> ## Documentation Index > Fetch the complete documentation index at: https://docs.mountsea.ai/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2 - Edit ## OpenAPI ````yaml mountsea-api.mint.json POST /ms/v1/run/openai/gpt-image-2/edit openapi: 3.0.0 info: title: mountsea-api description: >- mountsea unified AI API — video, image, and audio generation. ### Async task flow 1. `POST /ms/v1/run/{endpoint_slug}` — submit a job (returns Task with `status: queued`). 2. `GET /ms/v1/tasks/{task_id}` — poll until `succeeded` (`output.images` / `output.videos` / `output.audio`) or `failed`/`timeout` (`error`). Or pass `webhook_url` in the submit body for a signed terminal callback (`x-ms-signature`). 3. `GET /ms/v1/endpoints[/{slug}]` — marketplace listing with `input_schema`, `output_schema`, and `examples`. ### Request body - `{ "input": { ... } }` — all parameters and media URLs per endpoint `input_schema`. - Optional `webhook_url` for callbacks. ### SDK compatibility (optional) Prefer the native async API above? Skip this section. - **OpenAI SDK** — `baseURL = https://{gateway}/ms/v1` - Image (sync): `POST /ms/v1/images/generations|edits` — gpt-image-2 family - Video (async): `POST /ms/v1/videos` + `GET /ms/v1/videos/{id}` — sora-2 → Veo lite/pro slugs - **Gemini SDK** — `httpOptions.baseUrl = https://{gateway}/ms` - Image (sync): `POST /ms/v1beta/models/{model}:generateContent` — nano-banana family - Video (async): `POST /ms/v1beta/models/{model}:predictLongRunning` + poll `GET /ms/v1beta/operations/{task_id}` Unsupported `model` → **HTTP 400** before any task is created (no charge). Successful calls bill the **same endpoint slug** as the equivalent `/ms/v1/run/...` API. version: 1.0.0 contact: {} servers: - url: https://api.mountsea.ai description: API Gateway security: [] tags: - name: Run description: Submit async tasks by endpoint slug - name: Tasks description: Poll or cancel tasks - name: Endpoints (marketplace) description: Endpoint catalog and schemas - name: SDK Compatibility description: >- OpenAI / Gemini official SDK — sync image APIs (same billing as native run) - name: Admin - Catalog (internal) description: Internal admin (swagger only, not public gateway) paths: /ms/v1/run/openai/gpt-image-2/edit: post: tags: - Models / image summary: GPT Image 2 - Edit description: >- OpenAI GPT Image 2 instruction editing. **Endpoint**: `openai/gpt-image-2/edit` · **mode**: `image-to-image` Returns a Task with `status: queued` and `output: null`. Poll `GET /ms/v1/tasks/{task_id}` until `succeeded`, then read `output` (see response schema). Request examples are taken from the endpoint `examples` field. operationId: run_openai_gpt_image_2_edit requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/RunEndpointInput_openai_gpt_image_2_edit' example: input: prompt: Add a rainbow. image_size: auto image_urls: - https://example.com/a.jpg responses: '200': $ref: '#/components/responses/MsTaskImageResponse' '201': $ref: '#/components/responses/MsTaskImageResponse' '400': $ref: '#/components/responses/BadRequestResponse' '404': $ref: '#/components/responses/NotFoundResponse' security: - bearerAuth: [] components: schemas: RunEndpointInput_openai_gpt_image_2_edit: type: object properties: input: type: object description: >- Parameters for this endpoint (input_schema.params). Input media URLs use schema field names, e.g. image_url, image_urls, mask_url. properties: prompt: description: Text prompt describing the image. Maximum 32000 characters. type: string maxLength: 32000 quality: type: string enum: - auto - low - medium - high default: high mask_url: description: >- Optional mask image URL (PNG with transparency). Edited region is transparent or white. type: string format: uri sync_mode: type: boolean image_size: description: >- Preset name or custom {width,height}. Custom: both dims multiple of 16, max edge 3840px, aspect ratio 1:3 to 3:1, total pixels 655360-8294400. type: string default: auto image_urls: description: Input image URLs for editing (1-16 images). type: array items: type: string format: uri minItems: 1 maxItems: 16 num_images: description: Number of images to generate (1-4). type: integer minimum: 1 maximum: 4 default: 1 output_format: type: string enum: - jpeg - png - webp default: png required: - prompt - image_urls webhook_url: type: string format: uri description: >- Optional webhook URL for terminal status (HMAC header x-ms-signature) MsTaskImage: type: object description: Async image task properties: task_id: type: string example: ms-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx endpoint: type: string example: google/veo-3.1/text-to-video model: type: string example: veo-3.1 capability: type: string enum: - image - video - audio mode: type: string example: text-to-video status: type: string enum: - queued - processing - succeeded - failed - timeout - canceled error: type: object nullable: true properties: code: type: integer example: 500 message: type: string example: task failed created_at: type: string format: date-time started_at: type: string format: date-time nullable: true completed_at: type: string format: date-time nullable: true elapsed_ms: type: integer nullable: true output: nullable: true description: >- Normalized task output. Null while queued/processing; populated when status=succeeded. allOf: - $ref: '#/components/schemas/MsTaskOutputImage' required: - task_id - endpoint - model - capability - mode - status - created_at ErrorBody: type: object properties: statusCode: type: integer example: 400 message: type: string error: type: string MsTaskOutputImage: type: object description: >- Succeeded task output: normalized images. Count matches actual produced items. properties: images: type: array description: Generated images (1..N) items: type: object properties: url: type: string format: uri description: Stable mountsea CDN URL (preferred) b64: type: string description: Base64 payload when URL unavailable mime: type: string description: MIME type, e.g. image/png required: - images responses: MsTaskImageResponse: description: Image task (usually queued right after submit) content: application/json: schema: $ref: '#/components/schemas/MsTaskImage' BadRequestResponse: description: Validation failed or unsupported model content: application/json: schema: $ref: '#/components/schemas/ErrorBody' NotFoundResponse: description: Resource not found content: application/json: schema: $ref: '#/components/schemas/ErrorBody' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ````