Digitorn
Digitorn
All terms
Models & inference

Context window

The maximum number of tokens an LLM can process in a single call. Modern frontier models offer 200K to 2M.

also known as: context length
In depth

The context window caps how much input plus output fits in one call. Claude Sonnet ships 200K, GPT-4o is 128K, Gemini Pro pushes to 2M. Long sessions overflow eventually, which is why compaction exists. Bigger windows are not always better: cost scales with input tokens, and models often degrade in quality at the far edge of their window.

Related concepts
Newsletter

Get the next post in your inbox.

Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.

One-click unsubscribe. We never share your address. Powered by our own infrastructure, not a tracker.

More in Models & inference

Frontier model/glossary/frontier-modelInference/glossary/inferenceLLM/glossary/llmOpen-weight model/glossary/open-weight-modelStreaming/glossary/streamingTemperature/glossary/temperature