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

# MAI Image 2.6 Edit

> [Core Function] MAI Image 2.6 Edit is Microsoft's latest prompt-guided image editing model in the MAI Image family. [Strengths] It applies targeted edits to a single source image with the same quality gains as MAI Image 2.6 generation. [Best For] Highly recommended for: object edits, layout changes, text cleanup, and iterative photorealistic retouching. [Limitations] Do NOT use this if the caller provides more than one source image, a data URI, or a URL that is not publicly reachable over HTTP or HTTPS. It accepts exactly one JPEG or PNG image URL, and output is always PNG. auto_aspect_ratio and web_grounding are optional booleans; omit them unless the caller sets them. [Routing] Use this model when the latest MAI edit quality is required. For faster or lower-cost edits, route to MAI Image 2.6 Flash Edit.



## OpenAPI

````yaml /media-model-api/microsoft/microsoft-i2i.json post /microsoft/mai-image-2.6-edit
openapi: 3.1.0
info:
  description: >-
    The image-to-image (image editing) models API from Microsoft Foundry (MAI
    Image). Edits a single source image according to a text prompt and returns
    the result (PNG) synchronously via the async task interface.
  version: 1.0.0
  contact:
    name: Modellix Support
    email: support@modellix.ai
  title: Microsoft MAI Image Image-to-Image Models API
servers:
  - url: https://api.modellix.ai/api/v1
    description: The image-to-image models API from Microsoft Foundry (MAI Image).
security:
  - bearerAuth: []
paths:
  /microsoft/mai-image-2.6-edit:
    post:
      summary: MAI Image 2.6 Edit
      description: >-
        [Core Function] MAI Image 2.6 Edit is Microsoft's latest prompt-guided
        image editing model in the MAI Image family. [Strengths] It applies
        targeted edits to a single source image with the same quality gains as
        MAI Image 2.6 generation. [Best For] Highly recommended for: object
        edits, layout changes, text cleanup, and iterative photorealistic
        retouching. [Limitations] Do NOT use this if the caller provides more
        than one source image, a data URI, or a URL that is not publicly
        reachable over HTTP or HTTPS. It accepts exactly one JPEG or PNG image
        URL, and output is always PNG. auto_aspect_ratio and web_grounding are
        optional booleans; omit them unless the caller sets them. [Routing] Use
        this model when the latest MAI edit quality is required. For faster or
        lower-cost edits, route to MAI Image 2.6 Flash Edit.
      operationId: maiImage26EditAsync
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MAIImage26EditRequest'
            examples:
              basic:
                summary: Single source image
                value:
                  prompt: >-
                    Convert this photo into a cinematic film still with dramatic
                    lighting
                  images:
                    - https://example.com/photo.png
              with_optional_flags:
                summary: Optional auto aspect ratio and web grounding
                value:
                  prompt: >-
                    Convert this photo into a cinematic film still with dramatic
                    lighting
                  images:
                    - https://example.com/photo.png
                  auto_aspect_ratio: true
                  web_grounding: true
      responses:
        '200':
          description: Task submitted successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncTaskResponse'
              example:
                code: 0
                message: success
                data:
                  status: pending
                  task_id: task-mai-i2i-26-001
                  model_id: microsoft/mai-image-2.6-edit
                  get_result:
                    method: GET
                    url: https://api.modellix.ai/api/v1/tasks/task-mai-i2i-26-001
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
components:
  schemas:
    MAIImage26EditRequest:
      type: object
      required:
        - prompt
        - images
      description: >-
        Microsoft MAI Image 2.6 edit request. Shared by MAI Image 2.6 Edit and
        2.6 Flash Edit. Accepts exactly one source image (JPEG or PNG); output
        is always PNG. auto_aspect_ratio and web_grounding are optional; omit
        them to leave upstream defaults (do not send the fields).
      properties:
        prompt:
          type: string
          minLength: 1
          maxLength: 32000
          description: >-
            Text description of the edit to apply. Platform limit is 32,000
            UTF-8 bytes, not Unicode characters.
          example: Turn this photo into a watercolor painting
        images:
          type: array
          minItems: 1
          maxItems: 1
          description: >-
            Exactly one source image. The item must be a publicly accessible
            HTTP or HTTPS image URL (JPEG or PNG only).
          items:
            type: string
            minLength: 1
          example:
            - https://example.com/photo.png
        auto_aspect_ratio:
          type: boolean
          description: >-
            Optional. When true, the model chooses the output aspect ratio from
            the prompt and source image. Omit this field unless the caller
            explicitly wants model-directed framing.
        web_grounding:
          type: boolean
          description: >-
            Optional. When true, the model may retrieve current public
            information (Bing) as extra context. Omit this field unless the
            caller explicitly wants web-grounded editing.
    AsyncTaskResponse:
      type: object
      required:
        - code
        - message
        - data
      properties:
        code:
          type: integer
          description: Response code, 0 indicates success
          example: 0
        message:
          type: string
          description: Response message
          example: success
        data:
          type: object
          required:
            - status
            - task_id
            - model_id
          properties:
            status:
              type: string
              enum:
                - pending
                - processing
              description: Task status
              example: pending
            task_id:
              type: string
              description: Unique task identifier for polling
              example: task-abc123
            model_id:
              type: string
              description: Model ID in `provider/model` format
              example: microsoft/mai-image-2.5-edit
            get_result:
              type: object
              description: API information to query the task result
              properties:
                method:
                  type: string
                  example: GET
                url:
                  type: string
                  example: https://api.modellix.ai/api/v1/tasks/task-abc123
          description: Detailed data about the submitted asynchronous task.
    ErrorResponse:
      type: object
      required:
        - code
        - message
      properties:
        code:
          type: integer
          example: 400
        message:
          type: string
          example: 'Invalid parameters: parameter ''images'' is required'
  responses:
    BadRequest:
      description: Invalid request parameters
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 400
            message: 'Invalid parameters: parameter ''images'' is required'
    Unauthorized:
      description: Unauthorized - Invalid or missing API Key
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 401
            message: 'Authentication failed: invalid API key'
    TooManyRequests:
      description: Too many requests - Rate limit exceeded
      headers:
        X-RateLimit-Limit:
          description: Maximum requests per minute
          schema:
            type: integer
            example: 100
        X-RateLimit-Remaining:
          description: Remaining quota in current window
          schema:
            type: integer
            example: 0
        X-RateLimit-Reset:
          description: Rate limit window reset time (Unix timestamp)
          schema:
            type: integer
            example: 1704067260
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 429
            message: >-
              Rate limit exceeded: 100 requests per minute, retry after 60
              seconds
    InternalServerError:
      description: Internal server error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
          example:
            code: 500
            message: Internal server error
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'API Key authentication. Format: `Bearer YOUR_API_KEY`.'

````