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
101Mistral NemoMistral AI118.629.9—131K$0.022
102Gemma 3 4BGoogle116.023.2—131K$0.063
103Cydonia 24B V4.1TheDrummer———131K$0.35
104GLM 4.5Z.ai (Zhipu AI)———131K$1.00
105GLM 4.5 AirZ.ai (Zhipu AI)———131K$0.31
106GLM 4.6VZ.ai (Zhipu AI)———131K$0.45
107gpt-oss-safeguard-20bOpenAI———131K$0.13
108Granite 4.2 8BNEWIBM———131K$0.11
109Hermes 3 405B InstructNous Research———131K$1.00
110Hermes 3 70B InstructNous Research———131K$0.70
111Hermes 4 405BNous Research———131K$1.50
112Hunyuan A13B InstructTencent———131K$0.25
113Kimi K2 0711Moonshot AI———131K$1.00
114Llama 3.1 70B InstructMeta———131K$0.40
115Llama 3.1 8B InstructMeta———131K$0.058
116Llama 3.1 Euryale 70B v2.2Sao10K———131K$0.85
117Llama 3.2 3B InstructMeta———131K$0.12
118Llama 3.3 70B InstructMeta———131K$0.15
119Llama 3.3 Euryale 70BSao10K———131K$0.68
120Ministral 3 3B 2512Mistral AI———131K$0.10
121Muse Glimmer 30BMeta———131K$0.53
122Nemotron 3.5 Content SafetyNVIDIA———131K$0.20
123Qwen3 235B A22B Thinking 2507Alibaba (Qwen)———131K$0.75
124Qwen3 VL 235B A22B ThinkingAlibaba (Qwen)———131K$1.30
125Qwen3 VL 32B InstructAlibaba (Qwen)———131K$0.18
126Qwen3 VL 8B ThinkingAlibaba (Qwen)———131K$0.66
127Granite 4.0 MicroIBM—28.3—131K$0.041
128Mistral Small 3.1 24BMistral AI———128K$0.40
129Qwen2.5 VL 72B InstructAlibaba (Qwen)———128K$0.85
130Schematron V2 SmallNEWInference.net———128K$0.095
131Schematron V2 TurboNEWInference.net———128K$0.060
132UI-TARS 7BByteDance———128K$0.13
133UncensoredVenice———128K$0.38
134ERNIE 4.5 VL 424B A47BBaidu———123K$0.63
135Qwen3 30B A3B Thinking 2507Alibaba (Qwen)———82K$0.75
136GLM 4.5VZ.ai (Zhipu AI)———66K$0.90
137Mixtral 8x22B InstructMistral AI———66K$3.00
138Reka Flash 3Reka AI———66K$0.13
139WizardLM-2 8x22BMicrosoft—43.4—66K$0.62
140R1DeepSeek139.071.7—64K$1.15
141Llama 3.2 1B InstructMeta———60K$0.070
142Mistral Small 3Mistral AI127.147.3—33K$0.058
143Magnum v4 72Banthracite-org———33K$3.13
144Qwen2.5 72B InstructAlibaba (Qwen)———33K$0.37
145Qwen2.5 7B InstructAlibaba (Qwen)———33K$0.13
146Qwen2.5 Coder 32B InstructAlibaba (Qwen)———33K$0.74
147Skyfall 36B V2TheDrummer———33K$0.61
148Voxtral Small 24B 2507Mistral AI———33K$0.15
149Phi 4Microsoft130.456.1—16K$0.087
150Reka EdgeReka AI———16K$0.10
— 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