API Reference

Content Provenance Checks

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create content provenance check

$ openai content-provenance-checks create

POST/content_provenance_checks

Check whether an image or audio file contains known OpenAI provenance signals. Learn more about content provenance.

If not_detected, it means the tool did not find supported signals in the uploaded file. The content could still have been generated by OpenAI if the metadata was stripped or has evidence of tampering, the watermark was degraded, it comes from a legacy generation model, or it was created before provenance signals were available. Content could also still be AI-generated by another company’s model, which the tool currently does not detect.

ParametersExpand Collapse

--file: file path

The image or audio file to check for supported OpenAI provenance signals.

ReturnsExpand Collapse

content_provenance_check: object { created_at, object, results }

created_at: number

The Unix timestamp, in seconds, when the provenance check was created.

object: "content_provenance_check"

The object type. Always content_provenance_check for this endpoint.

results: array of object { generated_at, issuer, model, 3 more } or object { generated_at, model, outcome, type }

The provenance results that apply to the uploaded file. Image results include C2PA and SynthID; audio results include SynthID.

Create content provenance check

CLI Tool

HTTP

Python

TypeScript

Go

Ruby

Java

CLI Tool

openai content-provenance-checks create \
  --api-key 'My API Key' \
  --file 'Example data'

200 example

{
  "created_at": 0,
  "object": "content_provenance_check",
  "results": [
    {
      "generated_at": "generated_at",
      "issuer": "issuer",
      "model": "model",
      "outcome": "detected",
      "type": "c2pa",
      "validation_state": "trusted"
    }
  ]
}

Returns Examples

200 example

{
  "created_at": 0,
  "object": "content_provenance_check",
  "results": [
    {
      "generated_at": "generated_at",
      "issuer": "issuer",
      "model": "model",
      "outcome": "detected",
      "type": "c2pa",
      "validation_state": "trusted"
    }
  ]
}