Free long-context models
Models with a context window of 256K tokens or more — for RAG without chunking, whole-repository reviews, and long documents.
84 models14 providersup to 10.5M contextbest: GLM 5.3 FlashUpdated:
Read more
Free routes often cap context below the model's maximum. The column shows the provider-specific limit.
| # | Model ↕ | AA Index ↕ | GPQA ↕ | Context ↕ | Size ↕ | Free at ↕ | |
|---|---|---|---|---|---|---|---|
| 1 |  |
8.1 | 59% | 10.5M | Frontier |    Together AI, Cloudflare Workers AI, UnoRouter |
|
| 2 |  |
44.8 | 92% | 1M | Frontier | Together AI |
|
| 3 |  |
40.9 | 95% | 1M | Mid-size | Google AI Studio |
|
| 4 | |
33.7 | 90% | 1M | Frontier | Together AI |
|
| 5 | 27.8 | 90% | 1M | Small |  OpenRouter |
||
| 6 |  |
22.9 | 87% | 1M | Frontier |  OpenRouter, NVIDIA Build, UnoRouter |
|
| 7 | 25.0 | 87% | 1M | Small | OpenRouter |
||
| 8 | |
— | — | 1M | Frontier | Together AI |
|
| 9 | |
— | — | 1M | Mid-size |  OpenRouter, UnoRouter, OpenCode Zen |
|
| 10 |  |
11.7 | 70% | 1M | Frontier | Together AI |
|
| 11 | |
10.0 | 68% | 1M | Frontier | Together AI |
|
| 12 | — | — | 1M | Small |  Vercel AI Gateway, UnoRouter, OpenCode Zen |
||
| 13 | |
41.8 | 91% | 1M | Mid-size |  OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen |
|
| 14 |  |
39.5 | — | 1M | Frontier | OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen |
|
| 15 | |
41.8 | 91% | 1M | Mid-size | UnoRouter |
|
| 16 | |
34.0 | 93% | 1M | Mid-size | UnoRouter |
|
| 17 | |
22.2 | 84% | 1M | Small | UnoRouter |
|
| 18 | |
12.9 | 74% | 1M | Mid-size | +1OpenRouter, NVIDIA Build, Vercel AI Gateway, UnoRouter, OpenCode Zen |
|
| 19 | |
15.6 | 82% | 1M | Small | UnoRouter |
|
| 20 |  |
— | — | 1M | Frontier | UnoRouter |
|
| 21 | |
— | — | 1M | Mid-size | UnoRouter |
|
| 22 | |
— | — | 1M | Mid-size | UnoRouter |
|
| 23 | — | — | 1M | Small | UnoRouter |
||
| 24 |
Solar Mini 4
Upstage
|
— | — | 524K | Small |  Nous Portal |
|
| 25 | — | — | 524K | Small | UnoRouter |
||
| 26 |
Dots3-Note Preview
Dots Studio
|
— | — | 512K | Small | OpenRouter, UnoRouter |
|
| 27 | — | — | 512K | Small | UnoRouter |
||
| 28 | 
Command A Plus 05 2026
Cohere · 111B · Legacy
|
— | — | 436K | Frontier | Cohere |
|
| 29 | |
— | — | 289K | Frontier | Cohere |
|
| 30 |
Command A 03 2025
Cohere · 111B · Legacy
|
— | — | 288K | Frontier | Cohere |
|
| 31 | |
33.7 | 91% | 262K | Mid-size |  Groq, Cloudflare Workers AI, UnoRouter |
|
| 32 |  |
19.0 | 86% | 262K | Mid-size | OpenRouter, Together AI, NVIDIA Build, UnoRouter |
|
| 33 | |
16.7 | 79% | 262K | Mid-size | OpenRouter, Together AI, Cloudflare Workers AI, UnoRouter |
|
| 34 | |
18.2 | 84% | 262K | Mid-size | Together AI, UnoRouter |
|
| 35 |  |
19.5 | 81% | 262K | Frontier | Nous Portal |
|
| 36 | |
19.3 | 85% | 262K | Mid-size | Together AI |
|
| 37 | |
17.7 | 83% | 262K | Frontier | Together AI |
|
| 38 | |
14.2 | 75% | 262K | Mid-size | Together AI, UnoRouter |
|
| 39 | |
13.7 | 81% | 262K | Small | Together AI, UnoRouter |
