## Generate images
`POST /v1/images/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/images/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-2.5-flare",
"prompt": "A clean editorial product photograph of a translucent green glass bottle on pale stone, soft morning light",
"size": "1536x1024",
"quality": "high",
"background": "opaque",
"output_format": "jpeg",
"output_compression": 85,
"moderation": "auto",
"n": 1
}'
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Data exchange format.
## Request body
Model ID: `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare`.
Text description of the image to generate. Length: `1`–`32,000` characters.
Number of images to generate. Supported range: `1`–`10`.
`auto` or a custom `WIDTHxHEIGHT` value. Width and height must be multiples of 16, the aspect ratio must be between 1:3 and 3:1, neither edge may exceed 3,840 pixels, and total pixels must be between 655,360 and 8,294,400.
Rendering quality: `low`, `medium`, `high`, `xhigh`, `max`, or `auto`.
Background mode: `auto`, `opaque`, or `transparent`. Transparent backgrounds require PNG or WebP output.
Output format: `png`, `jpeg`, or `webp`.
JPEG or WebP compression level from `0` through `100`. Ignored for PNG output.
Moderation strictness: `auto` or `low`.
## Generation response
```json 200 theme={null}
{
"created": 1788926400,
"background": "opaque",
"data": [
{
"b64_json": "iVBORw0KGgoAAA..."
}
],
"output_format": "jpeg",
"quality": "high",
"size": "1536x1024"
}
```
Creation time as a Unix timestamp in seconds.
Resolved background mode: `opaque` or `transparent`.
Generated image results.
Base64-encoded image data.
Returned image format: `png`, `jpeg`, or `webp`.
Quality level used for the result.
Resolved output dimensions as `WIDTHxHEIGHT`.
## Edit images
`POST /v1/images/edits`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/images/edits \
--header 'Authorization: Bearer YOUR_API_KEY' \
--form 'model=gpt-image-2.5-sunburst' \
--form 'image[]=@/path/to/product.png' \
--form 'mask=@/path/to/mask.png' \
--form 'prompt=Keep the product unchanged and replace the background with a warm studio gradient' \
--form 'size=1536x1024' \
--form 'quality=xhigh' \
--form 'background=opaque' \
--form 'output_format=png' \
--form 'n=1'
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Set automatically when using multipart form uploads.
## Request body
Model ID: `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare`.
One source image file. Use `image[]` instead when uploading multiple images. Each source image must be smaller than 50 MB.
Up to 16 source image files. Do not send both `image` and `image[]`.
Optional edit mask. It guides the edit rather than defining a guaranteed pixel-exact boundary. It must contain an alpha channel, match the first source image's format and dimensions, and be smaller than 50 MB. With multiple source images, the mask applies to the first image.
Instructions describing the edit. Length: `1`–`32,000` characters.
Number of edited images to return. Supported range: `1`–`10`.
`auto` or a valid custom `WIDTHxHEIGHT` value using the same limits as image generation.
Rendering quality: `low`, `medium`, `high`, `xhigh`, `max`, or `auto`.
Background mode: `auto`, `opaque`, or `transparent`. Transparent backgrounds require PNG or WebP output.
Output format: `png`, `jpeg`, or `webp`.
JPEG or WebP compression level from `0` through `100`. Ignored for PNG output.
Moderation strictness: `auto` or `low`.
## Edit response
```json 200 theme={null}
{
"created": 1788926460,
"background": "opaque",
"data": [
{
"b64_json": "iVBORw0KGgoAAA..."
}
],
"output_format": "png",
"quality": "xhigh",
"size": "1536x1024"
}
```
Creation time as a Unix timestamp in seconds.
Resolved background mode: `opaque` or `transparent`.
Edited image results.
Base64-encoded edited image data.
Returned image format: `png`, `jpeg`, or `webp`.
Quality level used for the result.
Resolved output dimensions as `WIDTHxHEIGHT`.