Azure Image editing - ZnapAI Documentation

Request

curl --location 'https://api.znapai.com/azure/openai/deployments/gpt-image-2/images/edits?api-version=2025-04-01-preview' \
--header 'Authorization: Bearer $ZnapAI_API_KEY' \
--header 'spend-logs-metadata: {"user_id": "user-123", "project_id": "proj_abc", "env": "production"}' \
--form 'prompt="Replace the background with a clean white studio surface, keep the product exactly as is"' \
--form 'image=@"/path/to/image.png"' \
--form 'size="1024x1024"' \
--form 'quality="low"' \
--form 'output_format="png"'

Input

Response

{
    "created": 1778264554,
    "background": "opaque",
    "data": [
        {
            "b64_json": "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"
        }
    ],
    "output_format": "png",
    "quality": "low",
    "size": "1024x1024",
    "usage": {
        "input_tokens": 39,
        "input_tokens_details": {
            "image_tokens": 16,
            "text_tokens": 23
        },
        "output_tokens": 196,
        "total_tokens": 235
    }
}

Image from base64 data

Parameters

header

An optional header used for spend logging metadata, containing JSON properties like user_id, project_id, and env.

string

required

Text description of the desired edit.

file | array

required

Reference image(s) to edit. Up to 16 images supported. Must be uploaded via multipart form data — image URLs are not supported.

-F "image=@file.png" or -F "image[]=@file1.png" -F "image[]=@file2.png"

file | object

Alpha mask PNG. Transparent areas are regenerated; opaque areas are preserved. Must be uploaded via multipart — mask URLs are not supported.

-F "mask=@mask.png"

string

default:"1024x1024"

Output image dimensions. Supports arbitrary WIDTHxHEIGHT where both edges are multiples of 16, aspect ratio between 1:3 and 3:1, max edge 3840.Standard values: 1024x1024, 1536x1024, 1024x1536, auto.Supported values depend on the selected model. See the OpenAI image generation guide for the latest model-specific ranges.

string

default:"auto"

Allowed values: low, medium, high, auto

integer

default:"1"

Number of edited images to return.

string

default:"png"

Allowed values: png, jpeg

webp is not supported on Azure gpt-image-2.

integer

Compression level (0–100). Only applies when output_format is jpeg.

string

default:"auto"

Allowed values: auto, low

boolean

default:"false"

Stream partial edit results.

integer

Number of partial images during streaming (0–3). Only used when stream is true.

Params to Avoid

Param	Reason
`response_format: "url"`	Returns empty response from Azure
`image_url`	Azure does not support image URLs — use file upload via multipart
`input_fidelity: "low"`	gpt-image-2 rejects it on edits
`background: "transparent"`	Not supported on Azure gpt-image-2
`output_format: "webp"`	Not supported on Azure gpt-image-2
`style: "vivid"`	dall-e-3 only
`spend-logs-metadata`	This metadata must be passed as an HTTP header, not in the JSON request body

​Request

​Input

​Response

​Image from base64 data

​Parameters

​Params to Avoid

Request

Input

Response

Image from base64 data

Parameters

Params to Avoid