Generate video from a text prompt
A sentence becomes a video clip, with the model chosen by one string in the request. For apps that add a generate video button.
- Price
- from $0.85with Kling V3 Turbo Standard
- You send
- a text prompt
- You get
- video
How it works
Send a text prompt
One POST to /run with the model id and your input. It answers at once with an id.
We run Kling V3 Turbo Standard
from $0.85. Charged when it starts, refunded by itself if it fails.
Collect a video
GET /generations/{id}?wait=55 returns a video clip of the scene you described, as a file URL. Or pass a webhook and we call you.
3 models for this, by price
Prices are read from the live catalog. Each one opens the playground with this use case filled in.
The request
Filled in with sample files from our CDN, so it runs as it is. Swap in your own URLs.
curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "kling-v3-turbo-std-t2v",
"input": {
"prompt": "A woman presses her hand to a rain covered window, neon city lights behind her, slow push in"
}
}'Full reference in the docs. Every field Kling V3 Turbo Standard takes is on its model page.
Questions
What do I send to generate video from a text prompt?
Send a text prompt in one POST to https://api.percify.io/v3/playground/v1/run. You get a video clip of the scene you described.
What does it cost?
With Kling V3 Turbo Standard it is from $0.85 (from 34 credits). The picks on this page range from from $0.10 to from $4.00. The estimate call returns the exact price of your input before you run it, and a run that fails is refunded.
Which model should I use?
Budget: P-Video (Text-to-Video) (from $0.10). Balanced: Kling V3 Turbo Standard (from $0.85). Premium: Veo 3.1 (from $4.00). Switching is one string in the request: the model id.
Can an AI agent do this for me?
Yes. Connect your agent to the MCP server at https://mcp.percify.io/mcp and ask for it in plain words. The agent calls the generate tool with the same model id and input shown on this page, and the call spends the same credits.
