API Reference
OpenAI Image Edit
OpenAI Image Edit
Preview guide
Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.
Updated · Reviewed
Endpoint and authentication
POST https://api.tu-zi.com/v1/images/edits
Transport: multipart
Use an inference API key. Examples contain placeholders; read credentials from environment variables.
Authorization: Bearer YOUR_API_KEY
Before calling
- Examples use this site's address. For another gateway, replace only the site address and keep the full endpoint path.
- Replace
YOUR_MODELwith the exact model ID from the marketplace. - Use an inference key created on this site's token page. Set the
API_KEYenvironment variable or replaceYOUR_API_KEY, as shown in the selected example. - Prepare local file(s)
input.png, or replace their paths in the example.
Constraints
This page describes the base protocol. Use the selected model quick start for supported fields, enums, limits and asynchronous behavior. Replace YOUR_MODEL. Form initial values are not upstream defaults. Inspect every item in data[]: url is an image download URL; b64_json is Base64-encoded image bytes to decode and save, not a URL. Handle either form. HTTP 200, empty data[] or text alone does not prove image generation succeeded. Do not send the site API key when downloading result URLs. Save and validate the actual image format/MIME; renaming an extension does not convert an image. image=@input.png is cURL local file-upload syntax. Use files in Python or FormData/Blob in JavaScript; never send @input.png or a local path as a JSON string. Let the client library set the multipart Content-Type and boundary; do not set application/json. Use multiple images, masks, sizes and output formats only when explicitly supported by the selected model.
Minimal request example
{
"model": "YOUR_MODEL",
"prompt": "Add a blue background",
"image": "@input.png"
}
Body parameters
| Field | Type | Required | Description / constraints |
|---|---|---|---|
| model | string | Yes | Image editing model identifier. |
| image | file | Yes | Original image file to edit. |
| mask | file | No | Optional PNG mask; transparent areas indicate regions to edit. |
| prompt | string | Yes | Image editing instructions. Example: 保留主体,将背景替换为晴朗海滩。 |
| size | string | No | Output image dimensions. Form initial value (not an upstream default): "1024x1024" Values: "1024x1024", "1536x1024", "1024x1536" |
| n | integer | No | Number of images to generate. Form initial value (not an upstream default): 1 Range in this definition: 1 ~ 10 |
Response fields
| Field | Type | Description / constraints |
|---|---|---|
| data[].url | string | Image URL in URL output mode. |
| data[].b64_json | string | Base64 image when that output mode is supported. |
Illustrative response; some endpoints show essential fields only. Optional fields may be absent.
{
"created": 1793491200,
"data": [
{
"url": "https://example.com/result.png"
}
]
}
Errors and retries
Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.
Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.
兔子API