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 →
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Qwen: Qwen3.7 Plusqwen/qwen3.7-plus | — | $0.320 | $1.280 | 1,000,000 | Details → |
| 2 | NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | — | Free | Free | 256,000 | Details → |
| 3 | Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | — | $0.300 | $1.800 | 1,000,000 | Details → |
| 4 | Qwen: Qwen3.6 Flashqwen/qwen3.6-flash | — | $0.188 | $1.125 | 1,000,000 | Details → |
| 5 | Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | — | $0.140 | $1.000 | 262,144 | Details → |
| 6 | Qwen: Qwen3.6 27Bqwen/qwen3.6-27b | — | $0.450 | $2.700 | 262,144 | Details → |
| 7 | Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 52 | $0.070 | $0.340 | 262,144 | Details → |
| 8 | Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | — | Free | Free | 262,144 | Details → |
| 9 | Google: Gemma 4 31Bgoogle/gemma-4-31b-it | 57 | $0.120 | $0.370 | 262,144 | Details → |
| 10 | Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | — | Free | Free | 262,144 | Details → |
| 11 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | — | $0.325 | $1.950 | 1,000,000 | Details → |
| 12 | Mistral: Mistral Small 4mistralai/mistral-small-2603 | — | $0.150 | $0.600 | 262,144 | Details → |
| 13 | Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | — | $0.100 | $0.150 | 262,144 | Details → |
| 14 | Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | — | $0.140 | $1.000 | 262,144 | Details → |
| 15 | Qwen: Qwen3.5-27Bqwen/qwen3.5-27b | — | $0.260 | $2.600 | 262,144 | Details → |
| 16 | Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | — | $0.260 | $2.080 | 262,144 | Details → |
| 17 | Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | — | $0.065 | $0.260 | 1,000,000 | Details → |
| 18 | Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | — | $0.260 | $1.560 | 1,000,000 | Details → |
| 19 | Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | 64 | $0.390 | $2.340 | 262,144 | Details → |
| 20 | Mistral: Mistral Large 3 2512mistralai/mistral-large-2512 | — | $0.500 | $1.500 | 262,144 | Details → |
| 21 | Qwen: Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking | — | $0.117 | $1.365 | 256,000 | Details → |
| 22 | DeepSeek: DeepSeek V4 Flashdeepseek/deepseek-v4-flash | 75 | $0.094 | $0.188 | 1,048,576 | Details → |
| 23 | NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | — | $0.050 | $0.200 | 262,144 | Details → |
| 24 | Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 | — | $0.200 | $0.200 | 262,144 | Details → |
| 25 | Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | — | $0.150 | $0.150 | 262,144 | Details → |
| 26 | Meta: Llama 4 Scoutmeta-llama/llama-4-scout | — | $0.100 | $0.300 | 10,000,000 | Details → |
| 27 | NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | — | $0.080 | $0.450 | 1,000,000 | Details → |
| 28 | Qwen: Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instruct | — | $0.104 | $0.416 | 262,144 | Details → |
| 29 | Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct | — | $0.117 | $0.455 | 256,000 | Details → |
| 30 | Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct | — | $0.130 | $0.520 | 262,144 | Details → |
| 31 | Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking | — | $0.098 | $0.780 | 262,144 | Details → |
| 32 | Qwen: Qwen Plus 0728 (thinking)qwen/qwen-plus-2025-07-28:thinking | — | $0.260 | $0.780 | 1,000,000 | Details → |
| 33 | Meta: Llama 4 Maverickmeta-llama/llama-4-maverick | 16 | $0.200 | $0.800 | 1,048,576 | Details → |
| 34 | DeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-pro | 82 | $0.435 | $0.870 | 1,048,576 | Details → |
| 35 | Mistral: Devstral 2 2512mistralai/devstral-2512 | — | $0.400 | $2.000 | 262,144 | Details → |
| 36 | Qwen: Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | — | $0.300 | $3.000 | 262,144 | Details → |
| 37 | NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | — | $0.600 | $3.600 | 1,000,000 | Details → |
| 38 | Qwen: Qwen3 Max Thinkingqwen/qwen3-max-thinking | — | $0.780 | $3.900 | 262,144 | Details → |
| 39 | Qwen: Qwen3.7 Maxqwen/qwen3.7-max | — | $1.475 | $4.425 | 1,000,000 | Details → |
| 40 | Qwen: Qwen3.6 Max Previewqwen/qwen3.6-max-preview | — | $1.040 | $6.240 | 262,144 | Details → |
| 41 | Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking | — | $0.130 | $1.560 | 131,072 | Details → |
| 42 | DeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2 | — | $0.269 | $0.400 | 163,840 | Details → |
| 43 | DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | — | $0.270 | $0.410 | 163,840 | Details → |
| 44 | Qwen: Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking | — | $0.260 | $2.600 | 131,072 | Details → |
| 45 | DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1 | — | $0.250 | $0.950 | 163,840 | Details → |
| 46 | Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | — | $0.100 | $0.300 | 262,144 | Details → |
| 47 | Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | — | $0.090 | $0.550 | 262,144 | Details → |
| 48 | Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | — | $0.098 | $0.780 | 262,144 | Details → |
| 49 | Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next | — | $0.110 | $0.800 | 262,144 | Details → |
| 50 | Qwen: Qwen Plus 0728qwen/qwen-plus-2025-07-28 | — | $0.260 | $0.780 | 1,000,000 | Details → |