Responses API
Explain what OpenAI’s Responses API is for: how it brings tool calling, structured outputs, files and hosted containers into one execution path, and what it means for teams migrating away from Chat Completions.
Explain what OpenAI’s Responses API is for: how it brings tool calling, structured outputs, files and hosted containers into one execution path, and what it means for teams migrating away from Chat Completions.
ChatGPT Plus or API — which is the better deal? Here's the bottom line up front: if you mainly chat, write, and get office work done with it, the flat...
OpenAI's Decisions API became generally available on October 22. Built on GPT-6 Luna, it is designed for small decisions with bounded answers. In its ...
AAIF announced on October 22, 2026, at the AGNTCon + MCPCon North America conference in San Jose, that it is taking on four new projects at once, lift...
OpenAI prompt caching retention has been stretched from half an hour to 12 hours. The OpenAI Developers account announced on October 20, 2026 that the...
The Decisions API entered public beta on October 6, 2026, as OpenAI announced: the new interface that was only a limited preview at DevDay on Septembe...
Ultrafast API is the ultra-low-latency inference tier OpenAI launched in August alongside GPT-5.6 Sol, officially rated at up to 750 tokens per second...
On September 22, 2026, OpenAI announced two new additions to the GPT-6 family: GPT-6 Sol and GPT-6 Luna. Both models are priced at half the promotiona...
OpenAI has released a new article about the Responses API computer environment, focusing not on the "model tuning tool" again, but on connecting files...