokens": 32000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Liquid AI publishes LFM2.5 retriever checkpoints on Hugging Face under the LFM Open License v1.0 for local/self-hosted retrieval use. Liquid does not publish a separate hosted API token price for these retrieval-only models, so BenchLM represents them as self-host/free-per-token.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lfm2-5-embedding-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-embedding-350m.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": null, "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": 44.18, "overallRank": 175, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, { "canonicalModelKey": "ling-3-0-flash", "slug": "ling-3-0-flash", "model": "Ling 3.0 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "InclusionAI publishes the MIT-licensed BF16 checkpoint for self-hosting. The official model card links to a third-party OpenRouter route but does not publish a first-party hosted per-token price, so the numeric price fields remain unresolved.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 53.62, "overallRank": 112, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md" }, { "canonicalModelKey": "ling-3-0-flash-fin", "slug": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked Vercel and OpenRouter routes advertise temporary free access for this exact API model, but InclusionAI has not published a durable first-party USD token rate. The numeric fields remain unresolved so a time-limited gateway promotion is not presented as the model's canonical price. InclusionAI says weights will be released next week; this row must not be treated as self-hostable until that checkpoint and its license are public.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md" }, { "canonicalModelKey": "ling-3-0-flash-fp8", "slug": "ling-3-0-flash-fp8", "model": "Ling 3.0 Flash FP8", "creator": "InclusionAI", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "InclusionAI publishes the MIT-licensed blockwise FP8 checkpoint for self-hosting. The official model card does not publish a first-party hosted per-token price, so the numeric price fields remain unresolved.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fp8", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fp8.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": 51.48, "overallRank": 122, "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": 52.38, "overallRank": 120, "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": 40.36, "overallRank": 196, "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": 22.76, "overallRank": 215, "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": 39.55, "overallRank": 200, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-4-scout", "markdownUrl": "https://benchlm.ai/md/models/llama-4-scout.md" }, { "canonicalModelKey": "llama-omni", "slug": "llama-omni", "model": "LLaMA-Omni", "creator": "ICTNLP", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/llama-omni", "markdownUrl": "https://benchlm.ai/md/models/llama-omni.md" }, { "canonicalModelKey": "longcat-2-0", "slug": "longcat-2-0", "model": "LongCat-2.0", "creator": "Meituan", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "The LongCat-2.0 launch page describes the model as open sourced and exposes API access, but no first-party hosted token price was available in the reviewed source. BenchLM represents the open-weight checkpoint as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/longcat-2-0", "markdownUrl": "https://benchlm.ai/md/models/longcat-2-0.md" }, { "canonicalModelKey": "lyra-base", "slug": "lyra-base", "model": "Lyra Base", "creator": "DVL Lab", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lyra-base", "markdownUrl": "https://benchlm.ai/md/models/lyra-base.md" }, { "canonicalModelKey": "lyra-mini", "slug": "lyra-mini", "model": "Lyra Mini", "creator": "DVL Lab", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/lyra-mini", "markdownUrl": "https://benchlm.ai/md/models/lyra-mini.md" }, { "canonicalModelKey": "macaw-v1", "slug": "macaw-v1", "model": "Macaw", "creator": "Bad Theory Labs", "sourceType": "Open Weight", "contextWindow": "128K", "contextWindowTokens": 128000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Bad Theory Labs publishes the local Macaw MLX checkpoint under the LFM Open License v1.0 and does not publish a first-party hosted API token price. BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/macaw-v1", "markdownUrl": "https://benchlm.ai/md/models/macaw-v1.md" }, { "canonicalModelKey": "mair-hub-0-5b-omni", "slug": "mair-hub-0-5b-omni", "model": "Mair-hub 0.5B Omni", "creator": "Mair Hub", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mair-hub-0-5b-omni", "markdownUrl": "https://benchlm.ai/md/models/mair-hub-0-5b-omni.md" }, { "canonicalModelKey": "megrez-3b-omni", "slug": "megrez-3b-omni", "model": "Megrez-3B-Omni", "creator": "Infinigence AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/megrez-3b-omni", "markdownUrl": "https://benchlm.ai/md/models/megrez-3b-omni.md" }, { "canonicalModelKey": "meralion-audiollm", "slug": "meralion-audiollm", "model": "MERaLiON-AudioLLM", "creator": "AI Singapore", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/meralion-audiollm", "markdownUrl": "https://benchlm.ai/md/models/meralion-audiollm.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": 0.025, "trainingPrice": null, "note": "Inception's official model page lists Mercury 2 at $0.25/M input, $0.025/M cached input, and $0.75/M output tokens.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 48.13, "overallRank": 147, "scorePerOutputDollar": 64.173, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md" }, { "canonicalModelKey": "mercury-2-5-preview", "slug": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "contextWindow": "260K", "contextWindowTokens": 260000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "OpenRouter lists a limited-time discounted route at $0.04 per million input tokens, $0.004 per million cached-input tokens, and $0.15 per million output tokens through September 8, 2026. Inception's first-party model and pricing documentation does not yet list the exact Mercury 2.5 Preview SKU, so BenchLM leaves canonical pricing unresolved instead of storing the temporary third-party promotion.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.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": 53.25, "overallRank": 115, "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": 59.46, "overallRank": 78, "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": 68.9, "overallRank": 20, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5-pro.md" }, { "canonicalModelKey": "mini-omni", "slug": "mini-omni", "model": "Mini-Omni 0.5B", "creator": "gpt-omni", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mini-omni", "markdownUrl": "https://benchlm.ai/md/models/mini-omni.md" }, { "canonicalModelKey": "mini-omni2", "slug": "mini-omni2", "model": "Mini-Omni2", "creator": "gpt-omni", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/mini-omni2", "markdownUrl": "https://benchlm.ai/md/models/mini-omni2.md" }, { "canonicalModelKey": "minicpm-o-2-6", "slug": "minicpm-o-2-6", "model": "MiniCPM-o 2.6", "creator": "OpenBMB", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/minicpm-o-2-6", "markdownUrl": "https://benchlm.ai/md/models/minicpm-o-2-6.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": 24.21, "overallRank": 214, "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": 58.49, "overallRank": 85, "scorePerOutputDollar": 48.742, "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": 62.85, "overallRank": 49, "scorePerOutputDollar": 52.375, "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": 0.06, "trainingPrice": null, "note": "MiniMax's official API pricing page lists the permanent 50%-off standard rate for MiniMax-M3 at $0.30 input / $0.06 cached input / $1.20 output per million tokens for prompts up to 512K. The 512K-to-1M tier is $0.60 / $0.12 / $2.40; BenchLM stores the standard short-context rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 68.17, "overallRank": 22, "scorePerOutputDollar": 56.808, "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": 34, "overallRank": 209, "scorePerOutputDollar": 170, "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": 49.99, "overallRank": 138, "scorePerOutputDollar": 249.95, "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": 17.93, "overallRank": 222, "scorePerOutputDollar": 179.3, "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": 40.07, "overallRank": 198, "scorePerOutputDollar": 400.7, "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": 20.38, "overallRank": 219, "scorePerOutputDollar": 135.867, "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": 40.94, "overallRank": 192, "scorePerOutputDollar": 272.933, "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": 40.45, "overallRank": 194, "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": 45.58, "overallRank": 167, "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": 39.68, "overallRank": 199, "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": 42.12, "overallRank": 186, "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": 49.6, "overallRank": 139, "scorePerOutputDollar": 33.067, "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": 43.49, "overallRank": 177, "scorePerOutputDollar": 21.745, "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": null, "overallRank": null, "scorePerOutputDollar": null, "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": 46.35, "overallRank": 160, "scorePerOutputDollar": 77.25, "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": null, "overallRank": null, "scorePerOutputDollar": null, "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": 49.19, "overallRank": 142, "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": 45.38, "overallRank": 168, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/moonshot-v1", "markdownUrl": "https://benchlm.ai/md/models/moonshot-v1.md" }, { "canonicalModelKey": "moshi-7b", "slug": "moshi-7b", "model": "Moshi 