Several changes affect cost, speed and access: 12-hour prompt cachingReusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.Full definition → for Responses API requests, up to 8x faster Codex generation with Sol Ultrafast, higher rate limits through Build, Launch and Grow tiers, and a Windows Codex sandboxAn isolated environment where AI-generated code or agent actions run without being able to touch anything real.Full definition → that controls network and file access.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
prompt caching — Reusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
