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 2026-10-19), or query it live via the API.

#ModelScoreIn / 1MOut / 1MContext
1 DeepSeek: DeepSeek V4.1 Flash 1017 NEWdeepseek/deepseek-v4.1-flash-1017 — $0.150 $0.600 1,048,576 Details →
2 NVIDIA: Nemotron 3.5 Super VL NEWnvidia/nemotron-3.5-super-vl 40 1/5 $0.100 $0.400 1,048,576 Details →
3 NVIDIA: Nemotron 3.5 Super VL (free) NEWnvidia/nemotron-3.5-super-vl:free 40 1/5 Free Free 1,000,000 Details →
4 Mistral: Mistral Large 4 NEWmistralai/mistral-large-4-0 — $0.680 $2.090 1,048,576 Details →
5 Qwen: Qwen3.8 Max Primeqwen/qwen3.8-max-prime — $4.000 $12.000 1,000,000 Details →
6 Cohere: Command A+cohere/command-a-plus 14 1/5 $0.300 $1.500 192,000 Details →
7 Qwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash — $0.150 $0.470 1,000,000 Details →
8 DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash 65 1/5 $0.047 $0.120 1,048,576 Details →
9 DeepSeek: DeepSeek V4.1 Flash (batch)deepseek/deepseek-v4.1-flash:batch 65 1/5 $0.050 $0.150 1,048,576 Details →
10 Qwen: Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 76 1/5 $2.000 $6.000 1,000,000 Details →
11 Qwen: Qwen3.8 Flashqwen/qwen3.8-flash — $0.150 $0.470 1,000,000 Details →
12 DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp 56 1/5 $0.216 $0.647 1,048,576 Details →
13 Qwen: Qwen3.8 27Bqwen/qwen3.8-27b 54 1/5 $0.240 $2.200 1,000,000 Details →
14 Qwen: Qwen3.7 Flashqwen/qwen3.7-flash — $0.030 $0.130 1,000,000 Details →
15 Qwen: Qwen3.7 Plusqwen/qwen3.7-plus 38 1/5 $0.320 $1.280 1,000,000 Details →
16 Qwen: Qwen3.7 Plus (batch)qwen/qwen3.7-plus:batch 38 1/5 $0.230 $0.920 262,144 Details →
17 NVIDIA: Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free — Free Free 256,000 Details →
18 Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 — $0.300 $1.800 1,000,000 Details →
19 Qwen: Qwen3.6 Flashqwen/qwen3.6-flash — $0.188 $1.125 1,000,000 Details →
20 Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b 24 1/5 $0.150 $1.000 262,144 Details →
21 Qwen: Qwen3.6 27Bqwen/qwen3.6-27b — $0.250 $2.000 262,144 Details →
22 Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it 49 2/5 $0.068 $0.225 262,144 Details →
23 Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free 49 2/5 Free Free 262,144 Details →
24 Google: Gemma 4 31Bgoogle/gemma-4-31b-it 48 2/5 $0.200 $0.400 262,144 Details →
25 Google: Gemma 4 31B (free)google/gemma-4-31b-it:free 48 2/5 Free Free 262,144 Details →
26 Qwen: Qwen3.6 Plusqwen/qwen3.6-plus — $0.325 $1.950 1,000,000 Details →
27 Mistral: Mistral Small 4mistralai/mistral-small-2603 — $0.150 $0.600 262,144 Details →
28 Mistral: Mistral Small 4 (batch)mistralai/mistral-small-2603:batch — $0.075 $0.300 262,144 Details →
29 Qwen: Qwen3.5-9Bqwen/qwen3.5-9b 11 1/5 $0.100 $0.150 262,144 Details →
30 Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b — $0.150 $1.000 262,144 Details →
31 Qwen: Qwen3.5-27Bqwen/qwen3.5-27b — $0.195 $1.560 262,144 Details →
32 Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b 19 1/5 $0.260 $2.080 262,144 Details →
33 Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 — $0.065 $0.260 1,000,000 Details →
34 Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 — $0.260 $1.560 1,000,000 Details →
35 Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b 52 2/5 $0.500 $3.600 262,144 Details →
36 Mistral: Mistral Large 3 2512mistralai/mistral-large-2512 — $0.500 $1.500 262,144 Details →
37 Mistral: Mistral Large 3 2512 (batch)mistralai/mistral-large-2512:batch — $0.250 $0.750 262,144 Details →
38 Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking — $0.290 $1.000 262,144 Details →
39 NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning 14 1/5 $0.070 $0.200 262,144 Details →
40 DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash — $0.091 $0.182 1,048,576 Details →
41 Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batch — $0.075 $0.075 262,144 Details →
42 DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 — $0.150 $0.150 1,048,576 Details →
43 NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b 2 1/5 $0.060 $0.240 262,144 Details →
44 Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 — $0.200 $0.200 262,144 Details →
45 Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 — $0.150 $0.150 262,144 Details →
46 Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct 60 1/5 $0.094 $0.250 256,000 Details →
47 Meta: Llama 4 Scoutmeta-llama/llama-4-scout 2 1/5 $0.100 $0.300 1,310,720 Details →
48 NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b — $0.080 $0.450 262,144 Details →
49 Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct — $0.150 $0.600 262,144 Details →
50 Meta: Llama 4 Maverickmeta-llama/llama-4-maverick 11 2/5 $0.188 $0.652 1,048,576 Details →

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.