7B", "creator": "Kyutai", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/moshi-7b", "markdownUrl": "https://benchlm.ai/md/models/moshi-7b.md" }, { "canonicalModelKey": "muse-glimmer-30b", "slug": "muse-glimmer-30b", "model": "Muse Glimmer 30B", "creator": "Meta", "sourceType": "Open Weight", "contextWindow": "131K", "contextWindowTokens": 131000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Meta publishes Muse Glimmer 30B under Apache 2.0 for local and self-hosted use, including full-precision and 4-bit checkpoints. Meta did not publish a first-party hosted API token price at launch, so the pricing catalog represents the open checkpoint as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/muse-glimmer-30b", "markdownUrl": "https://benchlm.ai/md/models/muse-glimmer-30b.md" }, { "canonicalModelKey": "muse-spark-1-2", "slug": "muse-spark-1-2", "model": "Muse Spark 1.2", "creator": "Meta", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 1.25, "outputPrice": 4.25, "cachedInputPrice": 0.15, "trainingPrice": null, "note": "Meta Model API lists muse-spark-1.2 at $1.25 input, $0.15 cached input, and $4.25 output per million tokens. Meta separately lists muse-spark-1.2-contributor, whose data may be used to improve Meta products, at $0.10 input, $0.002 cached input, and $0.20 output per million tokens; BenchLM stores the standard non-contributor SKU as the headline rate.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": 61.29, "overallRank": 55, "scorePerOutputDollar": 14.421, "url": "https://benchlm.ai/models/muse-spark-1-2", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-2.md" }, { "canonicalModelKey": "muse-voice-transcribe", "slug": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Meta’s launch post confirms Meta Model API availability but does not publish a directly comparable text-token input/output rate for Muse Voice Transcribe.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.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": 53.63, "overallRank": 111, "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": 44.49, "overallRank": 172, "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": 50.73, "overallRank": 130, "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": 51.63, "overallRank": 121, "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": 45.68, "overallRank": 164, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md" }, { "canonicalModelKey": "nemotron-3-5-lightning-30b-a3b-nvfp4", "slug": "nemotron-3-5-lightning-30b-a3b-nvfp4", "model": "Nemotron 3.5 Lightning 30B A3B NVFP4", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "NVIDIA publishes this OpenMDW-1.1-licensed NVFP4 checkpoint for commercial self-hosting and does not publish a first-party hosted API token price. BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 26.55, "overallRank": 212, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-3-5-lightning-30b-a3b-nvfp4", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-5-lightning-30b-a3b-nvfp4.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": 44.99, "overallRank": 171, "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": 45.68, "overallRank": 165, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/nemotron-4-15b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-4-15b.md" }, { "canonicalModelKey": "next-gpt-7b", "slug": "next-gpt-7b", "model": "NExT-GPT 7B", "creator": "NExT-GPT authors", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/next-gpt-7b", "markdownUrl": "https://benchlm.ai/md/models/next-gpt-7b.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": 19.67, "overallRank": 220, "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": 48.18, "overallRank": 146, "scorePerOutputDollar": 0.803, "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": 48.48, "overallRank": 143, "scorePerOutputDollar": 0.808, "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": 46.12, "overallRank": 162, "scorePerOutputDollar": 0.077, "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": 46.82, "overallRank": 157, "scorePerOutputDollar": 5.853, "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": 46.69, "overallRank": 158, "scorePerOutputDollar": 10.611, "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": 47.2, "overallRank": 155, "scorePerOutputDollar": 0.59, "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": 50.62, "overallRank": 132, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/o4-mini-high", "markdownUrl": "https://benchlm.ai/md/models/o4-mini-high.md" }, { "canonicalModelKey": "ola-omni", "slug": "ola-omni", "model": "Ola", "creator": "Ola-Omni", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ola-omni", "markdownUrl": "https://benchlm.ai/md/models/ola-omni.md" }, { "canonicalModelKey": "ornith-1-0-35b", "slug": "ornith-1-0-35b", "model": "Ornith-1.0-35B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepReinforce publishes Ornith 1.0 checkpoints on Hugging Face under the MIT license. No first-party hosted API token price is published, so BenchLM represents local/self-hosted token pricing as