Observed source change · OpenAI

OpenAI API changelog documentation changed

Published documentation; runtime behavior and legal interpretation not established.

Last unchanged check: 2026-10-20T17:50:08Z
First changed check: 2026-10-20T19:55:07Z

Before

After

### Oct 20 Feature · API: v1/responses You can now choose 12-hour prompt caching in the API. 12-hour prompt caching keeps shared instructions, tools, and context cached longer to benefit from lower cached-input pricing, even when requests are hours apart. 12-hour cache writes cost 2.5x the input token price. Read more [here](https://developers.openai.com/api/docs/guides/prompt-caching). ### Oct 16 Feature · API: v1/agents [OpenAI-hosted sandboxes](https://developers.openai.com/api/docs/guides/agents-api/environments/openai-hosted) in the Agents API now include the Artifact SDK and skills for creating and editing spreadsheets, presentations, and Word documents. Added [Ultrafast mode](https://developers.openai.com/api/docs/guides/ultrafast-mode) to the Agents API. Set `agent.service_tier` …

Capture provenance and limitations

Raw before SHA-256: 51d96059b0cf06e5141c137b45fe1a729969b8eb37ada7905995ba0056c8b47c
Raw after SHA-256: 8c91d390bec4addbd0b2b845aa37a725a007df82a0590cca1048988af2a3c1c6

Full source responses are retained in the private evidence archive. Public excerpts show changed wording and may be truncated. The observed interval does not establish the vendor’s exact edit time. Hashes identify retained bytes; they are not an independent timestamp certificate.

Download archived excerpts and capture metadata · Back to the tracker