Vidrush Developer Docs

Build video, image, music, and audio generation workflows with the Vidrush REST API, MCP server, command-line client, or downloadable Agent Skill. Generation consumes credits. Fetch the model catalog before selecting a model or quoting a cost.

30-second quickstart

1. Create an API key in Settings -> API Keys. API keys begin with sk-.
2. Create a task with a current model and supported options:

curl -X POST https://vidrush-ai.com/api/v1/videos \
  -H "Authorization: Bearer $VIDRUSH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "mode": "text-to-video",
    "prompt": "A paper kite crossing a bright summer sky",
    "options": {
      "duration": "8s",
      "resolution": "720p",
      "aspect_ratio": "16:9"
    }
  }'

3. Poll the returned data.id every 5 seconds until the task reaches success, failed, or canceled:

curl -H "Authorization: Bearer $VIDRUSH_API_KEY" \
  https://vidrush-ai.com/api/v1/tasks/TASK_ID

The success result exposes generated video URLs in data.taskUrls.

Choose an integration

• REST API: Best for services and custom product integrations. Start with API overview.
• MCP: Best for Claude, Cursor, and other MCP clients. See MCP.
• CLI: Best for scripts and local automation. See CLI.
• Agent Skill: Best for agents that need a documented generation workflow. See Skills.