GET
/v1/schemas/openai/image/images%2Fedits
Accept:
Request body
15 properties · 2 required · 2 $defs| property | type | description | constraints |
|---|---|---|---|
| images* | ImageRefParam[] | Input image references to edit. For GPT image models, you can provide up to 16 images. | items ≥ 1 · items ≤ 16 |
| prompt* | string | A text description of the desired image edit. | length ≥ 1 · length ≤ 32000 |
| model | string | enum | The model to use for image editing. | nullable · default: "gpt-image-1.5" |
| mask | any | any | Reference an input image by either URL or uploaded file ID. Provide exactly one of `image_url` or `file_id`. | |
| n | integer | The number of edited images to generate. | 1 ≤ n ≤ 10 · nullable |
| quality | enum | Output quality for GPT image models. | low | medium | high | auto · nullable |
| input_fidelity | enum | Controls fidelity to the original input image(s). | high | low · nullable |
| size | enum | Requested output image size. | auto | 1024x1024 | 1536x1024 | 1024x1536 · nullable |
| user | string | A unique identifier representing your end-user, which can help OpenAI monitor and detect abuse. | |
| output_format | enum | Output image format. Supported for GPT image models. | png | jpeg | webp · nullable |
| output_compression | integer | Compression level for `jpeg` or `webp` output. | 0 ≤ n ≤ 100 · nullable |
| moderation | enum | Moderation level for GPT image models. | low | auto · nullable |
| background | enum | Background behavior for generated image output. | transparent | opaque | auto · nullable |
| stream | boolean | Stream partial image results as events. | nullable |
| partial_images | integer | The number of partial images to generate. This parameter is used for streaming responses that return partial images. Value must be between 0 and 3. When set to 0, the response will be a single image sent in one streaming event. | 0 ≤ n ≤ 3 · default: 0 · nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"openai","endpointId":"images/edits","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}