Model API

PixVerse 4.5

Generate high quality video clips from text and image prompts using PixVerse v4.5

Model id

Use this in every request

pixverse/v4.5/image-to-video

This model has other modes with their own ids: pixverse/v4.5/text-to-video, pixverse/v4.5/transition.

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": "pixverse/v4.5/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": "pixverse/v4.5/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 pixverse/v4.5/image-to-video
Name	Type	Description
`prompt`required	string	Text prompt for the video generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
`resolution`	string (enum)	The resolution of the generated video Default: `720p` One of: `360p`, `540p`, `720p`, `1080p`
`duration`	string (enum)	The duration of the generated video in seconds. 8s videos cost double. 1080p videos are limited to 5 seconds Default: `5` One of: `5`
`negative_prompt`	string	Negative prompt to be used for the generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
`style`	string (enum)	The style of the generated video One of: `anime`, `3d_animation`, `clay`, `comic`, `cyberpunk`
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same video every time.
`image_url`required	string (image URL)	URL of the image to use as the first frame
`camera_movement`	string (enum)	The type of camera movement to apply to the video One of: `horizontal_left`, `horizontal_right`, `vertical_up`, `vertical_down`, `zoom_in`, `zoom_out`, `crane_up`, `quickly_zoom_in`, `quickly_zoom_out`, `smooth_zoom_in`, `camera_rotation`, `robo_arm`, `super_dolly_out`, `whip_pan`, `hitchcock`, `left_follow`, `right_follow`, `pan_left`, `pan_right`, `fix_bg`

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

360p$0.24/ request
540p$0.24/ request
720p$0.32/ request
1080p$0.64/ request

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