Model API
PixVerse 5.5
PixVerse V5.5 Transition makes a 5, 8 or 10 second video that moves from a first image to an end image, guided by a prompt, at 360p to 1080p with optional generated audio and style presets.
Model id
pixverse/v5.5/transitionThis model has other modes with their own ids: pixverse/v5.5/text-to-video, pixverse/v5.5/image-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": "pixverse/v5.5/transition",
"input": {
"prompt": "A red ceramic cup on a wooden table, soft morning light",
"first_image_url": "https://example.com/input.png",
"end_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/v5.5/transition", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light","first_image_url":"https://example.com/input.png","end_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
| Name | Type | Description |
|---|---|---|
promptrequired | string | The prompt for the transition. 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. |
aspect_ratio | string (enum) | The aspect ratio of the generated video |
resolution | string (enum) | The resolution of the generated video |
duration | string (enum) | The duration of the generated video in seconds. Longer durations cost more. 1080p videos are limited to 5 or 8 seconds |
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 |
seed | integer | The same seed and the same prompt given to the same version of the model will output the same video every time. |
generate_audio_switch | boolean | Enable audio generation (BGM, SFX, dialogue) |
first_image_urlrequired | string (image URL) | URL of the image to use as the first frame |
end_image_urlrequired | string (image URL) | URL of the image to use as the last frame |
Output
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]Pricing
- 1080p · audio switch off$1.91/ video
- 1080p · audio switch on$2.06/ video
- 360p · audio switch off$0.72/ video
- 360p · audio switch on$0.88/ video
- 540p · audio switch off$0.72/ video
- 540p · audio switch on$0.88/ video
- 720p · audio switch off$0.96/ video
- 720p · audio switch on$1.11/ video
The exact charge for your input comes from a quote. How charges settle