Glossary / LLM APIs and AI
Glossary · LLM APIs and AI · checked Oct 24, 2026
Context window
Short answerThe context window is the most tokens a model can take in one request, prompt plus answer. Anything beyond it must be cut, summarized or retrieved.
Why it matters
A bigger window lets you paste whole documents or codebases, but you pay for every token you send, and some providers charge more per token once a prompt passes a size threshold.
Our number
14 of the 67 listed models in our table charge a long-context rate. Example: Claude Haiku 5.5 goes from $0.1 to $0.5 per 1M input tokens once a prompt is over 100,000 tokens.
Go deeper on this site
Where it shows up here
It appears on 81 pages of this site: 79 LLM price pages, 1 Article, 1 Free tool. A few to start with:
- Meta open-sourced an 816B model. Running it takes about 1TB of RAM
- LLM VRAM calculator.
- LLM API prices, and the cheapest model for your job
- chat-latest API pricing
Sources
- Anthropic: context windows: platform.claude.com/docs/en/build-with-claude/context-windows (checked Oct 24, 2026)
- Google Gemini API pricing: ai.google.dev/gemini-api/docs/pricing (checked Oct 24, 2026)
Related terms
Up next
Go deeperLLM API prices, with long-context ratesThe page on this site that does the most with this term.Read it next →Did this answer your question?