Model Context Window Comparison
Compare context windows across all models.
Result
Context windows compared
43 models ranked by context size
| Model | Provider | Context window | Max output |
|---|---|---|---|
| Llama 4 Scout | meta | 10,000,000 | 8,192 |
| GPT-5.4 | openai | 1,050,000 | 128,000 |
| Gemini 2.5 Pro | 1,048,576 | 65,536 | |
| GPT-4.1 | openai | 1,000,000 | 32,768 |
| GPT-4.1 Mini | openai | 1,000,000 | 32,768 |
| GPT-4.1 Nano | openai | 1,000,000 | 32,768 |
| Claude Opus 4.8 | anthropic | 1,000,000 | 64,000 |
| Claude Opus 4.6 | anthropic | 1,000,000 | 64,000 |
| Claude Sonnet 4.6 | anthropic | 1,000,000 | 64,000 |
| Claude Sonnet 5 | anthropic | 1,000,000 | 64,000 |
| Claude Fable 5 | anthropic | 1,000,000 | 64,000 |
| Gemini 2.5 Flash | 1,000,000 | 65,536 | |
| Gemini 2.5 Flash-Lite | 1,000,000 | 65,536 | |
| Amazon Nova Premier | aws-bedrock | 1,000,000 | 10,000 |
| Llama 4 Maverick | meta | 1,000,000 | 8,192 |
| DeepSeek V4 Flash | deepseek | 1,000,000 | 8,192 |
| DeepSeek V4 Pro | deepseek | 1,000,000 | 8,192 |
| Grok 4.3 | xai | 1,000,000 | — |
| Grok 4.5 | xai | 500,000 | — |
| Amazon Nova Pro | aws-bedrock | 300,000 | 5,120 |
| Amazon Nova Lite | aws-bedrock | 300,000 | 5,120 |
| Mistral Large 3 | mistral | 262,000 | 8,192 |
| Devstral 2 | mistral | 262,000 | 8,192 |
| Command A | cohere | 256,000 | 8,000 |
| o3 | openai | 200,000 | 100,000 |
| o4-mini | openai | 200,000 | 100,000 |
| Claude Haiku 4.5 | anthropic | 200,000 | 8,192 |
| Sonar Pro | perplexity | 200,000 | — |
| DeepSeek V3.2 | deepseek | 164,000 | 8,192 |
| Mistral Medium 3.1 | mistral | 131,000 | 8,192 |
| Mistral Small 4 | mistral | 131,000 | 8,192 |
| GPT-5 | openai | 128,000 | 128,000 |
| GPT-5 Mini | openai | 128,000 | 64,000 |
| GPT-4o | openai | 128,000 | 16,384 |
| GPT-4o mini | openai | 128,000 | 16,384 |
| Amazon Nova Micro | aws-bedrock | 128,000 | 5,120 |
| Llama 3.3 70B | meta | 128,000 | 8,192 |
| Command R+ | cohere | 128,000 | 4,096 |
| Command R | cohere | 128,000 | 4,096 |
| Command R7B | cohere | 128,000 | 4,096 |
| Sonar | perplexity | 128,000 | — |
| Sonar Reasoning Pro | perplexity | 128,000 | — |
| Sonar Deep Research | perplexity | 128,000 | — |
Compare the context window and max output of every model in one ranked table, from the largest windows to the smallest.
How this is calculated
This calculator uses the comparisons formulas described in our methodology. All figures are estimates for planning; verify current pricing with each provider before relying on them.
Worked example (defaults)
With the default inputs above, here is the result:
Result
Context windows compared
43 models ranked by context size
| Model | Provider | Context window | Max output |
|---|---|---|---|
| Llama 4 Scout | meta | 10,000,000 | 8,192 |
| GPT-5.4 | openai | 1,050,000 | 128,000 |
| Gemini 2.5 Pro | 1,048,576 | 65,536 | |
| GPT-4.1 | openai | 1,000,000 | 32,768 |
| GPT-4.1 Mini | openai | 1,000,000 | 32,768 |
| GPT-4.1 Nano | openai | 1,000,000 | 32,768 |
| Claude Opus 4.8 | anthropic | 1,000,000 | 64,000 |
| Claude Opus 4.6 | anthropic | 1,000,000 | 64,000 |
| Claude Sonnet 4.6 | anthropic | 1,000,000 | 64,000 |
| Claude Sonnet 5 | anthropic | 1,000,000 | 64,000 |
| Claude Fable 5 | anthropic | 1,000,000 | 64,000 |
| Gemini 2.5 Flash | 1,000,000 | 65,536 | |
| Gemini 2.5 Flash-Lite | 1,000,000 | 65,536 | |
| Amazon Nova Premier | aws-bedrock | 1,000,000 | 10,000 |
| Llama 4 Maverick | meta | 1,000,000 | 8,192 |
| DeepSeek V4 Flash | deepseek | 1,000,000 | 8,192 |
| DeepSeek V4 Pro | deepseek | 1,000,000 | 8,192 |
| Grok 4.3 | xai | 1,000,000 | — |
| Grok 4.5 | xai | 500,000 | — |
| Amazon Nova Pro | aws-bedrock | 300,000 | 5,120 |
| Amazon Nova Lite | aws-bedrock | 300,000 | 5,120 |
| Mistral Large 3 | mistral | 262,000 | 8,192 |
| Devstral 2 | mistral | 262,000 | 8,192 |
| Command A | cohere | 256,000 | 8,000 |
| o3 | openai | 200,000 | 100,000 |
| o4-mini | openai | 200,000 | 100,000 |
| Claude Haiku 4.5 | anthropic | 200,000 | 8,192 |
| Sonar Pro | perplexity | 200,000 | — |
| DeepSeek V3.2 | deepseek | 164,000 | 8,192 |
| Mistral Medium 3.1 | mistral | 131,000 | 8,192 |
| Mistral Small 4 | mistral | 131,000 | 8,192 |
| GPT-5 | openai | 128,000 | 128,000 |
| GPT-5 Mini | openai | 128,000 | 64,000 |
| GPT-4o | openai | 128,000 | 16,384 |
| GPT-4o mini | openai | 128,000 | 16,384 |
| Amazon Nova Micro | aws-bedrock | 128,000 | 5,120 |
| Llama 3.3 70B | meta | 128,000 | 8,192 |
| Command R+ | cohere | 128,000 | 4,096 |
| Command R | cohere | 128,000 | 4,096 |
| Command R7B | cohere | 128,000 | 4,096 |
| Sonar | perplexity | 128,000 | — |
| Sonar Reasoning Pro | perplexity | 128,000 | — |
| Sonar Deep Research | perplexity | 128,000 | — |
Frequently asked questions
Which model has the largest context window?+
Open-weight Llama 4 Scout leads with a very large window, followed by 1M-token models like GPT-4.1, Gemini 2.5 and Claude 4. See the table for the full ranking.