curl -X POST 'https://api.openai.com/v1/decisions' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "example-model",
  "input": "example-input",
  "questions": [
    {
      "type": "predicate",
      "name": "example-name",
      "instructions": "example-instructions"
    }
  ]
}'

# POST /decisions (OpenAI API)
Base URL: https://api.openai.com/v1
Auth: Authorization; OpenAI API key; required.
Request formats: application/json.
Last verified: 2026-10-07

> Create a decision

## Critical Gotchas
* The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
* Audio transcription uploads use multipart form data rather than a JSON request body.

## cURL
curl -X POST 'https://api.openai.com/v1/decisions' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "example-model",
  "input": "example-input",
  "questions": [
    {
      "type": "predicate",
      "name": "example-name",
      "instructions": "example-instructions"
    }
  ]
}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| model | body | string | Yes | Request body field model. |
| input | body | string | Yes | The text or images to evaluate for every question. Provide a text string or u... |
| questions | body | object[] | Yes | Request body field questions. |
| safety_identifier | body | string | No | Opaque caller-provided end-user identifier, scoped by the verified org. Match... |

## Response example
{"model":"string","answers":[{}]}

---
Need an API key? Get one at https://platform.openai.com/api-keys

POST

POST /decisions — OpenAI API

OpenAI API key (required); https://api.openai.com/v1

OpenAI API

Create a decision

Base URL: https://api.openai.com/v1
Auth: Authorization: Bearer <OPENAI_API_KEY>
Last verified: 2026-10-07 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 268 tokens · Vary: Accept

Critical gotchas

The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.

Audio transcription uploads use multipart form data rather than a JSON request body.

cURL

curl -X POST 'https://api.openai.com/v1/decisions' \  -H "Authorization: Bearer $OPENAI_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "model": "example-model",  "input": "example-input",  "questions": [    {      "type": "predicate",      "name": "example-name",      "instructions": "example-instructions"    }  ]}'

Parameters

Name	In	Type	Required	Description
model	body	string	Yes	Request body field model.
input	body	string	Yes	The text or images to evaluate for every question. Provide a text string or user messages containing text and inline images. Images must be inline data URLs; at most 128 images are allowed across all messages in one request. External URLs, files, audio, tools, and item references are not supported.
questions	body	object[]	Yes	Request body field questions.
safety_identifier	body	string	No	Opaque caller-provided end-user identifier, scoped by the verified org. Match Responses' limit; this is never the authenticated user identity.

Response 200 OK

{
  "model": "string",
  "answers": [
    {
      "type": "predicate",
      "name": "string",
      "probability": 0
    }
  ],
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0
    },
    "output_tokens": 0,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 0
  }
}

Get a free OpenAI API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.