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
301Sonar Deep ResearchPerplexity———128K$3.50
302Sonar Reasoning ProPerplexity———128K$3.50
303UI-TARS 7BByteDance———128K$0.13
304UncensoredVenice———128K$0.38
305SonarPerplexity———127K$1.00
306ERNIE 4.5 VL 424B A47BBaidu———123K$0.63
307Morph V3 FastMorph———82K$0.90
308Qwen3 30B A3B Thinking 2507Alibaba (Qwen)———82K$0.75
309GLM 4.5VZ.ai (Zhipu AI)———66K$0.90
310MiniMax M2-herMiniMax———66K$0.53
311Mixtral 8x22B InstructMistral AI———66K$3.00
312Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google———66K$1.13
313Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google———66K$0.56
314Nano Banana Pro (Gemini 3 Pro Image Preview)Google———66K$4.50
315Reka Flash 3Reka AI———66K$0.13
316WizardLM-2 8x22BMicrosoft—43.4—66K$0.62
317R1DeepSeek139.071.7—64K$1.15
318Llama 3.2 1B InstructMeta———60K$0.070
319Perceptron Mk1.5NEWPerceptron———37K$0.49
320Mistral Small 3Mistral AI127.147.3—33K$0.058
321Aion-RP 1.0 (8B)AionLabs———33K$1.00
322Magnum v4 72Banthracite-org———33K$3.13
323Nano Banana (Gemini 2.5 Flash Image)Google———33K$0.85
324Perceptron Mk1Perceptron———33K$0.49
325Qwen2.5 72B InstructAlibaba (Qwen)———33K$0.37
326Qwen2.5 7B InstructAlibaba (Qwen)———33K$0.13
327Qwen2.5 Coder 32B InstructAlibaba (Qwen)———33K$0.74
328SabaMistral AI———33K$0.30
329Skyfall 36B V2TheDrummer———33K$0.61
330Voxtral Small 24B 2507Mistral AI———33K$0.15
331GPT-3.5 TurboOpenAI · +1 variant———16K$0.75
332GPT-3.5 Turbo 16kOpenAI———16K$3.25
333Phi 4Microsoft130.456.1—16K$0.087
334Reka EdgeReka AI———16K$0.10
335Gemma 2 27BGoogle122.136.5—8K$0.65
336Hy-MT2-1.8BTencent———8K$0.077
337Hy-MT2-30B-A3BTencent———8K$0.13
338Hy-MT2-7BTencent———8K$0.13
339Llama 3 8B LunarisSao10K———8K$0.043
340MythoMax 13Bgryphe———8K$0.087
341GPT-4OpenAI———8K$37.50
342Weaver (alpha)Mancer———8K$0.49
343ReMM SLERP 13Bundi95———6K$0.42
344GPT-3.5 Turbo (older v0613)OpenAI———4K$1.25
345GPT-3.5 Turbo InstructOpenAI———4K$1.63
— 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