Model catalogEvery AI model we track: prices, context, benchmarks and modalities
449 models tracked as of Oct 9, 2026. Models with enough sourced data have a full detail page; the rest appear here with what is known so far.
| 1 | Claude Fable 5.1 Anthropic | Text LLM | 80.2 | 100% confidence 100 percent, Full | $10.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 2 | Claude Opus 5.5 Anthropic | Text LLM | 78.4 | 100% confidence 100 percent, Full | $4.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 3 | GPT-6 Astra OpenAI | Text LLM | 77.5 | 100% confidence 100 percent, Full | $10.00OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 4 | Claude Fable 5 Anthropic | Text LLM | 76.8 | 100% confidence 100 percent, Full | $10.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 5 | Claude Opus 5 Anthropic | Text LLM | 74.9 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 6 | GPT-6.1 Sol OpenAI | Text LLM | 73.0 | 100% confidence 100 percent, Full | $2.00OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 7 | GPT-5.6 Sol OpenAI | Text LLM | 72.1 | 100% confidence 100 percent, Full | $4.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.6-sol
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 8 | Claude Opus 4.7 Anthropic | Text LLM | 71.2 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 9 | Kimi K3 Moonshot AI | Text LLM | 71.0 | 100% confidence 100 percent, Full | $3.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.moonshot.ai/docs/api/chat. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; moonshotai/kimi-k3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 10 | Claude Opus 4.6 Anthropic | Text LLM | 70.8 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 11 | Muse Spark 1.3 Meta | Text LLM | 70.1 | 93% confidence 93 percent, High | $1.25Meta API pricingOfficial Meta Standard tier; applies only to the versions explicitly listed by the provider. Contributor training-data-discount tier and cached input excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 12 | Gemini 3.7 Flash Google | Text LLM | 70.0 | 100% confidence 100 percent, Full | $0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 13 | GPT-5.4 OpenAI | Text LLM | 69.7 | 100% confidence 100 percent, Full | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 14 | GPT-5.5 OpenAI | Text LLM | 69.5 | 100% confidence 100 percent, Full | $5.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 15 | Claude Sonnet 5.5 Anthropic | Text LLM | 69.4 | 93% confidence 93 percent, High | $2.00Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 16 | GPT-6 Sol OpenAI | Text LLM | 68.9 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-6-sol
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 17 | Gemini 3.8 Flash Google | Text LLM | 68.8 | 100% confidence 100 percent, Full | $0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 18 | Qwen3.8 Max Alibaba / Qwen | Text LLM | 68.7 | 85% confidence 85 percent, High | $1.65Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 19 | Gemini 3.5 Flash Google | Text LLM | 68.3 | 100% confidence 100 percent, Full | $1.50Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 20 | Claude Sonnet 4.6 Anthropic | Text LLM | 68.3 | 100% confidence 100 percent, Full | $3.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 21 | GPT-5.6 Terra OpenAI | Text LLM | 68.2 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.6-terra
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 22 | Gemini 3.1 Pro Preview Google | Text LLM | 68.1 | 100% confidence 100 percent, Full | $2.00Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 23 | MiniMax-M3 MiniMax | Text LLM | 68.0 | 100% confidence 100 percent, Full | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 24 | GLM-5.3 Z.ai | Text LLM | 67.7 | 93% confidence 93 percent, High | $1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 25 | Claude Sonnet 5 Anthropic | Text LLM | 67.7 | 93% confidence 93 percent, High | $2.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 26 | Claude Opus 4.8 Anthropic | Text LLM | 67.5 | 100% confidence 100 percent, Full | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 27 | Grok 4.6 xAI | Text LLM | 66.6 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.6
Retrieved Oct 9, 2026 · MIT Open source ↗ | 500Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 28 | Inkling Thinking Machines Lab | Text LLM | 66.5 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 29 | Qwen3.6 Max Preview Alibaba / Qwen | Text LLM | 66.4 | 64% confidence 64 percent, Medium | $1.30Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤128K; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 30 | GLM-5.3-Flash Z.ai | Text LLM | 66.2 | 100% confidence 100 percent, Full | $0.15Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 31 | DeepSeek V4.1 Flash DeepSeek | Text LLM | 66.2 | 69% confidence 69 percent, Medium | $0.15DeepSeek pricingOfficial off-peak uncached rate; peak is 2x; time schedule at source
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 32 | Kimi K2 Thinking Turbo Moonshot AI | Text LLM | 66.1 | 64% confidence 64 percent, Medium | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 33 | GPT-5.2 OpenAI | Text LLM | 65.9 | 100% confidence 100 percent, Full | $1.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.2
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 34 | GLM-5.2 Z.ai | Text LLM | 65.7 | 100% confidence 100 percent, Full | $1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 35 | Gemini 3.6 Flash Google | Text LLM | 65.5 | 100% confidence 100 percent, Full | $0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 36 | Grok 4.7 xAI | Text LLM | 65.5 | 100% confidence 100 percent, Full | $2.00xAI models & pricingPublished source fact
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 500KxAI models & pricingPublished source fact
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 37 | Grok 4.5 xAI | Text LLM | 64.8 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 500Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 38 | Kimi K2.6 Moonshot AI | Text LLM | 64.0 | 85% confidence 85 percent, High | $0.95models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.moonshot.ai/docs/api/chat. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; moonshotai/kimi-k2.6
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 39 | Qwen3.5 397B-A17B Alibaba / Qwen | Text LLM | 64.0 | 69% confidence 69 percent, Medium | $0.17Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 40 | GPT-5.5 Pro OpenAI | Text LLM | 63.5 | 53% confidence 53 percent, Medium | $30.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.5-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 41 | GPT-5.6 Luna OpenAI | Text LLM | 63.4 | 100% confidence 100 percent, Full | $0.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.6-luna
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 42 | Gemma 4 26B A4B IT Google | Text LLM | 63.4 | 64% confidence 64 percent, Medium | $0.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 43 | GLM-5.1 Z.ai | Text LLM | 63.3 | 64% confidence 64 percent, Medium | $1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 44 | DeepSeek V4 Pro DeepSeek | Text LLM | 63.1 | 85% confidence 85 percent, High | $1.32LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 45 | Gemma 4 31B IT Google | Text LLM | 63.0 | 64% confidence 64 percent, Medium | $0.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 46 | DeepSeek V4 Pro 0813 DeepSeek | Text LLM | 63.0 | 69% confidence 69 percent, Medium | $0.66DeepSeek pricingOfficial off-peak uncached rate; peak is 2x; time schedule at source
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 47 | Muse Spark 1.1 Meta | Text LLM | 62.9 | 61% confidence 61 percent, Medium | $1.25Meta API pricingOfficial Meta Standard tier; applies only to the versions explicitly listed by the provider. Contributor training-data-discount tier and cached input excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 48 | Qwen3.7 Plus Alibaba / Qwen | Text LLM | 62.7 | 64% confidence 64 percent, Medium | $0.28Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 49 | Qwen3.5 35B-A3B Alibaba / Qwen | Text LLM | 62.7 | 64% confidence 64 percent, Medium | $0.06Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 50 | Claude Opus 4.5 Anthropic | Text LLM | 62.6 | 100% confidence 100 percent, Full | $5.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.anthropic.com/en/docs/about-claude/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; anthropic/claude-opus-4-5-20251101