free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ornith-1-0-35b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-35b.md" }, { "canonicalModelKey": "ornith-1-0-397b", "slug": "ornith-1-0-397b", "model": "Ornith-1.0-397B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepReinforce publishes Ornith 1.0 checkpoints on Hugging Face under the MIT license. No first-party hosted API token price is published, so BenchLM represents local/self-hosted token pricing as free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md" }, { "canonicalModelKey": "ornith-1-0-9b", "slug": "ornith-1-0-9b", "model": "Ornith-1.0-9B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "contextWindow": "256K", "contextWindowTokens": 256000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "DeepReinforce publishes Ornith 1.0 checkpoints on Hugging Face under the MIT license. No first-party hosted API token price is published, so BenchLM represents local/self-hosted token pricing as free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ornith-1-0-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-9b.md" }, { "canonicalModelKey": "ornith-1-5-35b-a3b", "slug": "ornith-1-5-35b-a3b", "model": "Ornith-1.5-35B-A3B", "creator": "Ornith AI", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Ornith publishes the MIT-licensed Ornith-1.5-35B-A3B checkpoint on Hugging Face for self-hosted use. Ornith does not publish a first-party hosted API token price for this exact model, so BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 47.9, "overallRank": 149, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ornith-1-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-35b-a3b.md" }, { "canonicalModelKey": "ornith-1-5-397b", "slug": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Ornith publishes the MIT-licensed Ornith-1.5-397B checkpoint on Hugging Face for self-hosted use. Ornith does not publish a first-party hosted API token price for this exact model, so BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 67.4, "overallRank": 25, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, { "canonicalModelKey": "ornith-1-5-9b", "slug": "ornith-1-5-9b", "model": "Ornith-1.5-9B", "creator": "Ornith AI", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Ornith publishes the MIT-licensed Ornith-1.5-9B checkpoint on Hugging Face for self-hosted use. Ornith does not publish a first-party hosted API token price for this exact model, so BenchLM represents it as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 37.33, "overallRank": 205, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-9b.md" }, { "canonicalModelKey": "pandagpt-7b", "slug": "pandagpt-7b", "model": "PandaGPT 7B", "creator": "PandaGPT authors", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/pandagpt-7b", "markdownUrl": "https://benchlm.ai/md/models/pandagpt-7b.md" }, { "canonicalModelKey": "parakeet-ctc-1-1b", "slug": "parakeet-ctc-1-1b", "model": "Parakeet CTC 1.1B", "creator": "NVIDIA", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/parakeet-ctc-1-1b", "markdownUrl": "https://benchlm.ai/md/models/parakeet-ctc-1-1b.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": 22.55, "overallRank": 216, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/phi-4", "markdownUrl": "https://benchlm.ai/md/models/phi-4.md" }, { "canonicalModelKey": "phi-4-multimodal-instruct", "slug": "phi-4-multimodal-instruct", "model": "Phi-4 Multimodal Instruct", "creator": "Microsoft", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/phi-4-multimodal-instruct", "markdownUrl": "https://benchlm.ai/md/models/phi-4-multimodal-instruct.md" }, { "canonicalModelKey": "pokee-isaac-28b", "slug": "pokee-isaac-28b", "model": "Pokee-Isaac 28B", "creator": "Pokee AI", "sourceType": "Proprietary", "contextWindow": "10M", "contextWindowTokens": 10000000, "inputPrice": 0.15, "outputPrice": 1, "cachedInputPrice": null, "trainingPrice": null, "note": "Pokee AI's official model page lists Pokee-Isaac 28B at $0.15 input / $1.00 output per million tokens and a 10M-token context window. The linked technical report labels those rates provisional and subject to confirmation at launch, so this note preserves that qualification.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/pokee-isaac-28b", "markdownUrl": "https://benchlm.ai/md/models/pokee-isaac-28b.md" }, { "canonicalModelKey": "qwen-audio-7b", "slug": "qwen-audio-7b", "model": "Qwen-Audio 7B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen-audio-7b", "markdownUrl": "https://benchlm.ai/md/models/qwen-audio-7b.md" }, { "canonicalModelKey": "qwen-audio-chat-7b", "slug": "qwen-audio-chat-7b", "model": "Qwen-Audio-Chat 7B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen-audio-chat-7b", "markdownUrl": "https://benchlm.ai/md/models/qwen-audio-chat-7b.md" }, { "canonicalModelKey": "qwen2-audio-7b-instruct", "slug": "qwen2-audio-7b-instruct", "model": "Qwen2-Audio 7B Instruct", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-audio-7b-instruct", "markdownUrl": "https://benchlm.ai/md/models/qwen2-audio-7b-instruct.