Decisions API

Use it to make fast, structured decisions in applications and agents, such as classifying inputs, routing requests, or selecting actions during live voice conversations.

Availability

Generally available today with GPT-6 Luna through the dedicated Decisions endpoint

Pricing model

$0.10 per million input tokens; cached input costs $0.01 per million tokens; no output-token charges

Deployment

Regional processing is available in the US and EU

Privacy

Zero Data Retention is available to eligible customers

Licence

OpenAI Terms of Use

• The Decisions API was released in beta. ^[1]

  Released the Decisions API in beta with gpt-6-luna .

• The API turns text and images into typed answers. ^[1]

  Turn text and images into typed answers 10x faster than the Responses API.

• The beta uses gpt-6-luna. ^[1]

  Released the Decisions API in beta with gpt-6-luna .

• The Decisions API is generally available with GPT-6 Luna through the dedicated Decisions endpoint. ^[2]

  Decisions API is generally available today with GPT‑6 Luna through the dedicated Decisions endpoint.

• It accepts text, images, and native JSON as context and returns a probability, choice, or score. ^[2]

  Using the Decisions API is simple: developers define a question and its allowed answers, then provide context as text, images, or native JSON.

• It supports up to 400 questions per request. ^{[2] [3]}

  Developers can also pass native JSON inputs, include images in question instructions, and ask up to 400 questions per request, twice the previous limit.

• The API integrates natively with GPT-Live for decisions during live conversations. ^[2]

  Decisions API now [integrates natively with GPT‑Live⁠(opens in a new window)](https://developers.openai.com/api/docs/guides/decisions-voice), helping applications make fast, focused decisions during live conversations.

• Input tokens cost $0.10 per million, cached input tokens cost $0.01 per million, and there are no output-token charges. ^[2]

  For 30-minute and 12-hour cached writes, [read our pricing guide.⁠(opens in a new window)](https://developers.openai.com/api/docs/pricing?utm_source=chatgpt.com) You only pay for input tokens: there are no output-token charges.

• Regional processing is available in the US and EU. ^[2]

  Regional processing is available in the US and EU, and [Zero Data Retention⁠(opens in a new window)](https://developers.openai.com/api/docs/guides/your-data) is available to eligible customers.

• Edit generated images through conversation with Gemini Nano Banana 2.1 Daily brief 2026-10-06