Build more responsive apps with the Decisions API
- ID
- 38427
- Status
- summarized
- Published
- 23 Oct 2026, 3:00 AM
- Fetched
- 23 Oct 2026, 4:31 AM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/decisions-api
- Source URL
- https://openai.com/news/rss.xml
Summary
- Score
- 5.0
- Created
- 23 Oct 2026, 4:32 AM
- Tags
- Audience
- developersai_agent_usersai_ml_learnerssaas_founders
What happened
OpenAI has made the Decisions API generally available, built on GPT-6 Luna for bounded-answer decisions from text, images, and structured inputs, claiming up to 10x faster performance than GPT-6 Luna through the Responses API. Since beta it added GPT-Live integration, prompt caching, US/EU inference residency, native JSON and image inputs, and up to 400 questions per request, twice the previous limit. Customer examples cite roughly 5x faster route selection at Box on 30 certificate-of-insurance cases and 40x faster p95 for scoring agent-generated shell commands with comparable accuracy.
Why it matters
If your app or agent makes many small classification, routing, or risk-scoring calls, this is a concrete candidate to benchmark in the hot path. The 400-questions-per-request cap and prompt caching change how you might batch and reuse context, and added Asia capacity may help regional latency. But no price is disclosed, so do not assume 'low-cost'—measure p95 latency and accuracy on your own cases before swapping models.
Discussion angle
Which bounded decisions in your agent or SaaS workflow could move to a faster decision endpoint, and how would you benchmark p95 latency and accuracy against your current model—including batching up to 400 questions per request?