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": 34.21, "overallRank": 208, "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": 50.54, "overallRank": 134, "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": 52.83, "overallRank": 117, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-5-72b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-72b.md" }, { "canonicalModelKey": "qwen2-5-omni-7b", "slug": "qwen2-5-omni-7b", "model": "Qwen2.5-Omni 7B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen2-5-omni-7b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-omni-7b.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": 40.4, "overallRank": 195, "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": 56.75, "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": 58.77, "overallRank": 83, "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": 57.75, "overallRank": 89, "scorePerOutputDollar": 16.042, "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": 60.27, "overallRank": 68, "scorePerOutputDollar": 16.742, "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": 47.56, "overallRank": 152, "scorePerOutputDollar": 118.9, "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": 47.79, "overallRank": 150, "scorePerOutputDollar": 19.913, "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": 59.49, "overallRank": 77, "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": 59.7, "overallRank": 74, "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": 56.09, "overallRank": 100, "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": 64.56, "overallRank": 40, "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": 53.57, "overallRank": 113, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, { "canonicalModelKey": "qwen3-7-flash", "slug": "qwen3-7-flash", "model": "Qwen3.7 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0.03, "outputPrice": 0.13, "cachedInputPrice": null, "trainingPrice": null, "note": "QwenCloud's official pricing page lists qwen3.7-flash at $0.03 input / $0.13 output per million tokens for requests up to 32K tokens, $0.10 / $0.40 above 32K through 256K, and $0.20 / $0.80 above 256K through 1M. BenchLM stores the lowest tier as the headline API rate and records the higher tiers here.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-flash.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": 71.27, "overallRank": 18, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, { "canonicalModelKey": "qwen3-8-max", "slug": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Qwen publishes the Qwen3.8-2.4T-A95B checkpoint for self-hosting under the custom Qwen3.8-Max License. Alibaba Cloud Model Studio's official pricing page separately lists the hosted qwen3.8-max SKU in both non-thinking and thinking modes for the 0 < Token <= 1M tier. The China and global tables list CNY 12 input / CNY 36 output per million tokens; the US international table lists CNY 14.988 input / CNY 44.965 output. The USD numeric fields stay null because we do not convert a non-USD first-party price.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": 78.55, "overallRank": 6, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, { "canonicalModelKey": "qwen3-8-max-preview", "slug": "qwen3-8-max-preview", "model": "Qwen3.8 Max Preview", "creator": "Alibaba", "sourceType": "Proprietary", "contextWindow": null, "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Historical July 19, 2026 preview entry. Alibaba made qwen3.8-max-preview available through subscription-based Token Plan, Qoder, and QoderWork access without publishing a standard pay-as-you-go per-token rate for that exact preview. The final qwen3.8-max release is stored as a separate priced SKU.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-8-max-preview", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max-preview.md" }, { "canonicalModelKey": "qwen3-8-27b", "slug": "qwen3-8-27b", "model": "Qwen3.8-27B", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Qwen publishes Qwen3.8-27B under Apache-2.0 for self-hosting and has not published a first-party hosted token rate for the exact model. BenchLM represents the open-weight row as self-host/free-per-token before infrastructure costs. Qwen Cloud says hosted access is coming soon, so the pricing row does not inherit Qwen3.8 Max rates.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 71.9, "overallRank": 17, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md" }, { "canonicalModelKey": "qwen3-8-flash-next", "slug": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "contextWindow": "262K", "contextWindowTokens": 262000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "Qwen publishes Qwen3.8-Flash-Next under the Qwen Community 1.0 license for self-hosting and does not publish a distinct first-party hosted token rate for this exact experimental checkpoint. BenchLM represents the open-weight row as self-host/free-per-token before infrastructure costs. Qwen Cloud's production Qwen3.8-Flash is a separate model based on this architecture, so this row does not inherit its price or default 1M context.