‹ All stories

OpenAI API

Updated 4:17 AM ET
Product · 2 updates

Where it stands

As of Oct 21, OpenAI API developers can now choose 12-hour prompt caching on v1/responses.

Timeline · newest first
  1. Official

    OpenAI adds 12-hour prompt caching to the API

    OpenAI published this on Oct 21, 2026 (source: developers.openai.com).

    OpenAI API developers can now choose 12-hour prompt caching on v1/responses. It keeps shared instructions, tools and context cached longer, so requests hours apart still get lower cached-input pricing. 12-hour cache writes cost 2.5x the input token price.

    Source: OpenAI
  2. Official

    OpenAI API changelog: prompt-to-voice opens to all API customers for custom GPT-Live voices

    OpenAI published this on Oct 16, 2026 (source: developers.openai.com).

    OpenAI released prompt-to-voice for all API customers: you describe a voice in text through the API (v1/audio/voices) or the voice Playground, then reuse it in GPT-Live sessions. Creating a prompt-generated voice is free, and speech generation bills at regular GPT-Live session rates. The same Oct 16 entry adds nine natural GPT-Live voices across German, French, Hindi, Japanese and Korean.

    Source: OpenAI
Related stories
OpenAI39 updates · Apps & products→ChatGPT14 updates · Apps & products→OpenAI Daybreak2 updates · Apps & products→OpenAI agent incidents14 updates · Policy & safety→
How we label
Official
An institution announces something that has already happened, through its own channel or a founder or executive account.
Statement by …
A named person's views, predictions, plans or comments, including remarks reported by media when the original is unavailable.
Reported by …
Only media or another third party is saying it. We name the outlet.
Unconfirmed
Circulating online (posts, comments, leaks). No company, named person or outlet has confirmed it.

Items older than 72 hours never go in Top stories and show their original date.

DailyCitedRSSAboutPrivacy