claude-2-1-200k-context-window

IN premise — entries/2026/06/21/wiki-Claude_language_model.md

Created 2026-06-21T09:50:09+00:00

Claude 2.1 introduced a 200,000-token context window (approximately 500 pages).

Summary

Claude 2.1 can take in roughly 500 pages of text in a single pass, meaning the system can work through long documents, extended conversations, or large codebases without losing track of earlier content. This sets a practical baseline for how much context is available in one session and removes the need to chunk or summarize input just to fit within model limits.

Dependents

These beliefs depend on this one:

IN agentic-externalization-productization — Anthropic's product trajectory (200K context window → agentic CLI → multi-hour autonomous SWE-Bench runs) operationalizes the context-externalization principle at the product level: rather than scaling parameters toward 10¹⁵ for long-tail knowledge, the architecture externalizes task state into the context window and uses iterative agentic loops to extend effective context beyond any single forward pass.
IN context-externalization-principle — Rare knowledge is more efficiently stored externally (retrieval context, extended windows) than parametrically: the ~10¹⁵-parameter estimate for long-tail mastery, the 200K-token context window, and RAG-based mitigation are independent operationalizations of the same principle that context is a substitute for infeasible parametric scaling.
OUT context-window-externalization-validation — Long-context windows (200K tokens) with near-perfect in-context key-value retrieval provide operational validation of the externalization principle at practical scale, demonstrating that in-context storage is a reliable substitute for parametric long-tail knowledge when the model can attend to all relevant information simultaneously.
IN context-windows-expanded-10000x-in-seven-years — Context windows expanded approximately 10,000x from GPT-2's 1,024 tokens (2019) to Llama 4 Scout's 10 million tokens (2025), with Claude 2.1's 200K window as a major intermediate milestone in late 2023.