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 51 | MiMo-V2.5-Pro Xiaomi | Text LLM | 62.6 | 88% confidence 88 percent, High | $0.43models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.5-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 52 | Muse Spark 1.2 Meta | Text LLM | 62.3 | 53% confidence 53 percent, Medium | $1.25Meta API pricingOfficial Meta Standard tier; applies only to the versions explicitly listed by the provider. Contributor training-data-discount tier and cached input excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 53 | Mistral Large 4 Mistral AI | Text LLM | 62.2 | 64% confidence 64 percent, Medium | $0.68Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 54 | Qwen3.8 27B Alibaba / Qwen | Text LLM | 61.9 | 69% confidence 69 percent, Medium | $0.50Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 55 | GPT-6 Luna OpenAI | Text LLM | 61.6 | 100% confidence 100 percent, Full | $0.10OpenAI pricingOfficial Standard short-context rate; excludes Batch/Flex/cache discounts
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 56 | Qwen3.6 Plus Alibaba / Qwen | Text LLM | 61.6 | 80% confidence 80 percent, High | $0.28Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 57 | GLM-4.7 Z.ai | Text LLM | 61.3 | 69% confidence 69 percent, Medium | $0.60Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 58 | GPT-5.4 Pro OpenAI | Text LLM | 61.3 | 69% confidence 69 percent, Medium | $30.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 59 | Nemotron 3 Ultra 550B A55B NVIDIA | Text LLM | 61.2 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 60 | DeepSeek V4 Flash 0731 DeepSeek | Text LLM | 61.0 | 69% confidence 69 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 61 | Hy3 Tencent | Text LLM | 60.7 | 88% confidence 88 percent, High | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://cloud.tencent.com/document/product/1823/130050. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; tencent-tokenhub/hy3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 62 | Claude Haiku 4.5 Anthropic | Text LLM | 60.5 | 64% confidence 64 percent, Medium | $1.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.anthropic.com/en/docs/about-claude/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; anthropic/claude-haiku-4-5-20251001
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 63 | Qwen3.5 Flash Alibaba / Qwen | Text LLM | 59.5 | 64% confidence 64 percent, Medium | $0.03Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 64 | Claude Haiku 5.5 Anthropic | Text LLM | 59.4 | 68% confidence 68 percent, Medium | $0.10Anthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1MAnthropic models & pricingOfficial Claude API; lowest short-context on-demand tier; batch/cache/long-context rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | — |
| 65 | GLM-5 Z.ai | Text LLM | 59.4 | 90% confidence 90 percent, High | $1.00Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 66 | Kimi K2.5 Moonshot AI | Text LLM | 59.0 | 100% confidence 100 percent, Full | $0.60LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 67 | Qwen3.7 Max Alibaba / Qwen | Text LLM | 58.6 | 53% confidence 53 percent, Medium | $1.65Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 68 | Gemini 3 Pro Preview Google | Text LLM | 58.6 | 68% confidence 68 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 69 | GPT-5.5 Instant OpenAI | Text LLM | 58.3 | 64% confidence 64 percent, Medium | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 70 | MiniMax-M2.7 MiniMax | Text LLM | 57.9 | 88% confidence 88 percent, High | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 71 | Fugu Ultra Sakana AI | Text LLM | 57.9 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 72 | MiniMax-M2.5 MiniMax | Text LLM | 57.8 | 100% confidence 100 percent, Full | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 73 | Grok 4.20 (Reasoning) xAI | Text LLM | 57.7 | 80% confidence 80 percent, High | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.20-0309-reasoning
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 74 | MiMo-V2.6-Pro Xiaomi | Text LLM | 57.4 | 88% confidence 88 percent, High | $0.43models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.6-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 75 | GPT-5.4 nano OpenAI | Text LLM | 57.4 | 100% confidence 100 percent, Full | $0.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-nano
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 76 | GPT-5.4 mini OpenAI | Text LLM | 56.9 | 100% confidence 100 percent, Full | $0.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.4-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 77 | LongCat-2.0 Meituan | Text LLM | 56.6 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 78 | MiMo-V2.5 Xiaomi | Text LLM | 56.4 | 88% confidence 88 percent, High | $0.14models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 79 | DeepSeek V4 Flash DeepSeek | Text LLM | 56.2 | 53% confidence 53 percent, Medium | $0.30LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 80 | Fugu Sakana AI | Text LLM | 55.9 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 81 | MiMo-V2.6-Flash Xiaomi | Text LLM | 55.8 | 88% confidence 88 percent, High | $0.14models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.6-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 82 | DeepSeek V3 0324 DeepSeek | Text LLM | 55.7 | 74% confidence 74 percent, Medium | not yet reported | 164Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 83 | GPT-5 OpenAI | Text LLM | 55.7 | 100% confidence 100 percent, Full | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 84 | MiniMax-M2 MiniMax | Text LLM | 55.7 | 96% confidence 96 percent, High | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 85 | GPT-5.1 OpenAI | Text LLM | 55.7 | 85% confidence 85 percent, High | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.1
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 86 | Qwen3.6 27B Alibaba / Qwen | Text LLM | 55.6 | 53% confidence 53 percent, Medium | $0.60Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 87 | Claude Opus 4 Anthropic | Text LLM | 55.5 | 100% confidence 100 percent, Full | $15.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 88 | o3 OpenAI | Text LLM | 55.4 | 87% confidence 87 percent, High | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/o3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 89 | Gemini 3.5 Flash Lite Google | Text LLM | 55.2 | 100% confidence 100 percent, Full | $0.30Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 90 | GPT OSS 120B OpenAI | Text LLM | 54.8 | 79% confidence 79 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 91 | Gemini 3 Flash Preview Google | Text LLM | 54.8 | 93% confidence 93 percent, High | $0.50Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 92 | Grok 4.3 xAI | Text LLM | 54.6 | 80% confidence 80 percent, High | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.3
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 93 | DeepSeek-V3 DeepSeek | Text LLM | 54.1 | 93% confidence 93 percent, High | $0.27LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 94 | Claude Sonnet 4.5 Anthropic | Text LLM | 53.9 | 80% confidence 80 percent, High | $3.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.anthropic.com/en/docs/about-claude/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; anthropic/claude-sonnet-4-5-20250929
