Model API

Kandinsky 6 Pro

Animate an image into a 5-second 480p video with sound, with controls for prompt guidance and unwanted content.

Model id

Use this in every request

kandinsky6-pro/image-to-video

This model has other modes with their own ids: kandinsky6-pro/text-to-video.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kandinsky6-pro/image-to-video",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light",
    "image_url": "https://example.com/input.png"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "kandinsky6-pro/image-to-video", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light","image_url":"https://example.com/input.png"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for kandinsky6-pro/image-to-video
Name	Type	Description
`prompt`required	string	The text prompt describing the video and its sound.
`image_url`required	string (image URL)	The image used as the first frame of the video.
`negative_prompt`	string	What to avoid in the video. Defaults to the model's built-in negative prompt.
`aspect_ratio`	string (enum)	The aspect ratio of the generated video. `auto` picks the supported ratio closest to the image's; the image is center-cropped to it. Default: `auto` One of: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `auto`
`generate_audio`	boolean	Whether to generate a synchronized audio track. Default: `true`
`enable_prompt_expansion`	boolean	Whether to rewrite the prompt into a detailed video+audio description with the model's own Qwen2.5-VL text encoder before generating. Default: `false`
`seed`	integer	The random seed used for the generation process.
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history. Default: `false`
`num_inference_steps`	number (enum)	The number of denoising steps. Default: `50` One of: `50`
`guidance_scale`	number	Classifier-free guidance strength. Default: `5`

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

1 request$2.22/ request

The exact charge for your input comes from a quote. How charges settle