OpenAI Launches Prompt Caching Dashboard to Track Cache-Hit Rates and Misses
OpenAIDevs · x · 2026-09-23
Alongside its GPT-6 prompt caching improvements, OpenAI shipped a new Prompt Caching Dashboard. Developers can see what's being reused and what's preventing cache hits, and use the diagnostics API to identify changes that blocked reuse and estimate affected tokens.
Related event: OpenAI improves GPT-6 prompt caching with up to 90% input token savings(3 posts)→
More from coding & agent
- Two personal AIs tried to schedule coffee: agent interop needs a protocol — signulll · 2026-09-23
- Devin's iOS beta "Cog" hits TestFlight: code from your phone — msg · 2026-09-23
- Dev credits Alchemy for letting agents debug real deployments, landing major perf wins — samgoodwin89 · 2026-09-23
- Hooking Codex up to iMessage lets you interrogate months of chat history — gregmushen · 2026-09-23
- Sentry founder David Cramer finds Claude Code's new sidebar confusing vs Codex — zeeg · 2026-09-23
- Mid-session effort switching on Opus 5.5 preserves prompt cache in Claude Code v2.1.280+ — lydiahallie · 2026-09-23