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 95 | Inkling Small Thinking Machines Lab | Text LLM | 53.6 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 96 | DeepSeek V3.2 DeepSeek | Text LLM | 53.3 | 56% confidence 56 percent, Medium | $0.28LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 97 | GLM-4.7-Flash Z.ai | Text LLM | 53.3 | 69% confidence 69 percent, Medium | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-4.7-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 98 | Step 3.5 Flash StepFun | Text LLM | 53.0 | 88% confidence 88 percent, High | $0.10models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.stepfun.com/docs/zh/overview/concept. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; stepfun/step-3.5-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 99 | Qwen3 30B A3B Alibaba / Qwen | Text LLM | 52.6 | 64% confidence 64 percent, Medium | $0.11Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 100 | GPT OSS 20B OpenAI | Text LLM | 52.5 | 64% confidence 64 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 101 | Claude Sonnet 3.5 v2 Anthropic | Text LLM | 51.9 | 100% confidence 100 percent, Full | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 102 | Claude Opus 4.1 Anthropic | Text LLM | 51.5 | 80% confidence 80 percent, High | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 103 | o4-mini OpenAI | Text LLM | 51.2 | 87% confidence 87 percent, High | $1.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 104 | Llama 4 Scout 17B Instruct Meta | Text LLM | 51.0 | 64% confidence 64 percent, Medium | not yet reported | 10Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 105 | GPT-5 Mini OpenAI | Text LLM | 50.6 | 99% confidence 99 percent, High | $0.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 106 | Qwen3 32B Alibaba / Qwen | Text LLM | 50.4 | 67% confidence 67 percent, Medium | $0.16Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 107 | Qwen3 235B-A22B Alibaba / Qwen | Text LLM | 50.3 | 76% confidence 76 percent, Medium | $0.29Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 108 | Qwen3 Max Alibaba / Qwen | Text LLM | 50.2 | 69% confidence 69 percent, Medium | $0.36Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; Non-Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 109 | GPT-4o (2024-05-13) OpenAI | Text LLM | 49.4 | 93% confidence 93 percent, High | $5.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 110 | Claude Sonnet 3.7 Anthropic | Text LLM | 48.9 | 100% confidence 100 percent, Full | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 111 | Mistral Small 3.1 24B Mistral AI | Text LLM | 48.4 | 64% confidence 64 percent, Medium | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 112 | QwQ 32B Alibaba / Qwen | Text LLM | 48.2 | 67% confidence 67 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 113 | DeepSeek-R1 DeepSeek | Text LLM | 47.9 | 88% confidence 88 percent, High | $0.55LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 114 | GLM-4.6 Z.ai | Text LLM | 47.8 | 55% confidence 55 percent, Medium | $0.60Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 115 | Claude Sonnet 4 Anthropic | Text LLM | 46.6 | 100% confidence 100 percent, Full | $3.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 116 | Nemotron 3.5 Lightning 30B A3B NVIDIA | Text LLM | 46.1 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 117 | GPT-5 Pro OpenAI | Text LLM | 45.8 | 64% confidence 64 percent, Medium | $15.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 118 | Llama-3.1-70B-Instruct Meta | Text LLM | 45.7 | 93% confidence 93 percent, High | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 119 | Gemini 2.5 Pro Google | Text LLM | 45.2 | 90% confidence 90 percent, High | $1.25Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 120 | Gemma 3 12B IT Google | Text LLM | 45.1 | 64% confidence 64 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 121 | GPT-4o (2024-11-20) OpenAI | Text LLM | 42.2 | 61% confidence 61 percent, Medium | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o-2024-11-20
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 122 | Gemma 3 27B IT Google | Text LLM | 42.0 | 74% confidence 74 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 123 | o3-mini OpenAI | Text LLM | 41.6 | 96% confidence 96 percent, High | $1.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 124 | GPT-4.1 OpenAI | Text LLM | 41.5 | 100% confidence 100 percent, Full | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4.1
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 125 | Claude Haiku 3.5 Anthropic | Text LLM | 40.8 | 100% confidence 100 percent, Full | $0.80Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 126 | Claude Haiku 3 Anthropic | Text LLM | 39.9 | 93% confidence 93 percent, High | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 127 | Qwen2.5-Coder-32B-Instruct Alibaba / Qwen | Text LLM | 39.6 | 90% confidence 90 percent, High | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 128 | Gemma 3 4B IT Google | Text LLM | 39.2 | 64% confidence 64 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 129 | GPT-5 Nano OpenAI | Text LLM | 39.1 | 85% confidence 85 percent, High | $0.05models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5-nano
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 130 | Llama-3.1-8B-Instruct Meta | Text LLM | 37.7 | 93% confidence 93 percent, High | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 131 | Nova Pro Amazon | Text LLM | 37.4 | 100% confidence 100 percent, Full | not yet reported | 300Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 132 | GPT-4.1 mini OpenAI | Text LLM | 36.9 | 87% confidence 87 percent, High | $0.40models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4.1-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 133 | GPT-4o (2024-08-06) OpenAI | Text LLM | 36.7 | 100% confidence 100 percent, Full | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o-2024-08-06
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 134 | Nova Lite Amazon | Text LLM | 36.6 | 100% confidence 100 percent, Full | not yet reported | 300Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 135 | Mistral Large 2.1 Mistral AI | Text LLM | 35.3 | 100% confidence 100 percent, Full | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 136 | Mistral Medium 3 Mistral AI | Text LLM | 33.0 | 85% confidence 85 percent, High | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 137 | Llama-3.3-70B-Instruct Meta | Text LLM | 32.7 | 100% confidence 100 percent, Full | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 138 | Llama-3.2-1B Meta | Text LLM | 32.1 | 93% confidence 93 percent, High | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 139 | GPT-4.1 nano OpenAI | Text LLM | 32.1 | 82% confidence 82 percent, High | $0.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 140 | GPT-4o OpenAI | Text LLM | 31.2 | 59% confidence 59 percent, Medium | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| 141 | Llama 4 Maverick 17B Instruct Meta | Text LLM | 30.0 | 78% confidence 78 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| 142 | GPT-4o mini OpenAI | Text LLM | 22.9 | 100% confidence 100 percent, Full | $0.15models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-4o-mini
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Jamba Large AI21 Labs No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Jamba Mini AI21 Labs No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Gemma-SEA-LION-v4-27B-IT AI Singapore No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen Flash Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.02Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen-Image-2.1 Alibaba / Qwen Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 8.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen Max Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 53.0 | 75% confidence 75 percent, Medium | $1.60Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; No tiered pricing; Non-Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen-Omni Turbo Alibaba / Qwen Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | $0.07Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; standard tier; Non-Thinking mode. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen Plus Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.12Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen Turbo Alibaba / Qwen Evidence completeness 47.0%; at least 50% required | Text LLM | 46.6 | 47% confidence 47 percent, Low | $0.05Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; standard tier; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen-VL Max Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.80Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; No tiered pricing; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen-VL Plus Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.21Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; No tiered pricing; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen2.5-VL 72B Instruct Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.80models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://www.alibabacloud.com/help/en/model-studio/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; alibaba/qwen2-5-vl-72b-instruct
