> ## 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. # Gemini 3 Pro Image Preview (Nano Banana Pro) > Create asynchronous image tasks with gemini-3-pro-image-preview (alias Nano Banana Pro) via POST /v1/predictions. ## OpenAPI ````yaml en/api-reference/image-series/gemini/gemini-3-pro-image-preview-generate.json POST /v1/predictions openapi: 3.1.0 info: title: Gemini 3 Pro Image Preview (Nano Banana Pro) version: 1.0.0 servers: - url: https://api.shuyou.ai security: - bearerAuth: [] paths: /v1/predictions: post: tags: - Image Generation summary: Gemini 3 Pro Image Preview (Nano Banana Pro) description: >- Nano Banana Pro (`gemini-3-pro-image-preview`) supports text-to-image, image-to-image, and image editing. Use `input.aspect_ratio`, `input.resolution`, and other fields as documented. Async mode: poll with Get a prediction using `data.task_id`, or use top-level `webhook`. Generated image URLs are valid for 24 hours. operationId: createGemini3ProImagePreviewPrediction requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Gemini3ProImagePredictionRequest' examples: text_to_image: summary: Text to image (minimal) value: model: gemini-3-pro-image-preview input: prompt: A cat playing on the grass text_to_image_sized: summary: Text to image (aspect_ratio & resolution) value: model: gemini-3-pro-image-preview input: prompt: Cinematic wide shot of a futuristic city at dusk aspect_ratio: '16:9' resolution: 4K image_edit: summary: Image to image / edit value: model: gemini-3-pro-image-preview input: prompt: Turn the scene into watercolor style aspect_ratio: '1:1' resolution: 2K image_urls: - https://example.com/reference.png webhook: https://your-domain.com/webhook/image-done with_model_params: summary: With model_params value: model: gemini-3-pro-image-preview input: prompt: A photorealistic product shot on a clean studio background resolution: 2K model_params: web_search: true image_search: false thinking_level: high with_output_format: summary: With output_format value: model: gemini-3-pro-image-preview input: prompt: A minimalist ShuYou AI logo aspect_ratio: '1:1' resolution: 2K 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: Gemini3ProImagePredictionRequest: type: object required: - model - input properties: model: type: string description: >- Model ID. Use `gemini-3-pro-image-preview` (alias Nano Banana Pro) for this endpoint. enum: - gemini-3-pro-image-preview default: gemini-3-pro-image-preview example: gemini-3-pro-image-preview input: $ref: '#/components/schemas/Gemini3ProImageInput' 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 Gemini3ProImageInput: type: object required: - prompt properties: prompt: type: string description: >- Prompt describing the image to generate or how to edit reference images. Max 2,000 tokens. maxLength: 2000 example: A cat playing on the grass aspect_ratio: type: string description: Aspect ratio of the generated image. Default `auto`. enum: - auto - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '21:9' default: auto example: auto resolution: type: string description: >- Output quality of the generated image. Default `2K`. Note: 4K quality incurs additional charges. enum: - 1K - 2K - 4K default: 2K example: 2K image_urls: type: array description: >- Reference image URLs for image-to-image or editing. Up to 14 images per request; each up to 20MB; formats `.jpeg`, `.jpg`, `.png`, `.webp`. URLs must be directly accessible. At most 4 real-person images per request. items: type: string format: uri minItems: 0 maxItems: 14 example: - https://example.com/image1.png model_params: $ref: '#/components/schemas/Gemini3ProModelParams' description: Optional model extension parameters. num_images: type: integer description: >- **ShuYou platform.** Number of images to generate when the model supports batch output. minimum: 1 maximum: 10 default: 1 example: 1 output_format: type: string description: '**ShuYou platform.** Output encoding, e.g. `png`, `jpeg`, `webp`.' example: png Gemini3ProModelParams: type: object description: Model extension parameters. properties: web_search: type: boolean description: Enable web search to inform image generation. example: true image_search: type: boolean description: Enable image search to inform image generation. example: false thinking_level: type: string description: >- Reasoning depth before generation. `auto` (default), `min` (fastest), or `high` (best quality). enum: - auto - min - high default: auto example: auto securitySchemes: bearerAuth: type: http scheme: bearer description: '`Authorization: Bearer YOUR_API_KEY`' ````