self-hosted

Self-hostable open-weight models

Models from Llama, Mistral, Qwen, DeepSeek, and other vendors with downloadable weights.

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 →
#ModelScoreIn / 1MOut / 1MContext
1 Qwen: Qwen3.7 Plusqwen/qwen3.7-plus 100 $0.400 $1.600 1,000,000 Details →
2 Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash 100 $1.500 $9.000 1,048,576 Details →
3 Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite 100 $0.250 $1.500 1,048,576 Details →
4 Mistral: Mistral Medium 3.5mistralai/mistral-medium-3-5 100 $1.500 $7.500 262,144 Details →
5 NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free 100 Free Free 256,000 Details →
6 Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 100 $0.300 $1.800 1,000,000 Details →
7 Qwen: Qwen3.6 Flashqwen/qwen3.6-flash 100 $0.188 $1.125 1,000,000 Details →
8 Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b 100 $0.140 $1.000 262,144 Details →
9 Qwen: Qwen3.6 27Bqwen/qwen3.6-27b 100 $0.290 $3.200 262,144 Details →
10 Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free 100 Free Free 262,144 Details →
11 Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it 100 $0.060 $0.330 262,144 Details →
12 Google: Gemma 4 31B (free)google/gemma-4-31b-it:free 100 Free Free 262,144 Details →
13 Google: Gemma 4 31Bgoogle/gemma-4-31b-it 100 $0.120 $0.360 262,144 Details →
14 Qwen: Qwen3.6 Plusqwen/qwen3.6-plus 100 $0.325 $1.950 1,000,000 Details →
15 Mistral: Mistral Small 4mistralai/mistral-small-2603 100 $0.150 $0.600 262,144 Details →
16 Qwen: Qwen3.5-9Bqwen/qwen3.5-9b 100 $0.040 $0.150 262,144 Details →
17 Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview 100 $0.250 $1.500 1,048,576 Details →
18 Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b 100 $0.140 $1.000 262,144 Details →
19 Qwen: Qwen3.5-27Bqwen/qwen3.5-27b 100 $0.195 $1.560 262,144 Details →
20 Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b 100 $0.260 $2.080 262,144 Details →
21 Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 100 $0.065 $0.260 1,000,000 Details →
22 Google: Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools 100 $2.000 $12.000 1,048,756 Details →
23 Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview 100 $2.000 $12.000 1,048,576 Details →
24 Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 100 $0.260 $1.560 1,000,000 Details →
25 Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b 100 $0.390 $2.340 262,144 Details →
26 Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview 100 $0.500 $3.000 1,048,576 Details →
27 Mistral: Mistral Large 3 2512mistralai/mistral-large-2512 100 $0.500 $1.500 262,144 Details →
28 Qwen: Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking 100 $0.117 $1.365 256,000 Details →
29 Google: Gemini 2.5 Flash Lite Preview 09-2025google/gemini-2.5-flash-lite-preview-09-2025 100 $0.100 $0.400 1,048,576 Details →
30 Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite 100 $0.100 $0.400 1,048,576 Details →
31 Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash 100 $0.300 $2.500 1,048,576 Details →
32 Google: Gemini 2.5 Progoogle/gemini-2.5-pro 100 $1.250 $10.000 1,048,576 Details →
33 Google: Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview 100 $1.250 $10.000 1,048,576 Details →
34 Google: Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06 100 $1.250 $10.000 1,048,576 Details →
35 DeepSeek: DeepSeek V4 Flashdeepseek/deepseek-v4-flash 99 $0.098 $0.197 1,048,576 Details →
36 NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b 99 $0.050 $0.200 262,144 Details →
37 Qwen: Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 99 $0.100 $0.100 262,144 Details →
38 Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 99 $0.200 $0.200 262,144 Details →
39 Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 99 $0.150 $0.150 262,144 Details →
40 Meta: Llama 4 Scoutmeta-llama/llama-4-scout 99 $0.080 $0.300 10,000,000 Details →
41 NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b 99 $0.090 $0.450 1,000,000 Details →
42 Qwen: Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instruct 99 $0.104 $0.416 262,144 Details →
43 Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct 99 $0.080 $0.500 256,000 Details →
44 Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct 99 $0.130 $0.520 262,144 Details →
45 Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking 99 $0.098 $0.780 262,144 Details →
46 Meta: Llama 4 Maverickmeta-llama/llama-4-maverick 99 $0.150 $0.600 1,048,576 Details →
47 Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct 99 $0.200 $0.880 262,144 Details →
48 Qwen: Qwen Plus 0728 (thinking)qwen/qwen-plus-2025-07-28:thinking 99 $0.260 $0.780 1,000,000 Details →
49 Mistral: Codestral 2508mistralai/codestral-2508 99 $0.300 $0.900 256,000 Details →
50 DeepSeek: DeepSeek V4 Prodeepseek/deepseek-v4-pro 99 $0.435 $0.870 1,048,576 Details →