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": 60.91, "overallRank": 64, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, { "canonicalModelKey": "sakana-fugu", "slug": "sakana-fugu", "model": "Sakana Fugu", "creator": "Sakana AI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Sakana AI's Fugu release and technical report describe Fugu and Fugu-Ultra as public model interfaces/orchestrators but do not publish a first-party token price in the reviewed sources.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sakana-fugu", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu.md" }, { "canonicalModelKey": "sakana-fugu-ultra", "slug": "sakana-fugu-ultra", "model": "Sakana Fugu-Ultra", "creator": "Sakana AI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "Sakana AI's Fugu release and technical report describe Fugu and Fugu-Ultra as public model interfaces/orchestrators but do not publish a first-party token price in the reviewed sources.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sakana-fugu-ultra", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-ultra.md" }, { "canonicalModelKey": "sakana-fugu-ultra-v1-1", "slug": "sakana-fugu-ultra-v1-1", "model": "Sakana Fugu-Ultra v1.1", "creator": "Sakana AI", "sourceType": "Proprietary", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 5, "outputPrice": 30, "cachedInputPrice": 0.5, "trainingPrice": null, "note": "Sakana AI says fugu-ultra-v1.1 keeps the same price as the prior Ultra version: $5.00 input / $30.00 output / $0.50 cached input per million tokens at or below 272K context, rising to $10.00 / $45.00 / $1.00 above 272K.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sakana-fugu-ultra-v1-1", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-ultra-v1-1.md" }, { "canonicalModelKey": "salmonn-13b", "slug": "salmonn-13b", "model": "SALMONN 13B", "creator": "SALMONN authors", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/salmonn-13b", "markdownUrl": "https://benchlm.ai/md/models/salmonn-13b.md" }, { "canonicalModelKey": "salmonn-7b", "slug": "salmonn-7b", "model": "SALMONN 7B", "creator": "SALMONN authors", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/salmonn-7b", "markdownUrl": "https://benchlm.ai/md/models/salmonn-7b.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": 43.26, "overallRank": 179, "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": 41.1, "overallRank": 190, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/sarvam-30b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-30b.md" }, { "canonicalModelKey": "scribe-v2-2-realtime", "slug": "scribe-v2-2-realtime", "model": "Scribe v2.2 Realtime", "creator": "ElevenLabs", "sourceType": "Proprietary", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The provider documentation does not publish a directly comparable text-token input/output rate for this exact realtime, speech, or audio model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/scribe-v2-2-realtime", "markdownUrl": "https://benchlm.ai/md/models/scribe-v2-2-realtime.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": 50.88, "overallRank": 126, "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": 45.68, "overallRank": 166, "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": 50.49, "overallRank": 136, "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": 45.19, "overallRank": 169, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/seed-2-0-mini", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-mini.md" }, { "canonicalModelKey": "slam-omni", "slug": "slam-omni", "model": "SLAM-Omni", "creator": "X-LANCE", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/slam-omni", "markdownUrl": "https://benchlm.ai/md/models/slam-omni.md" }, { "canonicalModelKey": "soofi-s-30b-a3b", "slug": "soofi-s-30b-a3b", "model": "Soofi S 30B-A3B", "creator": "Soofi Project", "sourceType": "Open Weight", "contextWindow": "1M", "contextWindowTokens": 1000000, "inputPrice": 0, "outputPrice": 0, "cachedInputPrice": null, "trainingPrice": null, "note": "The Soofi Project publishes the Soofi S 30B-A3B base weights under Apache 2.0 for local and self-hosted use. The repositories remain access-gated during the beta phase, and no first-party hosted API token price is published, so BenchLM represents the checkpoint as self-host/free-per-token before infrastructure costs.", "hasNumericPricing": true, "isFreePricing": true, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/soofi-s-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/soofi-s-30b-a3b.md" }, { "canonicalModelKey": "speechgpt-7b", "slug": "speechgpt-7b", "model": "SpeechGPT 7B", "creator": "OpenMOSS", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/speechgpt-7b", "markdownUrl": "https://benchlm.ai/md/models/speechgpt-7b.