Model Context Window Comparison
Compare context windows across all models.
With the default inputs, Context windows compared — 326 models ranked by context size. Enter your own numbers below to recompute instantly; the full step-by-step math is shown under the worked example.
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
We list every model's context window and maximum output in one table, ranked from largest window to smallest, so you can shortlist by how much you need to fit in a single call.
Is this a good result? What to do next
Bigger isn't automatically better: a huge window costs more to fill and can degrade answer quality when overloaded. Pick the smallest window that comfortably fits your longest realistic input plus output.
Typical planning ranges
- Largest windows
- open-weight Llama 4 Scout, then 1M-token models
- 1M-token tier
- GPT-4.1, Gemini 2.5, Claude 4
- Max output
- separate from the input window
Ranges are typical planning figures to sanity-check your result, not authoritative benchmarks. Your numbers will vary with use case, volume, and vendor.
How to improve this number
- Match the window to your longest realistic prompt + output.
- Use RAG instead of a giant window for large corpora.
- Reserve big windows for genuine long-document work.
Common mistakes
- Choosing the biggest window by default.
- Confusing context window with max output length.
When to use a different approach
To lay out a specific prompt, use the context window planner. For pricing, use the LLM pricing comparison.
Worked example (defaults)
With the default inputs above, here is the result:
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.
Related calculators
Answering a real question?
This calculator powers these problem-solving guides: