Create a generation

Creates an asynchronous generation task. The model id determines whether an image or video is produced — use the same endpoint for both.

Authorization

bearerAuth

AuthorizationBearer <token>

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Generation request. Only model and prompt are required; every other field is optional and applies to the model type that supports it (e.g. duration/resolution for video, size/aspect_ratio for image).

model*string

PixMind model id, e.g. nano-banana-pro or veo-3.1.

prompt*string

Length1 <= length

aspect_ratio?string

size?string

Output resolution tier for image models.

duration?integer

Requested duration in seconds for video models.

Range1 <= value

resolution?string

Output resolution for video models.

image_url?string

Starting image for image-to-image or image-to-video workflows.

Formaturi

reference_images?array<>

n?integer

Number of samples to generate (image models).

Range1 <= value <= 4

callback_url?string

HTTPS endpoint that receives the terminal task event. Polling remains available when omitted.

Formaturi

Response Body

`application/json`

curl -X POST "https://example.com/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "nano-banana-pro",    "prompt": "string"  }'

{  "code": 0,  "message": "string",  "data": {    "id": "img_44160",    "taskId": "string",    "model": "nano-banana-pro",    "type": "image",    "status": "processing",    "progress": 0,    "error": "string",    "result": {      "images": [        "http://example.com"      ],      "videos": [        "http://example.com"      ]    }  }}

{  "code": 0,  "message": "string"}

{  "code": 0,  "message": "string"}

{  "code": 0,  "message": "string"}

Authorization

Request Body

Response Body

202application/json

400application/json

401application/json

429application/json

`application/json`

`application/json`

`application/json`

`application/json`