> ## Documentation Index > Fetch the complete documentation index at: https://docs.omniall.ai/llms.txt > Use this file to discover all available pages before exploring further. # Edit image > OpenAI-compatible image edit / inpaint. **Path:** `POST https://api.omniall.ai/v1/images/edits` Supports **`application/json`** (`image`/`mask` as URL or Base64) and **`multipart/form-data`** (file upload). Multiple images: JSON `image` string array; form repeated `image[]` file parts. Use `prompt` to describe edits; optional `mask` for editable regions. ## OpenAPI ````yaml openapi/xgapi-public.yaml POST /v1/images/edits openapi: 3.0.3 info: title: Omniall AI Public API description: >- Omniall AI public API. Website: https://omniall.ai — API host: https://api.omniall.ai — Model Square: https://omniall.ai/pricing version: 1.1.0 servers: - url: https://api.omniall.ai description: Production security: - bearerAuth: [] tags: - name: Models description: List models available to your API key. - name: ChatGPT Chat Completions x-group: ChatGPT description: OpenAI Chat Completions (`POST /v1/chat/completions`). - name: Responses description: OpenAI Responses API (`POST /v1/responses`). - name: Claude description: Anthropic Messages API (`POST /v1/messages`). - name: Gemini description: Google Gemini generateContent / streamGenerateContent. - name: Images description: >- Image generation (OpenAI Images), vendor guides, and Midjourney proxy APIs. - name: Video description: Async video tasks. - name: Audio description: Speech and related audio APIs. - name: Rerank description: Document reranking. paths: /v1/images/edits: post: tags: - Images summary: Edit image description: >- OpenAI-compatible image edit / inpaint. **Path:** `POST https://api.omniall.ai/v1/images/edits` Supports **`application/json`** (`image`/`mask` as URL or Base64) and **`multipart/form-data`** (file upload). Multiple images: JSON `image` string array; form repeated `image[]` file parts. Use `prompt` to describe edits; optional `mask` for editable regions. operationId: createImageEdit requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageEditRequest' examples: image_to_image: summary: Image-to-image (JSON) value: model: gpt-image-1 prompt: Replace the background with a clean white studio backdrop image: https://example.com/product.png 'n': 1 multi_reference: summary: Image-to-image · multi-reference (JSON) value: model: gpt-image-1 prompt: >- Blend composition and subject from both references into one ad image image: - https://example.com/ref-a.png - https://example.com/ref-b.png 'n': 1 multipart/form-data: schema: type: object required: - model - prompt - image description: >- OpenAI-compatible `multipart/form-data` edit request. Send text fields and image files in one form; the gateway forwards files upstream. properties: model: type: string description: Edit-capable model id. example: gpt-image-1 prompt: type: string description: Instruction describing how to edit the image. example: Replace the background with a clean white studio backdrop image: type: string format: binary description: >- Source image file. Use field name `image` for one file; for multiple references use repeated `image[]` or `image[0]`, `image[1]` file parts. mask: type: string format: binary description: Optional mask PNG. Transparent pixels mark editable regions. 'n': type: string description: Number of outputs (string in form, e.g. `1`). example: '1' size: type: string description: Output size when supported. quality: type: string description: Quality tier when supported. response_format: type: string enum: - url - b64_json description: Response format. examples: form_image_to_image: summary: Image-to-image (multipart form) value: model: gpt-image-1 prompt: Replace the background with a clean white studio backdrop 'n': '1' responses: '200': description: Edited image result content: application/json: schema: $ref: '#/components/schemas/ImageResponse' '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' '429': description: Rate limited content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' '500': description: Upstream/gateway error content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' components: schemas: ImageEditRequest: type: object required: - model - prompt description: >- OpenAI-compatible image edit (`POST /v1/images/edits`). JSON and multipart/form-data supported. properties: model: type: string description: >- Edit-capable model id (e.g. `gpt-image-1`, `dall-e-2`, Gemini/Qwen edit models). example: gpt-image-1 prompt: type: string description: Instruction describing how to edit the image. example: Replace the sky with a sunset image: oneOf: - type: string - type: array items: type: string description: >- Source image(s). JSON: URL / Base64 / **string array**. multipart: file field `image` (one) or repeated `image[]` / `image[n]` (multiple). mask: oneOf: - type: string description: Mask URL or Base64. - type: string format: binary description: '`mask` file in multipart form.' description: >- Optional mask. JSON: URL/Base64; multipart: `mask` file (PNG, transparent = editable). 'n': type: integer description: Number of edited images to return. default: 1 size: type: string description: Output size when supported. quality: type: string description: Quality tier when supported. response_format: type: string enum: - url - b64_json user: description: Opaque end-user id. ImageResponse: type: object description: OpenAI-compatible image response. properties: created: type: integer description: Unix timestamp when the image job completed. data: type: array description: Generated image payloads. items: type: object properties: url: type: string description: >- Temporary HTTPS URL of the image (download promptly; may expire). b64_json: type: string description: Base64-encoded image bytes when `response_format=b64_json`. revised_prompt: type: string description: Prompt rewritten by the model (e.g. DALL·E), if any. OpenAIErrorResponse: type: object description: OpenAI-style error envelope returned on auth/request failures. required: - error properties: error: type: object required: - message - type properties: message: type: string description: >- Human-readable error. The gateway may append a request id for support. type: type: string description: Error type, commonly `new_api_error`. example: new_api_error code: type: string description: >- Optional machine-readable code (e.g. `access_denied`). May be an empty string. description: Error object. securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Use Authorization: Bearer sk-... from https://omniall.ai/dashboard' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.