OpenAI APINew featureinfo

OpenAI adds 12-hour prompt caching to the Responses API on Oct 20, 2026

Detected
Oct 20, 2026
Effective
Oct 20, 2026
Confidence
92%

What changed

OpenAI has added a 12-hour prompt caching option to the v1/responses API, allowing cached instructions, tools, and context to persist longer for reduced cached-input pricing. Cache writes at this duration are priced at 2.5x the standard input token price.

What to do

Opt in to 12-hour prompt caching on the v1/responses endpoint to take advantage of lower cached-input pricing for long-lived sessions; note the 2.5x write cost premium.

Affected

endpoint: v1/responses

Source: platform.openai.com (OpenAI's own page, checked by Breakwatch)

Is your code affected?

Search your repositories for the OpenAI SDK and the names above:

npm: openaipip: openairuby: ruby-openaigo: github.com/sashabaranov/go-openaiphp: openai-php/clientjava: com.theokanning.openai-gpt3-javacsharp: OpenAIrust: async-openai

Or let Breakwatch do it: connect a repo and see which files call OpenAI, then get the next change as an alert pointing at those files. Check a repo free

Get OpenAI API changes by email

Once a week: the breaking changes and upcoming deadlines for OpenAI, each linked to the vendor's own page. Free, no account. One-click unsubscribe.

More OpenAI API changes

Every OpenAI API change →