OpenAI's Decisions API enters public beta with typed answers for text and images

01 What happened

OpenAI has opened its Decisions API in public beta. The dedicated POST /v1/decisions endpoint evaluates text, images or both, aimed at classification, routing and review workflows. OpenAI expects general availability in the coming weeks; it is not generally available yet.

02 Key details

• Question types set the answer format: predicate returns the probability that a condition is true, choice returns one option from a supplied set, and score returns a probability-weighted average of ordered level indices, which can fall between levels.
• For gpt-6-luna, input costs $0.10 per 1M tokens, and only input tokens are billed. Regional processing premiums and long-context input multipliers also apply.
• Images must be inline base64 data URLs. Hosted HTTP or HTTPS image URLs and file_id inputs are not supported by this endpoint.
• OpenAI says the API is about 10x faster than the Responses API. That figure is the company's own and was not independently tested. ZDR and HIPAA are supported for eligible customers.

03 Why it matters

Teams building classification, routing or review workflows on text and images get typed answers billed per input token. The beta, the single supported model and the image restrictions mean speed and GA timing should be validated before production use.

04 Who it matters to

Software developers and AI developers.