OpenAI launches Decisions API, powered by GPT-6 Luna, to turn text and images into app actions
OpenAI · youtube · 2026-10-07
OpenAI has introduced the Decisions API, a lightweight way to convert text and image inputs into concrete actions in your app: you give the model an input, define a question and a set of possible answers, and its choice drives what happens next.
Key points:
- Powered by GPT-6 Luna, focused on a small set of choices so interactions feel responsive
- Demoed scenarios include classifying text and routing sales leads, making decisions from images, adding expression to voice conversations alongside GPT-Live-1 and a Microduck, and guiding Lavender the robot
It's positioned as a low-latency, choice-focused inference API for routing and classification in developer workflows.
Related event: OpenAI Launches Decisions API Public Beta, Up to 10x Faster Decision-Making(5 posts)→
More from coding & agent
- 27B Model at 256k Context, 110+ tok/s on a Single RTX 5090 via focus-llama — Ok-Shower7286 · 2026-10-07
- Google Testing Blog: Two-Way Doors — Don't Code Yourself into a Corner — rseroter · 2026-10-07
- Hot take: AGENTS.md and agent skills are just text files—put in whatever works — intellectronica · 2026-10-07
- Dev burns 190B tokens in a month using 30 AI subscriptions, $6k for $93k of API value — BLUECOW009 · 2026-10-07
- Set Up Your GrokBot Like Hiring a New Employee: One Job, Minimal Access — alex_verem · 2026-10-07
- ChatGPT Can Now Subscribe to Netlify Events: Auto-Reply Forms, Summarize Deploys — thisiskp_ · 2026-10-07