self-hosted
Self-hostable open-weight models
Models with downloadable weights you can run yourself: Llama, Qwen, DeepSeek, Gemma, Phi, Mistral's open lines, and more.
What this is
Ranked by capability match + real benchmark scores + live pricing, daily-refreshed. Benchmark sources: Aider Polyglot (coding) and Artificial Analysis Intelligence Index (overall, coding, agentic). Full methodology →
Download this catalog: CSV · JSON (regenerated 2026-09-04), or query it live via the API.
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Qwen: Qwen3.8 Flash NEWqwen/qwen3.8-flash | — | $0.150 | $0.470 | 1,000,000 | Details → |
| 2 | DeepSeek: DeepSeek V4 Flash Vision Exp NEWdeepseek/deepseek-v4-flash-vision-exp | 90 3/5 | $0.220 | $0.660 | 1,048,576 | Details → |
| 3 | Qwen: Qwen3.8 27Bqwen/qwen3.8-27b | 89 3/5 | $0.420 | $3.000 | 1,000,000 | Details → |
| 4 | Qwen: Qwen3.8 Maxqwen/qwen3.8-max | 97 3/5 | $2.000 | $6.000 | 1,000,000 | Details → |
| 5 | Qwen: Qwen3.7 Flashqwen/qwen3.7-flash | — | $0.030 | $0.130 | 1,000,000 | Details → |
| 6 | Qwen: Qwen3.7 Plusqwen/qwen3.7-plus | 64 3/5 | $0.320 | $1.280 | 1,000,000 | Details → |
| 7 | NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | — | Free | Free | 256,000 | Details → |
| 8 | Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | — | $0.300 | $1.800 | 1,000,000 | Details → |
| 9 | Qwen: Qwen3.6 Flashqwen/qwen3.6-flash | — | $0.188 | $1.125 | 1,000,000 | Details → |
| 10 | Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | 52 3/5 | $0.100 | $0.900 | 262,144 | Details → |
| 11 | Qwen: Qwen3.6 27Bqwen/qwen3.6-27b | 65 3/5 | $0.600 | $3.600 | 262,144 | Details → |
| 12 | Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 52 4/5 | $0.070 | $0.340 | 262,144 | Details → |
| 13 | Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | 52 4/5 | Free | Free | 262,144 | Details → |
| 14 | Google: Gemma 4 31Bgoogle/gemma-4-31b-it | 56 4/5 | $0.090 | $0.340 | 262,144 | Details → |
| 15 | Google: Gemma 4 31B (batch)google/gemma-4-31b-it:batch | 56 4/5 | $0.390 | $0.970 | 262,144 | Details → |
| 16 | Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | 56 4/5 | Free | Free | 262,144 | Details → |
| 17 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | 68 3/5 | $0.325 | $1.950 | 1,000,000 | Details → |
| 18 | Mistral: Mistral Small 4mistralai/mistral-small-2603 | 6 1/5 | $0.150 | $0.600 | 262,144 | Details → |
| 19 | Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | 31 3/5 | $0.100 | $0.150 | 262,144 | Details → |
| 20 | Qwen: Qwen3.5-9B (batch)qwen/qwen3.5-9b:batch | 31 3/5 | $0.170 | $0.250 | 262,144 | Details → |
| 21 | Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | 48 1/5 | $0.250 | $1.250 | 262,144 | Details → |
| 22 | Qwen: Qwen3.5-27Bqwen/qwen3.5-27b | 56 1/5 | $0.195 | $1.560 | 262,144 | Details → |
| 23 | Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | 54 3/5 | $0.290 | $2.400 | 262,144 | Details → |
| 24 | Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | — | $0.065 | $0.260 | 1,000,000 | Details → |
| 25 | Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | — | $0.260 | $1.560 | 1,000,000 | Details → |
| 26 | Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | 63 4/5 | $0.550 | $3.500 | 262,144 | Details → |
| 27 | Mistral: Mistral Large 3 2512mistralai/mistral-large-2512 | — | $0.500 | $1.500 | 262,144 | Details → |
| 28 | Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking | — | $0.200 | $2.400 | 262,144 | Details → |
| 29 | NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | 34 3/5 | $0.080 | $0.200 | 262,144 | Details → |
| 30 | DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | — | $0.065 | $0.180 | 1,310,720 | Details → |
| 31 | DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | — | $0.089 | $0.177 | 1,048,576 | Details → |
| 32 | NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | 10 1/5 | $0.050 | $0.200 | 262,144 | Details → |
| 33 | DeepSeek: DeepSeek V4 Flash 0731 (batch)deepseek/deepseek-v4-flash-0731:batch | — | $0.140 | $0.280 | 1,048,576 | Details → |
| 34 | NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | 39 3/5 | $0.085 | $0.400 | 1,000,000 | Details → |
| 35 | Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 | — | $0.200 | $0.200 | 262,144 | Details → |
| 36 | Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | — | $0.150 | $0.150 | 262,144 | Details → |
| 37 | Meta: Llama 4 Scoutmeta-llama/llama-4-scout | 10 3/5 | $0.100 | $0.300 | 1,310,720 | Details → |
| 38 | Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct | 12 1/5 | $0.117 | $0.455 | 262,144 | Details → |
| 39 | Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct | 15 1/5 | $0.150 | $0.600 | 262,144 | Details → |
| 40 | Meta: Llama 4 Maverickmeta-llama/llama-4-maverick | 16 4/5 | $0.200 | $0.696 | 1,048,576 | Details → |
| 41 | Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking | — | $0.150 | $1.200 | 262,144 | Details → |
| 42 | Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | 22 1/5 | $0.210 | $1.900 | 262,144 | Details → |
| 43 | Mistral: Devstral 2 2512mistralai/devstral-2512 | — | $0.400 | $2.000 | 262,144 | Details → |
| 44 | DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro | 90 4/5 | $1.042 | $2.084 | 1,048,576 | Details → |
| 45 | NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | 63 3/5 | $0.625 | $3.125 | 262,144 | Details → |
| 46 | DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | — | $1.115 | $3.346 | 1,048,576 | Details → |
| 47 | Qwen: Qwen3 Max Thinkingqwen/qwen3-max-thinking | 53 1/5 | $0.780 | $3.900 | 262,144 | Details → |
| 48 | DeepSeek: DeepSeek V4 Pro 0813 (batch)deepseek/deepseek-v4-pro-0813:batch | — | $1.320 | $3.960 | 1,048,576 | Details → |
| 49 | Qwen: Qwen3.7 Maxqwen/qwen3.7-max | 76 3/5 | $1.475 | $4.425 | 1,000,000 | Details → |
| 50 | Qwen: Qwen3.6 Max Previewqwen/qwen3.6-max-preview | 67 1/5 | $1.027 | $6.162 | 262,144 | Details → |