Skip to main content
Welcome to Kinovi — a unified API for AI video and image generation. One endpoint, multiple models, simple async flow.

1. Create Your API Key

  1. Sign up at kinovi.ai
  2. Go to API Keys and create a key
  3. Add credits to your account
export KINOVI_API_KEY="your_api_key_here"
No API key yet? Try the Playground first — no code needed.

2. Make Your First Request

All models use the same endpoint: POST /jobs/createTask. Just change model and inputs:
curl -X POST "https://kinovi.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $KINOVI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-20",
    "inputs": {
      "prompt": "A serene Japanese garden with cherry blossoms swaying in the wind",
      "duration": "5",
      "aspectRatio": "16:9"
    }
  }'
Returns:
{ "taskId": "task_clxxxxxx" }
A 200 response means the task was created, not completed. You need to poll for the result.

3. Get Your Result

Poll every 3–5 seconds until status is success or fail:
curl -s "https://kinovi.ai/api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID" \
  -H "Authorization: Bearer $KINOVI_API_KEY"
Success response:
{
  "taskId": "task_clxxxxxx",
  "status": "success",
  "output": [{ "url": "https://..../result.mp4", "width": 1280, "height": 720 }],
  "creditsUsed": 200
}
That’s it — create taskpoll statusget output URL. Same flow for every model.

Next Steps

Available Models

See all supported video and image models

Authentication

API key, headers, rate limits, and security

Live Demo

Copy-paste scripts to test the API instantly

Playground

Generate in the browser — no code needed