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": 54.22, "overallRank": 108, "scorePerOutputDollar": 180.733, "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": 50.83, "overallRank": 127, "scorePerOutputDollar": 44.2, "url": "https://benchlm.ai/models/step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-7-flash.md" }, { "canonicalModelKey": "step-audio", "slug": "step-audio", "model": "Step-Audio", "creator": "StepFun", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/step-audio", "markdownUrl": "https://benchlm.ai/md/models/step-audio.md" }, { "canonicalModelKey": "step-audio-chat-130b", "slug": "step-audio-chat-130b", "model": "Step-Audio-Chat 130B", "creator": "StepFun", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/step-audio-chat-130b", "markdownUrl": "https://benchlm.ai/md/models/step-audio-chat-130b.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": null, "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": null, "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": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ternary-bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-8b.md" }, { "canonicalModelKey": "toast-1", "slug": "toast-1", "model": "Toast 1", "creator": "Mixedbread", "sourceType": "Proprietary", "contextWindow": "131K", "contextWindowTokens": 131000, "inputPrice": 0.3, "outputPrice": 0.72, "cachedInputPrice": 0.036, "trainingPrice": null, "note": "Mixedbread's launch pricing lists Toast 1 at $0.30 input, $0.036 cached input, and $0.72 output per million LLM tokens; cache writes are free. Mixedbread labels these discounted launch rates and bills any Mixedbread Search calls separately.", "hasNumericPricing": true, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/toast-1", "markdownUrl": "https://benchlm.ai/md/models/toast-1.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": 56.67, "overallRank": 97, "scorePerOutputDollar": 56.67, "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": 47.92, "overallRank": 148, "scorePerOutputDollar": 53.244, "url": "https://benchlm.ai/models/trinity-large-thinking", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-thinking.md" }, { "canonicalModelKey": "ultravox-glm-4p6", "slug": "ultravox-glm-4p6", "model": "Ultravox GLM-4P6", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-glm-4p6", "markdownUrl": "https://benchlm.ai/md/models/ultravox-glm-4p6.md" }, { "canonicalModelKey": "ultravox-glm-4p7", "slug": "ultravox-glm-4p7", "model": "Ultravox GLM-4P7", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-glm-4p7", "markdownUrl": "https://benchlm.ai/md/models/ultravox-glm-4p7.md" }, { "canonicalModelKey": "ultravox-v0-4-1-llama-3-1-8b", "slug": "ultravox-v0-4-1-llama-3-1-8b", "model": "Ultravox v0.4.1 Llama 3.1 8B", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-v0-4-1-llama-3-1-8b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-4-1-llama-3-1-8b.md" }, { "canonicalModelKey": "ultravox-v0-5-llama-3-1-8b", "slug": "ultravox-v0-5-llama-3-1-8b", "model": "Ultravox v0.5 Llama 3.1 8B", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-v0-5-llama-3-1-8b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-5-llama-3-1-8b.md" }, { "canonicalModelKey": "ultravox-v0-5-llama-3-2-1b", "slug": "ultravox-v0-5-llama-3-2-1b", "model": "Ultravox v0.5 Llama 3.2 1B", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-v0-5-llama-3-2-1b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-5-llama-3-2-1b.md" }, { "canonicalModelKey": "ultravox-v0-6-llama-3-3-70b", "slug": "ultravox-v0-6-llama-3-3-70b", "model": "Ultravox v0.6 Llama 3.3 70B", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-v0-6-llama-3-3-70b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-6-llama-3-3-70b.md" }, { "canonicalModelKey": "ultravox-v0-7", "slug": "ultravox-v0-7", "model": "Ultravox v0.7", "creator": "Fixie AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/ultravox-v0-7", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-7.md" }, { "canonicalModelKey": "vita-1-0", "slug": "vita-1-0", "model": "VITA 1.0", "creator": "VITA-MLLM", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/vita-1-0", "markdownUrl": "https://benchlm.ai/md/models/vita-1-0.md" }, { "canonicalModelKey": "vita-1-5", "slug": "vita-1-5", "model": "VITA 1.5", "creator": "VITA-MLLM", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/vita-1-5", "markdownUrl": "https://benchlm.ai/md/models/vita-1-5.md" }, { "canonicalModelKey": "voxtral-4b-tts-2603", "slug": "voxtral-4b-tts-2603", "model": "Voxtral 4B TTS 2603", "creator": "Mistral AI", "sourceType": "Open Weight", "contextWindow": "N/A", "contextWindowTokens": 0, "inputPrice": null, "outputPrice": null, "cachedInputPrice": null, "trainingPrice": null, "note": "The linked first-party project publishes weights or implementation resources but no directly comparable first-party hosted token price for this exact voice model.", "hasNumericPricing": false, "isFreePricing": false, "displayScore": null, "overallRank": null, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/voxtral-4b-tts-2603", "markdownUrl": "https://benchlm.ai/md/models/voxtral-4b-tts-2603.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": 45.73, "overallRank": 163, "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": null, "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": 31.16, "overallRank": 210, "scorePerOutputDollar": null, "url": "https://benchlm.ai/models/zaya1-8b", "markdownUrl": "https://benchlm.ai/md/models/zaya1-8b.md" } ] }