> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL.

## Create image edit

**post** `/images/edits`

Creates an edited or extended image given one or more source images and a prompt. This endpoint supports GPT Image models.

### Body Parameters

Content type: `application/json`

- `images: array of object { file_id, image_url }`

  Input image references to edit.
  For GPT image models, you can provide up to 16 images.

  `minItems: 1`, `maxItems: 16`

  - `file_id: optional string`

    The File API ID of an uploaded image to use as input.

  - `image_url: optional string`

    A fully qualified URL or base64-encoded data URL.

    `maxLength: 20971520`, `format: uri`

- `prompt: string`

  A text description of the desired image edit.

  `minLength: 1`, `maxLength: 32000`

- `background: optional "transparent" or "opaque" or "auto" or null (default: "auto")`

  Set the background of the generated image output. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`.

  - `"transparent"`

  - `"opaque"`

  - `"auto"`

- `complexity: optional "low" or "medium" or "high" or null`

  Computation spent planning the image, independently of rendering quality. Uses the image model's configured default when omitted. For SVG output, controls the reference image, independently of the SVG author's reasoning.

  - `"low"`

  - `"medium"`

  - `"high"`

- `frame_count: optional integer or null`

  Number of frames for GIF output. Accepts integers from 2 through 16. Defaults to 9 when omitted. Only supported with output_format=gif. The requested size must satisfy the selected model's GIF size limits. GIF output does not support streaming, partial images, masks, or custom output compression. Requires access to the GIF preview for the selected model.

  `minimum: 2`, `maximum: 16`

- `frame_duration_ms: optional integer or null`

  Requested delay per GIF frame, in milliseconds. Defaults to 200 when omitted. GIF output rounds to the nearest 10 ms and caps the encoded delay at 655,350 ms per frame. Only supported with output_format=gif.

  `minimum: 20`

- `input_fidelity: optional "high" or "low" or null`

  Control how much effort the model will exert to match the style and features, especially facial features, of input images. Supports `high` and `low` on `gpt-image-1.5`; `gpt-image-1-mini` supports only `low`. For `gpt-image-2`, omit this parameter. Defaults to `low` on supported models.

  - `"high"`

  - `"low"`

- `markup: optional object { file_id, image_url }`

  A transparent PNG overlaid on the first image, referenced by file ID, HTTPS URL, or base64 data URL. Must match that image's dimensions after orientation and contain transparent pixels. Supports GPT Image 2.5. Cannot be combined with mask.

  - `file_id: optional string`

    The File API ID of an uploaded image to use as input.

  - `image_url: optional string`

    A fully qualified URL or base64-encoded data URL.

    `maxLength: 20971520`, `format: uri`

- `mask: optional object { file_id, image_url }`

  Reference an input image by either URL or uploaded file ID.
  Provide exactly one of `image_url` or `file_id`.

  - `file_id: optional string`

    The File API ID of an uploaded image to use as input.

  - `image_url: optional string`

    A fully qualified URL or base64-encoded data URL.

    `maxLength: 20971520`, `format: uri`

- `model: optional string or "gpt-image-1.5" or "gpt-image-2" or "gpt-image-2-2026-04-21" or 9 more or null (default: "gpt-image-2.5-sunburst")`

  The GPT image model to use for image editing, including `gpt-image-2`, its dated
  snapshot `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`,
  `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`,
  `gpt-image-2.5-flare-2026-09-08`, `gpt-image-2.6-sunburst`, and `gpt-image-2.6-flare`.
  Defaults to `gpt-image-2.5-sunburst`.

  `gpt-image-1` was shut down on October 23, 2026. Use
  `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` instead.

  - `string`

  - `"gpt-image-1.5" or "gpt-image-2" or "gpt-image-2-2026-04-21" or 9 more`

    The GPT image model to use for image editing, including `gpt-image-2`, its dated
    snapshot `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`,
    `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`,
    `gpt-image-2.5-flare-2026-09-08`, `gpt-image-2.6-sunburst`, and `gpt-image-2.6-flare`.
    Defaults to `gpt-image-2.5-sunburst`.

    `gpt-image-1` was shut down on October 23, 2026. Use
    `gpt-image-2.5-sunburst` or `gpt-image-2.5-flare` instead.

    - `"gpt-image-1.5"`

    - `"gpt-image-2"`

    - `"gpt-image-2-2026-04-21"`

    - `"gpt-image-2.5-sunburst"`

    - `"gpt-image-2.5-sunburst-2026-09-08"`

    - `"gpt-image-2.5-flare"`

    - `"gpt-image-2.5-flare-2026-09-08"`

    - `"gpt-image-2.6-sunburst"`

    - `"gpt-image-2.6-flare"`

    - `"gpt-image-1"`

    - `"gpt-image-1-mini"`

    - `"chatgpt-image-latest"`

- `moderation: optional "low" or "auto" or null (default: "auto")`

  Moderation level for GPT image models.

  - `"low"`

  - `"auto"`

- `n: optional integer or null (default: 1)`

  The number of edited images to generate.

  `minimum: 1`, `maximum: 10`

- `output_compression: optional integer or null`

  Compression level for `jpeg` or `webp` output.

  `minimum: 0`, `maximum: 100`

- `output_format: optional "png" or "webp" or "jpeg" or 2 more or null (default: "png")`

  Output image format. Supported for GPT image models. SVG output requires a supported image model and project access.

  - `"png"`

  - `"webp"`

  - `"jpeg"`

  - `"gif"`

  - `"svg"`

- `partial_images: optional integer or null (default: 0)`

  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.

  Note that the final image may be sent before the full number of partial images
  are generated if the full image is generated more quickly.

  `minimum: 0`, `maximum: 3`

- `quality: optional "low" or "medium" or "high" or 3 more or null (default: "auto")`

  Output quality for GPT image models. The GPT image models support `low`, `medium`,
  and `high`. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their
  `2026-09-08` snapshots, also support `xhigh` and `max`. Defaults to `auto`.

  - `"low"`

  - `"medium"`

  - `"high"`

  - `"xhigh"`

  - `"max"`

  - `"auto"`

- `safety_identifier: optional string or null`

  A stable identifier for an end user in your organization, used for safety monitoring and abuse detection. Hash a username or email address to avoid sending identifying information. A non-empty value takes precedence over the deprecated `user` parameter. If omitted, null, or empty, the API uses `user` when available. [Learn more](/api/docs/guides/safety-best-practices#implement-safety-identifiers).

  `maxLength: 128`

- `size: optional string or "auto" or "1024x1024" or "1536x1024" or "1024x1536" or null (default: "auto")`

  The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing.

  - `string`

  - `"auto" or "1024x1024" or "1536x1024" or "1024x1536"`

    The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing.

    - `"auto"`

    - `"1024x1024"`

    - `"1536x1024"`

    - `"1024x1536"`

- `stream: optional boolean or null (default: false)`

  Stream partial image results as events.

- `svg: optional object { model, reasoning }  or null`

  Selects the author model and reasoning effort for `output_format=svg`. Supply `svg.model` when SVG model selection is enabled. Otherwise, omit this object. SVG output requires `n=1` and cannot use streaming, partial images, or output compression.

  - `model: optional string`

    `minLength: 1`

  - `reasoning: optional object { effort }  or null`

    Reasoning effort for SVG authoring. When omitted, uses the author model's default in both Images and Responses.

    - `effort: optional "none" or "minimal" or "low" or 4 more`

      Controls how much effort the model should spend on reasoning for this request.

      - `"none"`

      - `"minimal"`

      - `"low"`

      - `"medium"`

      - `"high"`

      - `"xhigh"`

      - `"max"`

- `user: optional string`

  Deprecated: use `safety_identifier` instead. This parameter remains accepted for backward compatibility and is used when `safety_identifier` is omitted, null, or empty. [Learn more](/api/docs/guides/safety-best-practices#implement-safety-identifiers).

### Returns

- `ImagesResponse object { created, background, data, 6 more }`

  The response from the image generation endpoint.

  - `created: integer`

    The Unix timestamp (in seconds) of when the image was created.

    `format: unixtime`

  - `background: optional "transparent" or "opaque"`

    The background parameter used for the image generation. Either `transparent` or `opaque`.

    - `"transparent"`

    - `"opaque"`

  - `data: optional array of Image`

    The list of generated images.

    - `b64_json: optional string`

      The base64-encoded JSON of the generated image. Returned by default for GPT image models, or when `response_format` is set to `b64_json` for models that support that parameter.

    - `revised_prompt: optional string`

      The revised prompt used to generate the image, for models that support prompt revision. Not returned by GPT image models.

    - `url: optional string`

      The URL of the generated image when `response_format` is set to `url` for models that support that parameter. Unsupported for GPT image models.

      `format: uri`

  - `output_format: optional "png" or "webp" or "jpeg" or 2 more`

    The output format of the generated or edited image.

    - `"png"`

    - `"webp"`

    - `"jpeg"`

    - `"gif"`

    - `"svg"`

  - `quality: optional "low" or "medium" or "high" or 2 more`

    The quality of the image generated. One of `low`, `medium`, `high`, `xhigh`, or `max`.

    - `"low"`

    - `"medium"`

    - `"high"`

    - `"xhigh"`

    - `"max"`

  - `safety_identifier: optional string or null`

    The effective safety identifier used for safety monitoring and abuse detection. This is the non-empty `safety_identifier` from the request, or the deprecated `user` value when `safety_identifier` is omitted, null, or empty.

