Video generation API
AI video generation, one API key
Generate cinematic video from text or images across 3 video models through one endpoint and one balance. Billed per second of output or per clip; failed jobs are refunded in full.
POST /v1/videos/generations · $0.50 free credit on the free tier, no card
3 models, one API key
Switch models with a string. Billed per use, refunded on failure.
Quick start
OpenAI-compatible. Point your client at https://kymaapi.com/v1 with a ky- key.
curl https://kymaapi.com/v1/videos/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "veo-3.1-fast",
"prompt": "A wave breaking on a rocky shore at golden hour, cinematic",
"duration_s": 5
}'
# Response: { "id": "vid_...", "status": "queued" }
# Poll: GET /v1/jobs/{id} until status = "succeeded"FAQ
Which video generation models does Kyma support?
Kyma serves Veo 3.1 Fast, Kling 3 Pro and Kling AI Avatar v2 Pro through one API, for text-to-video and image-to-video.
How is video generation billed?
Most models bill per second of generated video; some bill a flat rate per clip. You only pay for successful generations; failed jobs are refunded in full. See the pricing page for per-model rates.
How does the video API work?
Send a POST to /v1/videos/generations with a prompt and duration. Generation is asynchronous: you get back a job id and poll GET /v1/jobs/{id} until the status is succeeded, then download the result.
Can I generate video with sound?
Yes. Veo 3.1 Fast and Kling AI Avatar v2 Pro produce video with native audio, so you get a finished clip in one call.
$0.50 free credit on the free tier. No card required.
Get your free API key →