Image Generation API

Create an image task

POST /api/v1/images creates an image-generation task and consumes credits when accepted.

POST https://vidrush-ai.com/api/v1/images
Authorization: Bearer sk-your-api-key
Content-Type: application/json

Request body

Field	Required	Type	Description
`model`	Yes	string	A current model ID from `GET /api/v1/models?type=image`
`prompt`	Yes	string	Non-empty image instruction
`scene`	No	string	`text-to-image` or `image-to-image`; must be supported by the model
`image_urls`	No	string[]	Public HTTP(S) image URLs; required for `image-to-image`
`options`	No	object	Model-specific generation controls

If scene is omitted it defaults to text-to-image, except a non-empty image_urls array infers image-to-image.

`options`

Field	Type	Description
`aspect_ratio`	string	A supported ratio such as `1:1`, `16:9`, or `9:16`
`quality`	string	A supported quality such as `1K`, `2K`, or `4K`

Only send values advertised for the selected model and scene. GET /api/v1/models?type=image is the live machine-readable source.

Example

curl -X POST https://vidrush-ai.com/api/v1/images \
  -H "Authorization: Bearer $VIDRUSH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana-2",
    "scene": "text-to-image",
    "prompt": "A paper kite crossing a bright summer sky",
    "options": { "aspect_ratio": "16:9", "quality": "2K" }
  }'

Successful response

{
  "code": 0,
  "message": "ok",
  "data": {
    "id": "task_123",
    "status": "processing",
    "costCredits": 8
  }
}

Use data.id with GET /api/v1/tasks/{taskId}, polling every 5 seconds until a terminal status. On success, read the generated image URLs from data.taskUrls.