Images

One endpoint covers every image model, whether it is generating from scratch or working from images you supply.

POST /v1/images

Send a prompt on its own to generate. Attach input_references and the same request becomes reference-guided, so editing, remixing and style transfer are all the same call with the same parameters.

What you can do

• Generate images - create images from text descriptions.
• Edit and remix - pass input_references to guide the result with existing images.
• Shape the output - aspect_ratio on every model, plus quality or resolution to control how much detail the model spends.

Browse available models at Models.

Endpoints

Every endpoint expects a bearer token in the Authorization header. Create keys at Manage API Keys.

Errors

All errors follow the OpenAI structured shape:

{ "error": { "type": "invalid_request_error", "message": "..." } }