> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nano-gpt.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Image Edits

> OpenAI-compatible image editing endpoint with multipart and JSON inputs

## Overview

Use the image edits endpoint to modify one or more input images with a text prompt. This is an OpenAI-compatible image editing endpoint.

For new JSON-only image-to-image generation flows, also consider the dedicated [Image API](/api-reference/image-generation), which uses `input_references` and `POST /api/v1/images`.

Both paths are supported aliases:

* `POST /api/v1/images/edit`
* `POST /api/v1/images/edits`

## Authentication

Use either header:

* `Authorization: Bearer YOUR_API_KEY`
* `x-api-key: YOUR_API_KEY`

## Accountless x402 Payment

JSON image edit requests can be quoted without an account or API key on supported deployments when you explicitly opt in to the quote flow:

```bash theme={null}
curl -i https://nano-gpt.com/api/v1/images/edits \
  -H "Content-Type: application/json" \
  -H "x-x402: true" \
  -d '{
    "model": "gpt-image-1",
    "prompt": "Remove the background",
    "imageDataUrl": "data:image/png;base64,..."
  }'
```

To request an accountless x402 quote, send the API request without `Authorization` or `x-api-key`, and include `x-x402: true`. NanoGPT will return `402 Payment Required` with available payment options. This endpoint supports accountless x402 payments where listed by `GET /api/v1/x402/endpoints`, including Lightning L402 when advertised. Multipart uploads require normal authentication before conversion. See [Accountless x402 API Payments](/api-reference/miscellaneous/x402) for the full flow.

If you receive `401 missing_api_key` immediately, check that the initial quote request includes `x-x402: true`. Without that header, NanoGPT does not enter the x402 quote flow.

## Multipart Request

Send `multipart/form-data` when uploading files.

| Field     | Type                    | Required | Description                                                                       |
| --------- | ----------------------- | -------- | --------------------------------------------------------------------------------- |
| `prompt`  | string                  | Yes      | Edit instruction.                                                                 |
| `image`   | file or string          | Yes\*    | Input image file, image URL, or data URL.                                         |
| `image[]` | repeated file or string | Yes\*    | Repeated image inputs for multi-image editing.                                    |
| `mask`    | file                    | No       | Optional mask image for inpainting-capable models.                                |
| `model`   | string                  | No       | Image-edit-capable model. Defaults to an image-edit-capable default when omitted. |
| `size`    | string                  | No       | Requested output size, when supported by the model.                               |
| `n`       | integer                 | No       | Number of outputs, when supported by the model.                                   |

\*Provide `image` or one or more `image[]` fields.

Other image-generation parameters may pass through when supported by the selected model.

```bash theme={null}
curl -X POST https://nano-gpt.com/api/v1/images/edits \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -F model=gpt-image-1 \
  -F prompt="Remove the background" \
  -F image=@product.png \
  -F size=1024x1024
```

### Multi-image Multipart

```bash theme={null}
curl -X POST https://nano-gpt.com/api/v1/images/edit \
  -H "x-api-key: $NANOGPT_API_KEY" \
  -F model=gpt-image-1 \
  -F prompt="Combine these references into one product image" \
  -F "image[]=@reference-1.png" \
  -F "image[]=@reference-2.jpg"
```

## JSON Request

Send JSON when you already have images as data URLs.

```json theme={null}
{
  "model": "gpt-image-1",
  "prompt": "Remove the background",
  "imageDataUrl": "data:image/png;base64,...",
  "maskDataUrl": "data:image/png;base64,..."
}
```

### Multi-image JSON

```json theme={null}
{
  "model": "gpt-image-1",
  "prompt": "Combine these references into one product image",
  "imageDataUrls": [
    "data:image/png;base64,...",
    "data:image/jpeg;base64,..."
  ]
}
```

## Response

Responses follow the same image response conventions as image generation. Depending on request parameters and model support, returned items may contain `url` or `b64_json`.

```json theme={null}
{
  "created": 1778155200,
  "data": [
    {
      "url": "https://..."
    }
  ]
}
```

## Common Errors

| Code                     | Description                         |
| ------------------------ | ----------------------------------- |
| `missing_image_input`    | `image` is required.                |
| `image_input_too_large`  | Upload or input image is too large. |
| `invalid_multipart_body` | Multipart body could not be parsed. |
| `rate_limit_exceeded`    | Too many image edit uploads.        |

## Notes

* Multipart uploads have strict size limits.
* Generated URLs are temporary unless another page explicitly guarantees longer retention.
* Use `GET /api/v1/image-models` to discover image-edit-capable models and supported parameters.