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen2.5-Coder-0.5B Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3 235B-A22B Instruct 2507 Alibaba / Qwen Evidence completeness 48.0%; at least 50% required | Text LLM | 42.4 | 48% confidence 48 percent, Low | $0.23Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3-Coder 30B-A3B Instruct Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 48.0 | 19% confidence 19 percent, Low | $0.22Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3-Coder 480B-A35B Instruct Alibaba / Qwen Evidence completeness 47.0%; at least 50% required | Text LLM | 52.7 | 47% confidence 47 percent, Low | $0.86Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3 Coder Flash Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.14Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3 Coder Next Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.30Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤32K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3 Coder Plus Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.57Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3-Next 80B-A3B Instruct Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 53.7 | 32% confidence 32 percent, Low | $0.14Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3-Next 80B-A3B (Thinking) Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 53.0 | 32% confidence 32 percent, Low | $0.14Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3 VL 235B A22B Instruct Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 53.8 | 32% confidence 32 percent, Low | $0.29Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Non-Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3 VL 235B A22B Thinking Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 53.5 | 32% confidence 32 percent, Low | $0.29Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; standard tier; Thinking mode only. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3-VL Plus Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.14Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.5 122B-A10B Alibaba / Qwen Evidence completeness 37.0%; at least 50% required | Text LLM | 56.8 | 37% confidence 37 percent, Low | $0.12Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3.5 27B Alibaba / Qwen Evidence completeness 37.0%; at least 50% required | Text LLM | 56.8 | 37% confidence 37 percent, Low | $0.09Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3.5 9B Alibaba / Qwen Evidence completeness 32.0%; at least 50% required | Text LLM | 55.1 | 32% confidence 32 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3.5 Plus Alibaba / Qwen Evidence completeness 32.0%; at least 50% required | Text LLM | 59.0 | 32% confidence 32 percent, Low | $0.12Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤128K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.6 35B-A3B Alibaba / Qwen Evidence completeness 37.0%; at least 50% required | Text LLM | 56.3 | 37% confidence 37 percent, Low | $0.25Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3.6 Flash Alibaba / Qwen Evidence completeness 32.0%; at least 50% required | Text LLM | 54.9 | 32% confidence 32 percent, Low | $0.17Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤256K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.7 Flash Alibaba / Qwen Evidence completeness 32.0%; at least 50% required | Text LLM | 54.5 | 32% confidence 32 percent, Low | $0.03Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤32K; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.8 2.4T A95B Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.00Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3.8 Flash Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.11Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.8 Flash Next Alibaba / Qwen Evidence completeness 21.0%; at least 50% required | Text LLM | 54.3 | 21% confidence 21 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Qwen3.8 Max 0902 Alibaba / Qwen Evidence completeness 40.0%; at least 50% required | Text LLM | 51.9 | 40% confidence 40 percent, Low | $1.65Alibaba Model Studio pricingOfficial Alibaba Model Studio Global USD on-demand API; 0<Token≤1M; Non-Thinking and Thinking modes. Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.8 Max Preview Alibaba / Qwen Evidence completeness 6.0%; at least 50% required | Text LLM | 50.9 | 6% confidence 6 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen 3.8 Max Prime Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Qwen3.8 Omni Flash Alibaba / Qwen No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.15models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://www.alibabacloud.com/help/en/model-studio/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; alibaba/qwen3.8-omni-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | QwQ Plus Alibaba / Qwen Results cover 1 pillar; at least 2 required | Text LLM | 53.9 | 32% confidence 32 percent, Low | $0.80Alibaba Model Studio pricingOfficial Alibaba Model Studio International USD on-demand API; standard tier; . Output uses non-thinking rate when both modes are available; thinking-only products use their thinking rate. Cache, Batch, free quotas and regional rates excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nova 2 Lite Amazon Results cover 1 pillar; at least 2 required | Text LLM | 52.9 | 100% confidence 100 percent, Full | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nova Micro Amazon Results cover 1 pillar; at least 2 required | Text LLM | 50.2 | 100% confidence 100 percent, Full | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nova Premier Amazon No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Haiku 4.5 (latest) Anthropic Evidence completeness 33.0%; at least 50% required | Text LLM | 47.3 | 33% confidence 33 percent, Low | $1.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Mythos 5 Anthropic Evidence completeness 5.0%; at least 50% required | Text LLM | 51.7 | 5% confidence 5 percent, Low | $10.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Opus 4 (latest) Anthropic No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Opus 4.1 (latest) Anthropic Results cover 1 pillar; at least 2 required | Text LLM | 46.4 | 14% confidence 14 percent, Low | $15.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Opus 4.5 (latest) Anthropic Results cover 1 pillar; at least 2 required | Text LLM | 53.1 | 14% confidence 14 percent, Low | $5.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Sonnet 4 (latest) Anthropic Results cover 1 pillar; at least 2 required | Text LLM | 49.7 | 6% confidence 6 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Claude Sonnet 4.5 (latest) Anthropic Evidence completeness 43.0%; at least 50% required | Text LLM | 48.2 | 43% confidence 43 percent, Low | $3.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Trinity Large Preview Arcee AI Results cover 1 pillar; at least 2 required | Text LLM | 52.5 | 100% confidence 100 percent, Full | not yet reported | 524Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Trinity Large Thinking Arcee AI Results cover 1 pillar; at least 2 required | Text LLM | 52.5 | 100% confidence 100 percent, Full | not yet reported | 524Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Trinity Mini Arcee AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Trinity Nano Preview Arcee AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Seed 1.6 ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 1.6 Flash ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 1.6 Vision ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 1.8 ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 2.0 Code ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 2.0 Lite ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 2.0 Mini ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 2.0 Pro ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 2.1 Pro ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed 2.1 Turbo ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed Character ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seed Evolving ByteDance Seed No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seedance 2.0 ByteDance Seed Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Seedance 2.5 ByteDance Seed Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Aya Expanse 32B Cohere Results cover 1 pillar; at least 2 required | Text LLM | 50.4 | 75% confidence 75 percent, Medium | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Aya Expanse 8B Cohere Results cover 1 pillar; at least 2 required | Text LLM | 49.7 | 75% confidence 75 percent, Medium | not yet reported | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Aya Vision 32B Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 16Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Aya Vision 8B Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 16Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command A Cohere Results cover 1 pillar; at least 2 required | Text LLM | 52.4 | 75% confidence 75 percent, Medium | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-a-03-2025
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command A Plus Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-a-plus-05-2026
