OpenAI launches Decisions API beta for classification

GPT 6 Luna returns probabilities, categories and scores for applications.

Jordan Reid
October 6, 2026
Tools, OpenAI
1 min

Close up of colorful Python code on a computer screen — Illustrative coding photograph. Photo by Chris Ried / Unsplash.

Listen to this article

OpenAI launched the Decisions API in public beta on October 6. It uses GPT 6 Luna to return probabilities, category choices or rubric scores from text and images.

Developers can use these outputs to route requests or flag items for review. The official guide says answers arrive about ten times faster than through the Responses API. ByteForward has not tested that claim.

Pricing starts at $0.10 per million input tokens, with no output or cache charges. Regional processing premiums and long context multipliers apply.

Images must be embedded as base64 data. Hosted image links and file IDs are unsupported.

GPT 6 Luna is the only supported model during the beta. OpenAI expects general availability in the coming weeks but gives no firm date.

Teams should set routing and review thresholds using labeled examples and the cost of false decisions.

Archival photograph by Chris Ried on Unsplash, published in January 2018 and used under the Unsplash License. The Python code illustrates software development and does not show the Decisions API. Existing WebP rendition.

Jordan Reid

Jordan Reid is focused on AI tools, agents, developer products, and the way technology changes everyday work. Jordan approaches a launch from the user’s side of the screen. What can it actually help someone finish? The voice is practical, conversational, and skeptical of products that turn a simple job into five new settings. Coverage follows coding assistants, creative software, browser agents, and the workflows around them, with attention to pricing, permissions, setup, and the human work that remains.