Context window

Short answer

The context window is the maximum number of tokens (input + output) a model can process in a single request. GPT-5.5 and Claude Opus 4.8 both have 1M-token context windows as of 2026-06-17.

The context window determines how much the model can "see" at once: long documents, big codebases, multi-turn chat history. As of 2026-06-17, the frontier text models cluster around 1M tokens:

  • GPT-5.5 / GPT-5.4 — 1M tokens (1,048,576).
  • Claude Opus 4.8 / Sonnet 4.6 / Haiku 4.5 — 1M tokens (200K for Haiku 4.5).
  • Gemini 3.1 Pro — 1M tokens.
  • DeepSeek V4 Pro — 1M tokens.

Note: some providers price differently past a threshold. Gemini 2.5 Pro doubles its input price when the prompt exceeds 200K tokens. Always check tiered pricing for long-context workloads.

Related terms