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command A Reasoning Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-a-reasoning-08-2025
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command A Translate Cohere Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-a-translate-08-2025
Retrieved Oct 9, 2026 · MIT Open source ↗ | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command A Vision Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-a-vision-07-2025
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command R Cohere Results cover 1 pillar; at least 2 required | Text LLM | 49.8 | 75% confidence 75 percent, Medium | $0.15models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-r-08-2024
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command R+ Cohere Results cover 1 pillar; at least 2 required | Text LLM | 50.5 | 75% confidence 75 percent, Medium | $2.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-r-plus-08-2024
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command R7B Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.04models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-r7b-12-2024
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Command R7B Arabic Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.04models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.cohere.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; cohere/command-r7b-arabic-02-2025
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | North Mini Code Cohere Results cover 1 pillar; at least 2 required | Text LLM | 50.4 | 13% confidence 13 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | North Small Translate Cohere Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 16Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Tiny Aya Earth Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Tiny Aya Fire Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Tiny Aya Global Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Tiny Aya Water Cohere No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ornith 1.0 31B DeepReinforce No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ornith 1.0 35B DeepReinforce Results cover 1 pillar; at least 2 required | Text LLM | 53.5 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ornith 1.0 397B DeepReinforce Results cover 1 pillar; at least 2 required | Text LLM | 56.3 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ornith 1.0 9B DeepReinforce Results cover 1 pillar; at least 2 required | Text LLM | 50.4 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ornith 1.5 35B A3B DeepReinforce No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | DeepSeek Chat DeepSeek Evidence completeness 32.0%; at least 50% required | Text LLM | 53.5 | 32% confidence 32 percent, Low | $0.28LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | DeepSeek OCR 2 DeepSeek No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 8.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | DeepSeek-R1-Distill-Qwen-32B DeepSeek Evidence completeness 32.0%; at least 50% required | Text LLM | 52.9 | 32% confidence 32 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | DeepSeek Reasoner DeepSeek Evidence completeness 32.0%; at least 50% required | Text LLM | 58.9 | 32% confidence 32 percent, Low | $0.28LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | DeepSeek-V3.1 DeepSeek Results cover 1 pillar; at least 2 required | Text LLM | 53.7 | 32% confidence 32 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | DeepSeek V4 Flash Vision Exp DeepSeek Evidence completeness 21.0%; at least 50% required | Text LLM | 54.8 | 21% confidence 21 percent, Low | $0.30LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Deep Research Max Preview Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Deep Research Preview Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | DiffusionGemma 26B A4B IT Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Gemini 2.0 Flash Google Evidence completeness 28.0%; at least 50% required | Text LLM | 40.6 | 28% confidence 28 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 2.0 Flash-Lite Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 2.5 Computer Use Preview Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-2.5-computer-use-preview-10-2025
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 2.5 Flash Google Evidence completeness 47.0%; at least 50% required | Text LLM | 45.0 | 47% confidence 47 percent, Low | $0.30Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $0.30models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-2.5-flash-image
Retrieved Oct 9, 2026 · MIT Open source ↗ | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 2.5 Flash-Lite Google Results cover 1 pillar; at least 2 required | Text LLM | 48.0 | 6% confidence 6 percent, Low | $0.10Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 2.5 Flash TTS Google Speech / TTS: outside the text leaderboard | Speech / TTS | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 2.5 Pro TTS Google Speech / TTS: outside the text leaderboard | Speech / TTS | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana Pro Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3-pro-image
Retrieved Oct 9, 2026 · MIT Open source ↗ | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana Pro Preview Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3-pro-image-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana 2 Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $0.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.1-flash-image
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana 2 Preview Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $0.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.1-flash-image-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.1 Flash Lite Google Evidence completeness 32.0%; at least 50% required | Text LLM | 53.2 | 32% confidence 32 percent, Low | $0.25Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio
Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana 2 Lite Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $0.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.1-flash-lite-image
Retrieved Oct 9, 2026 · MIT Open source ↗ | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.1 Flash Lite Preview Google Evidence completeness 48.0%; at least 50% required | Text LLM | 42.6 | 48% confidence 48 percent, Low | $0.25LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.1 Flash Live Preview Google Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | $0.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.1-flash-live-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.1 Flash TTS Preview Google Speech / TTS: outside the text leaderboard | Speech / TTS | — | 0% confidence 0 percent, Low | $1.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.1-flash-tts-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 8.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.1 Pro Preview Custom Tools Google Results cover 1 pillar; at least 2 required | Text LLM | 56.4 | 32% confidence 32 percent, Low | $2.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.1-pro-preview-customtools
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.5 Live Translate Preview Google Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | $3.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-3.5-live-translate-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini 3.5 Transcribe Live Google Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Embedding 001 Google Embedding: outside the text leaderboard | Embedding | — | 0% confidence 0 percent, Low | $0.15models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-embedding-001
Retrieved Oct 9, 2026 · MIT Open source ↗ | 2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Embedding 2 Google Embedding: outside the text leaderboard | Embedding | — | 0% confidence 0 percent, Low | $0.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-embedding-2
Retrieved Oct 9, 2026 · MIT Open source ↗ | 8.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Flash Latest Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-flash-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Flash-Lite Latest Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.30models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-flash-lite-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Nano Banana 2.1 Google Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Omni Flash Preview Google Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | $1.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://ai.google.dev/gemini-api/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; google/gemini-omni-flash-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemini Robotics-ER 1.6 Preview Google Robotics: outside the text leaderboard | Robotics | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Gemma 4 12B IT Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Gemma 4 E2B IT Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Gemma 4 E4B IT Google No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Lyria 3 Clip Preview Google Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Lyria 3 Pro Preview Google Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Veo 3.1 Fast Preview Google Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 1Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Veo 3.1 Preview Google Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 1Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Veo 3.1 Lite Preview Google Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 1Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Granite-4.0-H-Micro IBM No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Granite-4.0-H-Small IBM No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ling 3.0 Flash Fin inclusionAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Ling 3.1 Flash inclusionAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | LongCat-2.5-Preview Meituan No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Llama-3.2-11B-Vision-Instruct Meta No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama-3.2-3B Meta Results cover 1 pillar; at least 2 required | Text LLM | 48.3 | 75% confidence 75 percent, Medium | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama-Guard-3-8B Meta No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Muse Glimmer 30B Meta Evidence completeness 6.0%; at least 50% required | Text LLM | 50.9 | 6% confidence 6 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MAI-Code-1-Flash Microsoft Results cover 1 pillar; at least 2 required | Text LLM | 50.1 | 100% confidence 100 percent, Full | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | MAI-Code-1.1-Flash Microsoft No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Phi-4-mini Microsoft No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniMax image-01 MiniMax Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | MiniMax H3 MiniMax Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniMax-M2 Her MiniMax No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | MiniMax-M2.1 MiniMax Results cover 1 pillar; at least 2 required | Text LLM | 50.6 | 13% confidence 13 percent, Low | $0.30MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniMax-M2.5-highspeed MiniMax No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.60MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniMax-M2.7-highspeed MiniMax No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.60MiniMax API pricingOfficial MiniMax global on-demand API; lowest short-context tier and displayed permanent promotional discount; excludes high-context, fast tier and subscriptions
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 205Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniMax-M3.1-Flash-Preview MiniMax No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Codestral-22B-v0.1 Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Codestral 25.08 Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.30models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/codestral-2508
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Codestral (latest) Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.30models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/codestral-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Devstral 2 Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 48.4 | 19% confidence 19 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Devstral Medium Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 50.5 | 6% confidence 6 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Devstral 2 (latest) Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.40LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://mistral.ai/news/devstral-2-vibe-cli. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Devstral Small 2 Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Devstral Small Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 49.3 | 19% confidence 19 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Magistral Medium (latest) Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 44.1 | 16% confidence 16 percent, Low | $1.50LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Magistral Small Mistral AI Evidence completeness 48.0%; at least 50% required | Text LLM | 37.1 | 48% confidence 48 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Magistral Small 1.2 Mistral AI Evidence completeness 32.0%; at least 50% required | Text LLM | 47.7 | 32% confidence 32 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ministral 14B Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ministral 3 14B Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.20Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ministral 3 3B Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.10Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ministral 3 8B Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.15Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ministral 3B Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Ministral 8B Instruct Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Embed Mistral AI Embedding: outside the text leaderboard | Embedding | — | 0% confidence 0 percent, Low | $0.10models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/mistral-embed
Retrieved Oct 9, 2026 · MIT Open source ↗ | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Mistral Large 3 Mistral AI Evidence completeness 37.0%; at least 50% required | Text LLM | 44.7 | 37% confidence 37 percent, Low | $0.50Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Large (latest) Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/mistral-large-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Medium 3.5 Mistral AI Evidence completeness 37.0%; at least 50% required | Text LLM | 58.1 | 37% confidence 37 percent, Low | $1.50Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Medium (latest) Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 51.2 | 6% confidence 6 percent, Low | $1.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/mistral-medium-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Nemo Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Small 3.2 Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 52.5 | 32% confidence 32 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Small 4 Mistral AI Results cover 1 pillar; at least 2 required | Text LLM | 48.5 | 6% confidence 6 percent, Low | $0.15Mistral API pricingOfficial Mistral Serverless API Standard rate, displayed sale price where applicable; cache, Batch, specialist units and hosted third-party models excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Small (latest) Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.15models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/mistral-small-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Pixtral 12B Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Pixtral Large (25.02) Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Pixtral Large (latest) Mistral AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Voxtral Mini 3B 2507 Mistral AI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Voxtral Small 24B 2507 Mistral AI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Voxtral Small (latest) Mistral AI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | $0.10models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.mistral.ai/getting-started/models/. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; mistral/voxtral-small-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 32Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Toast 1 Mixedbread No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Kimi K2 Thinking Moonshot AI Results cover 1 pillar; at least 2 required | Text LLM | 52.1 | 19% confidence 19 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Kimi K2.7 Code Moonshot AI Evidence completeness 48.0%; at least 50% required | Text LLM | 56.3 | 48% confidence 48 percent, Low | $0.95models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.moonshot.ai/docs/api/chat. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; moonshotai/kimi-k2.7-code
