Skip to content

Longest context

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

All90d30d
Open weights
All typesTextImageAudio
40 models

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
1GPT-6 AstraNEWbatchOpenAI · +1 variant———1.05M$10.00
2GPT-6 Astra ProNEWOpenAI · +1 variant———1.05M$20.00
3GPT-6 LunaNEWOpenAI · +1 variant———1.05M$0.20
4GPT-6 Luna ProNEWOpenAI · +1 variant———1.05M$0.20
5GPT-6 SolNEWOpenAI · +1 variant———1.05M$4.00
6GPT-6 Sol ProNEWOpenAI · +1 variant———1.05M$4.00
7GPT-6.1 SolNEWOpenAI · +1 variant———1.05M$4.00
8GPT-6.1 Sol ProNEWOpenAI · +1 variant———1.05M$4.00
9MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
10MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
11Gemini 3.8 FlashNEWGoogle · +1 variant157.195.473.81.05M$1.50
12Muse Spark 1.3NEWMeta156.9——1.05M$2.00
13DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
14Ember-1NEWFireworks AI———1.05M$6.00
15GLM 5.3 FlashXNEWZ.ai (Zhipu AI)———1.05M$0.59
16MiMo-V2.6-Pro-UltraSpeedNEWXiaomi———1.05M$5.44
17Muse Spark 1.3 ContributorNEWMeta———1.05M$0.13
18Claude Fable 5.1NEWAnthropic · +1 variant165.0——1M$20.00
19Qwen3.8 Max (0902)NEWAlibaba (Qwen)155.3——1M$3.00
20Claude Opus 5.5NEWAnthropic · +1 variant—90.6—1M$8.00
21Claude Sonnet 5.5NEWAnthropic · +1 variant—95.6—1M$4.00
22Fugu MaxNEWSakana AI———1M$3.00
23Fugu Ultra v2NEWSakana AI———1M$11.25
24GLM 5.3 PrimeNEWZ.ai (Zhipu AI)———1M$4.30
25Jev RouterNEWTypeSafe———1M—
26Qwen3.8 Max PrimeNEWAlibaba (Qwen)———1M$6.00
27Qwen3.8 Omni FlashNEWAlibaba (Qwen)———1M$0.23
28Solar Mini 4NEWUpstage———524K$0.087
29Grok 4.7NEWxAI———500K$3.00
30Aion 3.5NEWAionLabs———262K$3.75
31Aion 3.5 MiniNEWAionLabs———262K$0.88
32Ling 3.0 Flash VLNEWinclusionAI (Ant Group)———262K$0.031
33Nex-N2.5-MiniNEWNex AGI———262K$0.044
34Nex-N2.5-ProNEWNex AGI———262K$0.12
35ParetoNEWunbiased———262K$3.75
36Ternary Bonsai 2 27BNEWPrismML———262K$0.18
37Mercury 2.5NEWInception Labs———260K$0.068
38Schematron V2 SmallNEWInference.net———128K$0.095
39Schematron V2 TurboNEWInference.net———128K$0.060
40Perceptron Mk1.5NEWPerceptron———37K$0.49
— 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