> ## Documentation Index > Fetch the complete documentation index at: https://docs.shuyou.ai/llms.txt > Use this file to discover all available pages before exploring further. # GPT Image 2 Generation > Create asynchronous image generation tasks with gpt-image-2 via POST /v1/predictions. ## OpenAPI ````yaml en/api-reference/image-series/openai/gpt-image-2-generate.json POST /v1/predictions openapi: 3.1.0 info: title: GPT Image 2 Generation version: 1.0.0 servers: - url: https://api.shuyou.ai security: - bearerAuth: [] paths: /v1/predictions: post: tags: - Image Generation summary: GPT Image 2 Generation description: >- GPT Image 2 (`gpt-image-2`) supports text-to-image, image-to-image, and image editing. Prefer official `input` fields (`size`, `n`, `quality`, …); ShuYou also accepts platform aliases (`aspect_ratio`, `num_images`, `output_format`) when official fields are omitted. Async mode: poll with Get a prediction using `data.task_id`, or use top-level `webhook`. operationId: createGptImage2Prediction requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GptImage2PredictionRequest' examples: text_to_image: summary: Text to image (minimal) value: model: gpt-image-2 input: prompt: A vivid, colorful sunset over the ocean text_to_image_hd: summary: Text to image (HD 16:9) value: model: gpt-image-2 input: prompt: Cinematic wide shot of a futuristic city skyline at dusk size: '16:9' resolution: 4K quality: high 'n': 1 text_to_image_pixel: summary: Text to image (explicit pixels) value: model: gpt-image-2 input: prompt: Minimalist logo design size: 1024x1024 quality: medium image_edit: summary: Image to image / edit value: model: gpt-image-2 input: prompt: Add a cute kitten beside her size: '1:1' resolution: 1K quality: medium image_urls: - https://example.com/input.png webhook: https://your-domain.com/webhook/image-done image_inpaint: summary: Inpaint (with mask) value: model: gpt-image-2 input: prompt: Replace the sky with a starry night size: '1:1' resolution: 1K quality: medium image_urls: - https://example.com/input.png mask_url: https://example.com/mask.png batch_generation: summary: Batch generation value: model: gpt-image-2 input: prompt: Cute robot in pixel art style size: '1:1' resolution: 2K quality: high 'n': 4 platform_params: summary: ShuYou platform fields value: model: gpt-image-2 input: prompt: A minimalist ShuYou AI logo aspect_ratio: '1:1' resolution: 1K num_images: 1 output_format: png image_urls: [] webhook: https://api.shuyou.ai/api/callback responses: '200': description: Async task created content: application/json: schema: $ref: '#/components/schemas/PredictionTaskResponse' example: data: task_id: 2c4d50261173430290971a2395a3b607 task_status: processing '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '402': description: Insufficient quota content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: Model access denied content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: GptImage2PredictionRequest: type: object required: - model - input properties: model: type: string description: Model ID. Use `gpt-image-2` for this endpoint. enum: - gpt-image-2 default: gpt-image-2 example: gpt-image-2 input: $ref: '#/components/schemas/GptImage2Input' webhook: type: string format: uri description: >- Optional HTTPS callback URL when the task completes, fails, or is cancelled (Predictions API). PredictionTaskResponse: type: object properties: data: type: object properties: task_id: type: string description: Async task ID. Use with Get a prediction or webhook correlation. example: 2c4d50261173430290971a2395a3b607 task_status: type: string description: Current task status, e.g. `processing`. example: processing required: - task_id - task_status required: - data ErrorResponse: type: object properties: error: type: object properties: code: type: string message: type: string type: type: string GptImage2Input: type: object required: - prompt properties: prompt: type: string description: >- Prompt describing the image to generate, or how to edit reference images. Max 32,000 Unicode code points. maxLength: 32000 example: A vivid, colorful sunset over the ocean image_urls: type: array description: >- Reference image URLs for image-to-image or editing. Supports 1–16 images per request; each file up to 50MB; formats `.jpeg`, `.jpg`, `.png`, `.webp`. URLs must be directly accessible by the server. Reference images incur additional input token usage. items: type: string format: uri minItems: 0 maxItems: 16 example: - https://example.com/image1.png mask_url: type: string format: uri description: >- Inpaint mask URL (edit mode only; requires `image_urls`). PNG with alpha: transparent pixels = repaint region. Mask dimensions must exactly match the reference image. Ignored for text-to-image-only requests. size: type: string description: >- **Official (preferred).** Output size: aspect ratio (`1:1`, `16:9`, …), explicit pixels `WxH`, or `auto`. If both `size` and `aspect_ratio` are set, `size` takes precedence. Default `auto`. default: auto example: auto resolution: type: string description: >- Resolution tier when `size` is an aspect ratio: `1K` (~1 MP), `2K` (~4 MP), `4K` (~8.29 MP). Ignored for explicit pixel `size` or `auto`. Case-insensitive. enum: - 1K - 2K - 4K default: 1K example: 1K quality: type: string description: >- Render quality (`low`, `medium`, `high`). Affects output tokens and cost. Default `medium`. enum: - low - medium - high default: medium example: medium 'n': type: integer description: >- **Official (preferred).** Number of images to generate (1–10). If both `n` and `num_images` are set, `n` takes precedence. minimum: 1 maximum: 10 default: 1 example: 1 aspect_ratio: type: string description: >- **ShuYou platform.** Aspect ratio shorthand (e.g. `1:1`, `16:9`, `9:16`). Used when `size` is omitted; maps to the same ratio values as official `size`. Ignored if `size` is set. example: '1:1' num_images: type: integer description: >- **ShuYou platform.** Number of images to generate. Used when `n` is omitted. Ignored if `n` is set. minimum: 1 maximum: 10 default: 1 example: 1 output_format: type: string description: >- **ShuYou platform.** Output encoding, e.g. `png`, `jpeg`, `webp`. Optional; model or platform default applies when omitted. example: png securitySchemes: bearerAuth: type: http scheme: bearer description: '`Authorization: Bearer YOUR_API_KEY`' ````