# Context size reduction The context-window arms race runs in one direction in the marketing (bigger!), but vendors sometimes quietly go the other way. OpenAI reduced the Codex model's context size from 372k to 272k tokens, and because the Codex CLI is open source, the change surfaced as a GitHub pull request rather than an announcement. The pull request reached the Hacker News front page. Thibault Sottiaux (Codex team) gave the reason on X: cache reads cost more as a bigger context is sent back and forth between tool calls, so the cheapest setting isn't the maximum length. He says output quality is similar above 272k, and that OpenAI is working on tuning that would allow a higher limit again without charging more usage. Hacker News commenters gave other reasons a smaller window can make sense: - **Cost and latency** — serving a bigger window is expensive and slow, and many sessions never come close to filling it. Cutting the ceiling improves the median experience. - **Quality.** Users reported keeping sessions under 200k by choice because models get noticeably worse past that; my own experience with context rot in long [[Claude Code]] sessions matches, although I feel like it's still ok between 250-400K tokens. - **Compaction quality beats raw capacity.** One [[OpenAI Codex]] user reported never noticing the limit because compaction just works; another compared it to Fable sessions that run 500k tokens without compacting once. What users actually experience is the compaction strategy, not the window size. Simon Willison spotted that the same commit added destructive-action guardrails to the system prompt (resolve targets with read-only checks first; never target `$HOME` or `/` with recursive destructive commands), Basic specs like context size are also undocumented: you find them in X threads and open-source diffs. The takeaway for anyone building on these models: [[Treat AI context as a budget to manage|treat the context window as a budget to manage]], not a capacity to fill. See [[Context Engineering]]. ## References - Hacker News discussion: https://news.ycombinator.com/item?id=48965850 - The PR: https://github.com/openai/codex/pull/33972/files - Explanation from Thibault Sottiaux: https://x.com/thsottiaux/status/2076543065045795309 ## Related - [[Context Window]] - [[Context Engineering]] - [[Agentic Context Management]] - [[OpenAI Codex]] - [[Codex CLI]] - [[Orchestrator tax]] - [[2026-08-05 OpenAI shrank the Codex context window on purpose]]