OpenAI makes the Decisions API generally available
Original title: Build more responsive apps with the Decisions API
Built on GPT-6 Luna, it returns bounded answers up to 10x faster, at $0.10 per million input tokens.
OpenAI said the Decisions API is generally available for applications and agents that need bounded answers from text, images, or structured inputs. It uses GPT-6 Luna and can return a probability, choice, or score. Since public beta, OpenAI added a native GPT-Live integration, prompt caching, US and EU inference residency, native JSON, images in instructions, and up to 400 questions per request. Input is billed; there are no output-token charges.
- Developers may ask up to 400 questions per request, twice the previous limit.
- Cached input costs $0.01 per million tokens.
- Regional processing is available in the US and EU.
- Zero Data Retention is available to eligible customers.
- Vendors
- OpenAI
- Products
- Decisions API
- AI models
- GPT-6 LunaGPT-Live
From the original article
4 min read at openai.com
Applications and agents make many small decisions throughout a workflow: how to classify an input, where to route a request, or which action to take next. Individually, they are simple. At scale, their latency and cost add up.
openai.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.