OpenAI launches a Prompt Caching dashboard
UpdateVerifiedAdded Sep 22, 2026
The dashboard tracks cache hit rate over time, cache reads per write and the split of cache-read, cache-write and uncached tokens, filterable by model and service tier, to help improve caching efficiency.
Topics: BI, Observability, Developer tools
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More OpenAI API releases
Every OpenAI API release| Date | Release | Type |
|---|---|---|
| Aug 20 | OpenAI gpt-image-2 adds transparent backgrounds in preview Preview | Preview |
| Aug 21 | OpenAI API adds per-request regional processing via prefixed domains Update | Update |
| Aug 21 | OpenAI cuts GPT-5.6 Sol pricing to $4 input and $20 output per MTok Pricing | Pricing |
| Aug 24 | Advancing price-performance for developers with GPT‑5.6 in Kiro Update | Update |
| Aug 26 | OpenAI deprecates whisper-1 and gpt-4o transcribe models, shutdown February 26, 2027 Deprecation | Deprecation |
| Aug 13 | OpenAI announces Ultrafast mode for GPT-5.6 Sol in limited preview Preview | Preview |
| Aug 29 | OpenAI API mTLS and X.509 workload identity federation are GA GA | GA |
| Sep 1 | OpenAI API supports IPv6 connections to api.openai.com Update | Update |
