- Glossary
- Context window
What is a context window?
A context window is the maximum number of tokens a model can process in one request, counting the prompt, the conversation history, any documents or tool definitions, and the response it generates. Text beyond the limit is rejected or must be removed, so the context window sets how much a model can consider at once.
Also called: Context length, Context size · Last updated
Why it matters
A larger window lets you send whole documents, long conversations, or a full codebase in one request. Filling it raises cost, because every input token you send is billed on each call.
The same model can have different windows
Providers do not always serve a model with the same limits. One deployment may offer the full window while another caps it lower. LLM Gateway routes requests that name only a model to deployments that offer the model's full context window.