Skip to content

Longest context

Ranked by maximum context window (tokens) as listed by the API provider.

Ranked by maximum context window (tokens) as listed by the API provider. Source: OpenRouter. Variants (reasoning effort, batch) are folded into one row.

#ModelCapabilityReasoningCodingContext$/M
1GLM 5.3Z.ai (Zhipu AI) · +1 variant155.690.969.01.31M$2.15
2DeepSeek V4 Flash 0731DeepSeek154.591.0—1.31M$0.093
3GLM 5.3 FlashZ.ai (Zhipu AI) · +1 variant151.990.263.41.31M$0.24
4Llama 4 ScoutMeta129.651.8—1.31M$0.15
5MiMo-V2.5Xiaomi———1.05M$0.17
6MiMo-V2.5-ProXiaomi———1.05M$0.54
7MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
8LongCat 2.0Meituan———1.05M$0.53
9Kimi K3Moonshot AI · +1 variant157.793.168.51.05M$6.00
10DeepSeek V4 Pro 0813DeepSeek155.491.7—1.05M$1.41
11GLM 5.2Z.ai (Zhipu AI)151.891.943.81.05M$1.51
12DeepSeek V4 Pro 0423DeepSeek149.1——1.05M$1.19
13MiniMax M3MiniMax147.090.9—1.05M$0.53
14DeepSeek V4 Flash 0423DeepSeek146.1——1.05M$0.17
15Llama 4 MaverickMeta132.2——1.05M$0.30
16DeepSeek V4 Flash Vision ExpDeepSeek———1.05M$0.32
17DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
18Hy4 previewTencent———1.05M$1.25
19Laguna S 2.1Poolside———1.05M$0.11
20MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
21Qwen3.8 2.4T A95BAlibaba (Qwen)———1.05M$3.00
22UnslopNemo 12BTheDrummer———1.02M$0.40
23MiniMax-01MiniMax———1M$0.42
24Nemotron 3.5 LightningNVIDIA———1M$0.085
25Qwen3.8 27BAlibaba (Qwen)———1M$1.15
26Qwen3.8 FlashAlibaba (Qwen)———1M$0.23
27Inkling SmallThinking Machines Lab150.1——524K$0.64
28InklingThinking Machines Lab148.6——524K$1.76
29Kimi K2.6Moonshot AI151.090.8—262K$1.34
30Kimi K2.7 CodeMoonshot AI150.087.930.5262K$1.32
31Kimi K2.5Moonshot AI148.1——262K$0.90
32Qwen3.5 397B A17BAlibaba (Qwen)146.686.4—262K$1.29
33Qwen3.6 27BAlibaba (Qwen)146.585.9—262K$1.04
34Nemotron 3 UltraNVIDIA146.285.4—262K$1.05
35Kimi K2 ThinkingMoonshot AI146.0——262K$1.07
36Gemma 4 31BGoogle142.775.8—262K$0.15
37Qwen3.5-35B-A3BAlibaba (Qwen)142.583.5—262K$0.45
38Gemma 4 26B A4BGoogle141.873.2—262K$0.14
39Mistral Medium 3.5Mistral AI141.4——262K$3.00
40Qwen3.5-9BAlibaba (Qwen)139.479.0—262K$0.11
41Devstral 2 2512Mistral AI———262K$0.80
42Hy3Tencent———262K$0.23
43Hy3 previewTencent———262K$0.28
44Kimi K2 0905Moonshot AI———262K$1.07
45Laguna XS 2.1Poolside———262K$0.075
46Ling 3.0 FlashinclusionAI (Ant Group)———262K$0.032
47Ling 3.0 Flash VLNEWinclusionAI (Ant Group)———262K$0.031
48Ministral 3 14B 2512Mistral AI———262K$0.20
49Ministral 3 8B 2512Mistral AI · +1 variant———262K$0.15
50Mistral Small 4Mistral AI · +1 variant———262K$0.26
— means no published score from that source yet · click a model for every benchmark with its source

New - awaiting independent evaluation

All new models →

Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.

Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research