> ## Documentation Index > Fetch the complete documentation index at: https://api-docs.upmore.net/llms.txt > Use this file to discover all available pages before exploring further. # gpt-image-2.5 · Image-to-image > Edits an existing image with a text prompt, optionally guided by additional reference images and a mask. Send as multipart/form-data. ## OpenAPI ````yaml api-reference/model-api/openai/gpt-image-2-5/openapi.yaml POST /v1/images/edits openapi: 3.1.0 info: title: GPT Image 2.5 description: >- OpenAI GPT Image 2.5 image generation and editing via the Upmore OpenAI-compatible API version: 1.0.0 servers: - url: https://api.upmore.net security: - bearerAuth: [] paths: /v1/images/edits: post: summary: Edit image description: >- Edits an existing image with a text prompt, optionally guided by additional reference images and a mask. Send as multipart/form-data. operationId: editImageGPTImage25 requestBody: required: true content: application/json: schema: type: object required: - model - prompt - images properties: model: type: string enum: - gpt-image-2.5-flare - gpt-image-2.5-sunburst example: gpt-image-2.5-flare description: The image model to use. Both model IDs are interchangeable. prompt: type: string example: Turn the fox's fur bright blue and add falling snowflakes description: Text description of the desired edit. images: type: array minItems: 1 maxItems: 16 description: >- Source images to edit. Use this JSON form to pass images by URL instead of uploading files. items: type: object description: Exactly one of image_url or file_id must be provided. properties: image_url: type: string example: https://your-bucket.tos-cn-beijing.volces.com/fox.png description: >- Public HTTPS URL (TOS, R2, CDN) or an inline data:image/png;base64,... payload. The upstream fetches it, so it must be publicly reachable. The tos:// scheme is not accepted. file_id: type: string description: >- Not usable on Upmore — the Files upload API is not exposed. mask: type: object description: >- Editable region. Must be a PNG with an alpha channel the same size as the source image. properties: image_url: type: string description: Public HTTPS URL or inline data URL of the mask. 'n': type: integer minimum: 1 maximum: 10 default: 1 description: Number of images to generate. size: type: string example: 1024x1024 description: >- {width}x{height}. Edges must be multiples of 16, aspect ratio <= 3:1, total pixels 655,360-8,294,400, max edge 3,840px. Omit to let the model choose (~1.3M pixels). quality: type: string enum: - low - medium - high - auto default: low description: Rendering quality. background: type: string enum: - opaque - transparent - auto default: opaque description: Background treatment. output_format: type: string enum: - png - jpeg default: png description: Output image format. output_compression: type: integer minimum: 0 maximum: 100 description: Compression level for jpeg output. moderation: type: string enum: - auto - low default: auto description: Content moderation strictness. stream: type: boolean default: false description: Stream partial images as server-sent events. partial_images: type: integer description: Number of preview frames to request when stream is true. multipart/form-data: schema: type: object required: - model - prompt - image properties: model: type: string enum: - gpt-image-2.5-flare - gpt-image-2.5-sunburst example: gpt-image-2.5-flare description: The image model to use. Both model IDs are interchangeable. prompt: type: string example: Turn the fox's fur bright blue and add falling snowflakes description: Text description of the desired edit. image: type: string format: binary description: Source image to edit. image[]: type: array items: type: string format: binary description: >- Additional source images. Repeat this field to pass multiple reference images instead of image. mask: type: string format: binary description: >- PNG mask the same size as the source image. Transparent pixels mark the region the model may repaint. 'n': type: integer minimum: 1 maximum: 10 default: 1 description: Number of images to generate. size: type: string example: 1024x1024 description: >- {width}x{height}. Edges must be multiples of 16, aspect ratio <= 3:1, total pixels 655,360-8,294,400, max edge 3,840px. Omit to let the model choose (~1.3M pixels). quality: type: string enum: - low - medium - high - auto default: low description: Rendering quality. background: type: string enum: - opaque - transparent - auto default: opaque description: Background treatment. output_format: type: string enum: - png - jpeg default: png description: Output image format. output_compression: type: integer minimum: 0 maximum: 100 description: Compression level for jpeg output. moderation: type: string enum: - auto - low default: auto description: Content moderation strictness. stream: type: boolean default: false description: Stream partial images as server-sent events. partial_images: type: integer description: Number of preview frames to request when stream is true. responses: '200': description: Image edited successfully content: application/json: schema: $ref: '#/components/schemas/ImageResponse' '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ImageResponse: type: object properties: created: type: integer description: Unix timestamp of the generation. background: type: string description: Background treatment used. output_format: type: string description: Format of the returned images. quality: type: string description: Quality actually used. size: type: string description: Resolution actually used. data: type: array items: type: object properties: b64_json: type: string description: Base64-encoded image data. usage: type: object properties: input_tokens: type: integer input_tokens_details: type: object properties: image_tokens: type: integer text_tokens: type: integer output_tokens: type: integer total_tokens: type: integer Error: type: object properties: error: type: object properties: code: type: string message: type: string securitySchemes: bearerAuth: type: http scheme: bearer ````