Retrieved Oct 9, 2026 · MIT Open source ↗ | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Kimi K2.7 Code Highspeed Moonshot AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Kimi K2.8 Preview Moonshot AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Motif 3 Motif Technologies No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nex-N2-Pro Nex AGI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama 3.1 Nemotron 70B Instruct NVIDIA Results cover 1 pillar; at least 2 required | Text LLM | 51.5 | 100% confidence 100 percent, Full | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama 3.1 Nemotron Safety Guard 8B v3 NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama 3.1 Nemotron Ultra 253B NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama 3.3 Nemotron Super 49B v1 NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama 3.3 Nemotron Super 49B v1.5 NVIDIA Results cover 1 pillar; at least 2 required | Text LLM | 52.5 | 100% confidence 100 percent, Full | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama Nemotron Embed VL 1B v2 NVIDIA Embedding: outside the text leaderboard | Embedding | — | 0% confidence 0 percent, Low | not yet reported | 32.8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Llama Nemotron Rerank VL 1B v2 NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Mistral Nemotron NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron 3 Content Safety NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron 3 Nano 30B A3B NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron 3 Super 120B A12B NVIDIA Results cover 1 pillar; at least 2 required | Text LLM | 53.1 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron 3.5 Content Safety NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron Cascade 2 30B A3B NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron Content Safety Reasoning 4B NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron Mini 4B Instruct NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron Nano 12B v2 VL NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron Nano 9B v2 NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Nemotron VoiceChat NVIDIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GPT-3.5-turbo OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.50LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 16.4Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-4 OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $30.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 8.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-4 Turbo OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $10.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5 Chat (latest) OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.25LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/models/gpt-5-chat-latest. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5-Codex OpenAI Results cover 1 pillar; at least 2 required | Text LLM | 49.5 | 6% confidence 6 percent, Low | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.1 Chat OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.25LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.1 Codex OpenAI Results cover 1 pillar; at least 2 required | Text LLM | 51.8 | 14% confidence 14 percent, Low | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.1 Codex Max OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.1 Codex mini OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.2 Chat OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.75LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.2 Codex OpenAI Evidence completeness 43.0%; at least 50% required | Text LLM | 57.8 | 43% confidence 43 percent, Low | not yet reported | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.2 Pro OpenAI Evidence completeness 48.0%; at least 50% required | Text LLM | 55.8 | 48% confidence 48 percent, Low | $21.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.2-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.3 Chat (latest) OpenAI Results cover 1 pillar; at least 2 required | Text LLM | 53.3 | 32% confidence 32 percent, Low | $1.75LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.3 Codex OpenAI Results cover 1 pillar; at least 2 required | Text LLM | 56.2 | 32% confidence 32 percent, Low | $1.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.3-codex
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.3 Codex Spark OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.3-codex-spark
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-5.6 Cyber OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $12.50models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-daybreak-red-latest
Retrieved Oct 9, 2026 · MIT Open source ↗ | 400Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-6 Astra (Fast) OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-Image-1 OpenAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-Image-1.5 OpenAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT-Image-2 OpenAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | $5.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-image-2
Retrieved Oct 9, 2026 · MIT Open source ↗ | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT Image 2.5 Flare OpenAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT Image 2.5 Sunburst OpenAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 0models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT OSS Safeguard 120B OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GPT OSS Safeguard 20B OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GPT-Realtime-2.1 OpenAI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | $4.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-realtime-2.1
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GPT Realtime Whisper OpenAI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 16Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | o1 OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $15.00LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | o1-pro OpenAI Results cover 1 pillar; at least 2 required | Text LLM | 44.7 | 16% confidence 16 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | o3-deep-research OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | o3-pro OpenAI Evidence completeness 22.0%; at least 50% required | Text LLM | 52.0 | 22% confidence 22 percent, Low | $20.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/o3-pro
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | o4-mini-deep-research OpenAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Whisper 3 Large OpenAI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 448models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Whisper Large v3 Turbo OpenAI Audio: outside the text leaderboard | Audio | — | 0% confidence 0 percent, Low | not yet reported | 448models.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniCPM5-1B OpenBMB No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiniCPM5-2B OpenBMB No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Sonar Perplexity No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Sonar Deep Research Perplexity No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Sonar Pro Perplexity No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Sonar Reasoning Pro Perplexity No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Laguna M.1 Poolside No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Laguna S 2.1 Poolside No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Laguna XS 2.1 Poolside Results cover 1 pillar; at least 2 required | Text LLM | 50.5 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Laguna XS.2 Poolside No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Arrow 2 Quiver AI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Arrow 2 Telos Quiver AI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 1.1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Sakana Namazu Sakana AI Results cover 1 pillar; at least 2 required | Text LLM | 53.5 | 100% confidence 100 percent, Full | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Sarvam 105B Sarvam AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Sarvam 30B Sarvam AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | ALLaM-2-7b SDAIA No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 4.1Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Step 3.5 Flash 2603 StepFun Results cover 1 pillar; at least 2 required | Text LLM | 48.5 | 13% confidence 13 percent, Low | $0.10models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.stepfun.com/docs/zh/overview/concept. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; stepfun/step-3.5-flash-2603
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Step 3.7 Flash StepFun Evidence completeness 13.0%; at least 50% required | Text LLM | 50.3 | 13% confidence 13 percent, Low | $0.18models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.stepfun.com/docs/zh/overview/concept. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; stepfun/step-3.7-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Step 5 Preview StepFun Results cover 1 pillar; at least 2 required | Text LLM | 54.1 | 75% confidence 75 percent, Medium | $0.96models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.stepfun.com/docs/zh/overview/concept. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; stepfun/step-5-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Apertus 70B Swiss AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Apertus 8B Swiss AI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Hy3 preview Tencent Results cover 1 pillar; at least 2 required | Text LLM | 52.1 | 13% confidence 13 percent, Low | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://cloud.tencent.com/document/product/1823/130050. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; tencent-tokenhub/hy3-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Hy4 preview Tencent No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.83models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://cloud.tencent.com/document/product/1823/130050. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; tencent-tokenhub/hy4-preview
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Trendyol Asure 12B Trendyol No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | Pareto Unbiased No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Solar Pro 2 Upstage No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 65.5Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Solar Pro 3 Upstage No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Solar Pro 4 Upstage Results cover 1 pillar; at least 2 required | Text LLM | 53.3 | 100% confidence 100 percent, Full | not yet reported | 524Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Vision Large Vispark No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Vision Medium Vispark No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Vision Small Vispark No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Viv Fast Vivgrid No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Palmyra X4 Writer No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Palmyra X5 Writer No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok 4.1 Fast xAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 2Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok 4.1 Fast (Reasoning) xAI Results cover 1 pillar; at least 2 required | Text LLM | 53.6 | 32% confidence 32 percent, Low | not yet reported | 2Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok 4.20 (Non-Reasoning) xAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.25models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-4.20-0309-non-reasoning
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Build 0.1 xAI Evidence completeness 16.0%; at least 50% required | Text LLM | 52.0 | 16% confidence 16 percent, Low | $1.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.x.ai/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xai/grok-build-0.1
Retrieved Oct 9, 2026 · MIT Open source ↗ | 256Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Imagine Image 2.0 xAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 8Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Imagine Image Quality xAI Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 16Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Imagine Video 1.5 xAI Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 1Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Imagine Video 1.5 Lite xAI Video: outside the text leaderboard | Video | — | 0% confidence 0 percent, Low | not yet reported | 1Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Voice STT 1.0 xAI No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | not yet reported | 15Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | Grok Voice TTS 1.0 xAI Speech / TTS: outside the text leaderboard | Speech / TTS | — | 0% confidence 0 percent, Low | not yet reported | 15Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | MiMo-V2-Flash Xiaomi Results cover 1 pillar; at least 2 required | Text LLM | 53.4 | 75% confidence 75 percent, Medium | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiMo-V2-Omni Xiaomi Results cover 1 pillar; at least 2 required | Text LLM | 53.8 | 75% confidence 75 percent, Medium | not yet reported | 262Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | MiMo-V2-Pro Xiaomi Results cover 1 pillar; at least 2 required | Text LLM | 54.0 | 75% confidence 75 percent, Medium | not yet reported | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | MiMo-V2.5-Pro-UltraSpeed Xiaomi No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.30models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.5-pro-ultraspeed
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | MiMo-V2.6-Pro-UltraSpeed Xiaomi No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $4.35models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.xiaomimimo.com/#/docs. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; xiaomi/mimo-v2.6-pro-ultraspeed
Retrieved Oct 9, 2026 · MIT Open source ↗ | 1Mmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-4.5 Z.ai Evidence completeness 47.0%; at least 50% required | Text LLM | 51.0 | 47% confidence 47 percent, Low | $0.60Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-4.5-Air Z.ai Evidence completeness 37.0%; at least 50% required | Text LLM | 45.3 | 37% confidence 37 percent, Low | $0.20Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-4.5-AirX Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.10Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | not yet reported | not yet reported |
| — | GLM-4.5-Flash Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-4.5-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 131Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GLM-4.5-X Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $2.20Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | not yet reported | not yet reported |
| — | GLM-4.5V Z.ai Evidence completeness 37.0%; at least 50% required | Text LLM | 41.6 | 37% confidence 37 percent, Low | $0.60models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-4.5v
Retrieved Oct 9, 2026 · MIT Open source ↗ | 64Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-4.6V Z.ai Results cover 1 pillar; at least 2 required | Text LLM | 53.1 | 32% confidence 32 percent, Low | $0.30models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-4.6v
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-4.6V-Flash Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-4.6v-flash
Retrieved Oct 9, 2026 · MIT Open source ↗ | 128Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-4.7-FlashX Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.07Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
| — | GLM-5-Turbo Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $1.20models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://docs.z.ai/guides/overview/pricing. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; zai/glm-5-turbo
Retrieved Oct 9, 2026 · MIT Open source ↗ | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GLM-5.3-FlashX Z.ai No usable open benchmark results found | Text LLM | — | 0% confidence 0 percent, Low | $0.37Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded
Retrieved Oct 9, 2026 · factual citation Open source ↗ | not yet reported | not yet reported |
| — | GLM-5V-Turbo Z.ai Results cover 1 pillar; at least 2 required | Text LLM | 54.0 | 32% confidence 32 percent, Low | not yet reported | 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | — |
| — | GLM-Image Z.ai Image: outside the text leaderboard | Image | — | 0% confidence 0 percent, Low | not yet reported | 10.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT Open source ↗ | Open |
All model kinds appear in this catalog. The general leaderboard covers text LLMs with enough evidence. Browse every kind in the model catalog. Prices are USD per 1M tokens (official first-party API). Dotted values carry their source: hover or tap to see it. “Not yet reported” means the source hasn’t published that figure for this model.