|
| 40 | |
10.3 | 47% | 262K | Mid-size |  +1OpenRouter, Together AI, NVIDIA Build, TokenRouter, UnoRouter |
|
| 41 | |
12.8 | 80% | 262K | Frontier | NVIDIA Build, UnoRouter |
|
| 42 |
Ornith 1.5 122B
Ornith · 122B
|
— | — | 262K | Frontier | Nous Portal |
|
| 43 |
Beam 1.0 501B A23B
Reflection · 501B · 23B
|
— | — | 262K | Frontier | Nous Portal |
|
| 44 | — | — | 262K | Frontier | UnoRouter |
||
| 45 | — | — | 262K | Frontier | UnoRouter |
||
| 46 |  |
— | — | 262K | Frontier | UnoRouter |
|
| 47 | |
13.4 | 77% | 262K | Frontier | Together AI |
|
| 48 | |
13.1 | 77% | 262K | Small | UnoRouter |
|
| 49 | |
12.8 | 80% | 262K | Frontier | Together AI |
|
| 50 | |
12.7 | 79% | 262K | Frontier | Together AI |
|
| 51 | |
9.9 | 76% | 262K | Small | OpenRouter, UnoRouter |
|
| 52 | |
9.8 | 71% | 262K | Mid-size | Together AI, Cloudflare Workers AI |
|
| 53 | |
9.6 | 52% | 262K | Frontier | Together AI |
|
| 54 | |
9.5 | 67% | 262K | Mid-size | UnoRouter |
|
| 55 |
Xing4.0 29B A4B
XingChen · 29B · 4B
|
— | — | 262K | Mid-size | OpenRouter |
|
| 56 | — | — | 262K | Mid-size | Together AI |
||
| 57 | 
Holo3 35B A3B
35B · 3B
|
— | — | 262K | Mid-size | Together AI |
|
| 58 | — | — | 262K | Mid-size | UnoRouter |
||
| 59 | — | — | 262K | Mid-size | UnoRouter |
||
| 60 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 61 | |
8.9 | 76% | 262K | Mid-size | Together AI |
|
| 62 | |
8.8 | 67% | 262K | Small | Together AI |
|
| 63 | |
6.9 | 46% | 262K | Small | Together AI |
|
| 64 | — | — | 262K | Small | NVIDIA Build, UnoRouter |
||
| 65 |
Flint
Recursive
|
— | — | 262K | Small | OpenRouter |
|
| 66 | — | — | 262K | Small | Cloudflare Workers AI |
||
| 67 | — | — | 262K | Small | UnoRouter |
||
| 68 | — | — | 262K | Small | UnoRouter |
||
| 69 | — | — | 262K | Small | Cloudflare Workers AI |
||
| 70 | |
21.4 | 86% | 262K | Frontier | UnoRouter |
|
| 71 | |
21.4 | 84% | 262K | Mid-size | UnoRouter |
|
| 72 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 73 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 74 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 75 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 76 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 77 | |
— | — | 262K | Mid-size | UnoRouter |
|
| 78 | |
5.8 | 38% | 262K | Mid-size | Mistral AI, UnoRouter |
|
| 79 | — | — | 262K | Small | UnoRouter |
||
| 80 | 12.3 | — | 260K | Small | UnoRouter |
||
| 81 | |
— | — | 256K | Frontier | Cloudflare Workers AI |
|
| 82 |
Cohere Command A
Cohere · 111B · Legacy
|
— | — | 256K | Frontier | UnoRouter |
|
| 83 | |
— | — | 256K | Small | Mistral AI |
|
| 84 | |
— | — | 256K | Small | UnoRouter |
No models match your filters.
Benchmarks: Artificial Analysis (September 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.
FAQ
What is the best free model for long context?
GLM 5.3 Flash currently leads — free at OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen. Next come GLM 5.3, DeepSeek V4.1 Flash, GLM 5.3 Flash Thinking.