LLM Context Window Comparison 2026

Compare context window sizes across 92 large language models. Larger context windows let you process longer documents and maintain richer conversation histories.

Data verified Apr 20, 2026

Context Window by Model

All Models — Ranked by Context Window

ModelProviderContext WindowMax OutputInput $/MOutput $/M
Llama 4 ScoutMeta10.48576M32,768$0.080$0.300
Gemini Experimental 1206Google2M8,192$0.00$0.00
Gemini 1.5 ProGoogle2M8,192$1.25$5.00
Gemini 2.5 ProGoogle1.048576M65,536$1.25$10.00
Llama 4 MaverickMeta1.048576M32,768$0.150$0.600
Gemini 2.0 FlashGoogle1.048576M8,192$0.100$0.400
Gemini 2.0 Flash LiteGoogle1.048576M8,192$0.075$0.300
Gemini 2.5 FlashGoogle1M8,192$0.300$2.50
Gemini 1.5 FlashGoogle1M8,192$0.075$0.300
Gemini 1.5 Flash 8BGoogle1M8,192$0.037$0.150
Amazon Nova ProAmazon300K4,096$0.800$3.20
Amazon Nova LiteAmazon300K4,096$0.060$0.240
Command ACohere256K4,096$2.50$10.00
Codestral 22BMistral AI256K4,096$0.300$0.900
Claude Opus 4Anthropic200K32,000$5.00$25.00
o3OpenAI200K100,000$2.00$8.00
o1OpenAI200K100,000$15.00$60.00
Grok 3xAI200K8,192$3.00$15.00
Claude Sonnet 4Anthropic200K64,000$3.00$15.00
Claude 3.5 SonnetAnthropic200K8,192$3.00$15.00
Claude 3.5 HaikuAnthropic200K8,192$0.800$4.00
Claude Haiku 4Anthropic200K8,192$1.00$5.00
Sonar ProPerplexity200K8,192$3.00$15.00
Llama 3.1 405B (Fireworks)Fireworks AI131.072K4,096$3.00$3.00
Grok 2xAI131.072K4,096$2.00$10.00
Llama 3.3 70B (Fireworks)Fireworks AI131.072K4,096$0.900$0.900
DeepSeek R1DeepSeek128K8,192$0.500$2.15
Qwen 3 235B MoEAlibaba128K4,096$0.455$1.82
GPT-4.5OpenAI128K8,192$75.00$150.00
DeepSeek R1 (Groq)Groq128K8,192$0.750$0.990
DeepSeek V3DeepSeek128K8,192$0.259$0.420
o3-miniOpenAI128K65,536$1.10$4.40
o1-miniOpenAI128K65,536$1.10$4.40
ChatGPT-4o LatestOpenAI128K16,384$5.00$15.00
GPT-4oOpenAI128K16,384$2.50$10.00
o4-miniOpenAI128K32,768$1.10$4.40
Qwen 2.5 MaxAlibaba128K8,192$0.160$0.640
GPT-4o (Aug 2024)OpenAI128K16,384$2.50$10.00
DeepSeek R1 Distill Llama 70BDeepSeek128K8,192$0.700$0.800
Mistral LargeMistral128K8,192$0.500$1.50
GPT-4 TurboOpenAI128K4,096$10.00$30.00
Llama 3.1 405BMeta128K4,096$3.00$3.00
Pixtral LargeMistral AI128K4,096$2.00$6.00
Qwen 2.5 72BAlibaba128K4,096$0.120$0.390
GPT-4o MiniOpenAI128K16,384$0.150$0.600
Llama 3.3 70B (Groq)Groq128K4,096$0.590$0.790
Llama 3.3 70BMeta128K4,096$0.120$0.380
Mistral Medium 3Mistral AI128K4,096$0.400$2.00
Llama 3.3 70B (Together)Together AI128K4,096$0.880$0.880
Llama 3.2 90B VisionMeta128K4,096$0.900$0.900
Command R+Cohere128K4,096$2.50$10.00
DeepSeek V2.5DeepSeek128K4,096$0.140$0.280
Llama 3.1 70BMeta128K4,096$0.400$0.400
Phi-3.5 MoEMicrosoft128K4,096$0.170$0.680
Mistral SmallMistral128K8,192$0.150$0.600
GPT-4 1.5-miniOpenAI128K4,096$0.400$1.60
Grok 3-minixAI128K4,096$0.300$0.500
Phi-3 MediumMicrosoft128K4,096$0.170$0.170
Llama 3.2 11B VisionMeta128K4,096$0.245$0.245
Phi-3.5 MiniMicrosoft128K4,096$0.130$0.520
Qwen 2.5 7BAlibaba128K4,096$0.040$0.100
GPT-4 1.5-nanoOpenAI128K4,096$0.100$0.400
Command RCohere128K4,096$0.150$0.600
Mistral Nemo 12BMistral AI128K4,096$0.020$0.040
Amazon Nova MicroAmazon128K4,096$0.035$0.140
Command R7BCohere128K4,096$0.038$0.150
Llama 3.1 8B (Groq)Groq128K4,096$0.050$0.080
Llama 3.1 8BMeta128K4,096$0.020$0.050
Qwen 2.5 Coder 32BAlibaba128K4,096$0.660$1.00
Sonar ReasoningPerplexity127K8,192$2.00$8.00
SonarPerplexity127K4,096$1.00$1.00
DeepSeek R1 (Together)Together AI64K8,192$3.00$7.00
DeepSeek R1 Distill Qwen 32BDeepSeek64K8,192$0.290$0.290
Mixtral 8x22B (Fireworks)Fireworks AI64K4,096$0.900$0.900
WizardLM-2 8x22BMicrosoft64K4,096$0.620$0.620
Gemini 2.0 Flash ThinkingGoogle32K16,384$0.00$0.00
QwQ 32BAlibaba32K8,192$0.150$0.580
Qwen 2.5 72B (Together)Together AI32K4,096$1.20$1.20
Yi-Large01.AI32K4,096$3.00$3.00
Mixtral 8x7B (Groq)Groq32K4,096$0.240$0.240
InternLM 2.5 20BShanghai AI Lab32K4,096$0.180$0.180
Mistral 7BMistral AI32K4,096$0.110$0.190
Mistral 7B (Together)Together AI32K4,096$0.200$0.200
Phi-4Microsoft16.384K4,096$0.065$0.140
Yi-Lightning01.AI16K4,096$0.140$0.140
GPT-3.5 TurboOpenAI16K4,096$0.500$1.50
Grok 2 VisionxAI8.192K4,096$2.00$10.00
GPT-4 1OpenAI8.192K2,048$2.00$8.00
Gemma 2 27BGoogle8K4,096$0.650$0.650
Gemma 2 9B (Groq)Groq8K4,096$0.200$0.200
Gemma 2 9BGoogle8K4,096$0.030$0.090
Llama 3.1 405B (Together)Together AI4K4,096$3.50$3.50

Frequently Asked Questions

What is a context window?
A context window is the maximum number of tokens (words and word pieces) that a language model can process in a single request. It includes both the input prompt and the generated output. Larger context windows allow you to send longer documents, maintain longer conversation histories, and process more data in a single API call.
Which LLM has the largest context window?
As of 2026, Gemini 2.5 Pro leads with a 1 million token context window, followed by Gemini 2.0 Flash and Flash Lite with 1M tokens each. Among non-Google models, Claude Opus 4 and Claude Sonnet 4 offer 200K tokens, while GPT-4o provides 128K tokens.
Does context window size affect price?
Context window size itself doesn't directly affect per-token pricing, but larger context windows mean you can send more tokens per request, which increases total cost. Some providers offer cached input pricing at a discount for repeated content within the context window. Models with very large context windows (like Gemini) may also have different rate limits.