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
251Aion-3.0-MiniAionLabs———131K$0.88
252Cydonia 24B V4.1TheDrummer———131K$0.35
253GLM 4.5Z.ai (Zhipu AI)———131K$1.00
254GLM 4.5 AirZ.ai (Zhipu AI)———131K$0.31
255GLM 4.6VZ.ai (Zhipu AI)———131K$0.45
256gpt-oss-safeguard-20bOpenAI———131K$0.13
257Granite 4.2 8BIBM———131K$0.11
258Hermes 3 405B InstructNous Research———131K$1.00
259Hermes 3 70B InstructNous Research———131K$0.70
260Hermes 4 405BNous Research———131K$1.50
261Hunyuan A13B InstructTencent———131K$0.25
262Kimi K2 0711Moonshot AI———131K$1.00
263Llama 3.1 70B InstructMeta———131K$0.40
264Llama 3.1 8B InstructMeta———131K$0.058
265Llama 3.1 Euryale 70B v2.2Sao10K———131K$0.85
266Llama 3.2 3B InstructMeta———131K$0.12
267Llama 3.3 70B InstructMeta———131K$0.15
268Llama 3.3 Euryale 70BSao10K———131K$0.68
269Ministral 3 3B 2512Mistral AI———131K$0.10
270Mistral Large 2407Mistral AI———131K$3.00
271Mistral Medium 3.1Mistral AI · +1 variant———131K$0.80
272Muse Glimmer 30BMeta———131K$0.64
273Nano Banana 2 (Gemini 3.1 Flash Image)Google———131K$1.13
274Nano Banana Pro (Gemini 3 Pro Image)Google———131K$4.50
275Nemotron 3.5 Content SafetyNVIDIA———131K$0.20
276Qwen3 235B A22B Thinking 2507Alibaba (Qwen)———131K$0.75
277Qwen3 VL 235B A22B ThinkingAlibaba (Qwen)———131K$1.30
278Qwen3 VL 32B InstructAlibaba (Qwen)———131K$0.18
279Qwen3 VL 8B ThinkingAlibaba (Qwen)———131K$0.66
280Solar Pro 3Upstage———131K$0.26
281Granite 4.0 MicroIBM—28.3—131K$0.041
282GPT-4o-miniOpenAI · +1 variant126.637.7—128K$0.26
283Mistral LargeMistral AI122.038.8—128K$3.00
284Command R (08-2024)Cohere———128K$0.26
285Command R7B (12-2024)Cohere———128K$0.066
286GPT AudioOpenAI———128K$4.38
287GPT Audio MiniOpenAI———128K$1.05
288GPT-4 TurboOpenAI · +1 variant———128K$15.00
289GPT-4oOpenAI · +1 variant———128K$4.38
290GPT-4o (2024-05-13)OpenAI———128K$7.50
291GPT-4o (2024-08-06)OpenAI———128K$4.38
292GPT-4o (2024-11-20)OpenAI———128K$4.38
293GPT-4o-mini (2024-07-18)OpenAI———128K$0.26
294GPT-5.2 ChatOpenAI———128K$4.81
295Mercury 2Inception Labs———128K$0.38
296Mistral Small 3.1 24BMistral AI———128K$0.40
297Nova Micro 1.0Amazon———128K$0.061
298Qwen2.5 VL 72B InstructAlibaba (Qwen)———128K$0.85
299Schematron V2 SmallNEWInference.net———128K$0.095
300Schematron V2 TurboNEWInference.net———128K$0.060
— 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