  - `size: optional string or "1024x1024" or "1024x1536" or "1536x1024"`

    The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`.

    - `string`

    - `"1024x1024" or "1024x1536" or "1536x1024"`

      The image dimensions as a `WIDTHxHEIGHT` string, for example `1536x864`.

      - `"1024x1024"`

      - `"1024x1536"`

      - `"1536x1024"`

  - `svg_usage: optional object { input_tokens, model, output_tokens, 2 more }`

    Token usage for SVG authoring, separate from image rendering usage.

    - `input_tokens: integer`

    - `model: string`

    - `output_tokens: integer`

    - `reasoning_tokens: integer`

    - `total_tokens: integer`

  - `usage: optional object { input_tokens, input_tokens_details, output_tokens, 2 more }`

    Token usage information for image generation with GPT Image models.

    - `input_tokens: integer`

      The number of tokens (images and text) in the input prompt.

    - `input_tokens_details: object { image_tokens, text_tokens }`

      The input tokens detailed information for the image generation.

      - `image_tokens: integer`

        The number of image tokens in the input prompt.

      - `text_tokens: integer`

        The number of text tokens in the input prompt.

    - `output_tokens: integer`

      The number of output tokens generated by the model.

    - `total_tokens: integer`

      The total number of tokens (images and text) used for the image generation.

    - `output_tokens_details: optional object { image_tokens, text_tokens }`

      The output token details for the image generation.

      - `image_tokens: integer`

        The number of image output tokens generated by the model.

      - `text_tokens: integer`

        The number of text output tokens generated by the model.

### Example

```http
curl https://api.openai.com/v1/images/edits \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -d '{
          "images": [
            {
              "image_url": "https://example.com/source-image.png"
            }
          ],
          "prompt": "Add a watercolor effect to this image",
          "model": "gpt-image-1.5",
          "quality": "high",
          "size": "1024x1024"
        }'
```

#### 200 — Example

```json
{
  "created": 0,
  "background": "transparent",
  "data": [
    {
      "b64_json": "b64_json",
      "revised_prompt": "revised_prompt",
      "url": "https://example.com"
    }
  ],
  "output_format": "png",
  "quality": "low",
  "safety_identifier": "safety_identifier",
  "size": "1024x1024",
  "svg_usage": {
    "input_tokens": 0,
    "model": "model",
    "output_tokens": 0,
    "reasoning_tokens": 0,
    "total_tokens": 0
  },
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 0,
    "total_tokens": 0,
    "output_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}
```

### Edit image

```http
curl -s -D >(grep -i x-request-id >&2) \
  -o >(jq -r '.data[0].b64_json' | base64 --decode > gift-basket.png) \
  -X POST "https://api.openai.com/v1/images/edits" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "model=gpt-image-1.5" \
  -F "image[]=@body-lotion.png" \
  -F "image[]=@bath-bomb.png" \
  -F "image[]=@incense-kit.png" \
  -F "image[]=@soap.png" \
  -F 'prompt=Create a lovely gift basket with these four items in it'
```

### JSON request with image URL (json_with_url)

```http
curl https://api.openai.com/v1/images/edits \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -d '{
          "images": [
            {
              "image_url": "https://example.com/source-image.png"
            }
          ],
          "prompt": "Add a watercolor effect to this image",
          "model": "gpt-image-1.5",
          "quality": "high",
          "size": "1024x1024"
        }'
```

### JSON request with uploaded file id (json_with_file_id)

```http
curl https://api.openai.com/v1/images/edits \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $OPENAI_API_KEY" \
    -d '{
          "images": [
            {
              "file_id": "file-abc123"
            }
          ],
          "prompt": "Replace the background with a snowy mountain scene",
          "mask": {
            "file_id": "file-mask123"
          },
          "model": "gpt-image-1.5",
          "output_compression": 100,
          "output_format": "png"
        }'
```

### Streaming

```http
curl -s -N -X POST "https://api.openai.com/v1/images/edits" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F "model=gpt-image-1.5" \
  -F "image[]=@body-lotion.png" \
  -F "image[]=@bath-bomb.png" \
  -F "image[]=@incense-kit.png" \
  -F "image[]=@soap.png" \
  -F 'prompt=Create a lovely gift basket with these four items in it' \
  -F "stream=true"
```

#### Response example

```json
event: image_edit.partial_image
data: {"type":"image_edit.partial_image","b64_json":"...","partial_image_index":0}

event: image_edit.completed
data: {"type":"image_edit.completed","b64_json":"...","usage":{"total_tokens":100,"input_tokens":50,"output_tokens":50,"input_tokens_details":{"text_tokens":10,"image_tokens":40}}}
```
