Video-to-Video API
Transform existing footage through one API — restyle, edit, extend, or upscale video with a single request shape and transparent per-second pricing.
5 video-to-video models available right now — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant via MCP.
Video-to-Video models & pricing
| Model | Endpoint | Price |
|---|---|---|
| Wan VACE Video Edit | wan-video/wan-vace/video-edit | $0.1 per second of video |
| Bria Video Background Removal | bria/video/background-removal | $0.0042 per second of video |
| RIFE Video Interpolation | megvii-research/rife/video | ≈$0.0032365 per video |
| MMAudio V2 | mmaudio/v2 | $0.001 per second of video |
| Sync Lipsync 2 | sync/lipsync/v2 | $0.05 per second of video |
Full catalog on the models page; live per-configuration costs on the pricing page.
Call a video-to-video model in one request
Every model shares the same request lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/wan-video/wan-vace/video-edit \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": { "prompt": "..." } }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use video-to-video models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every video-to-video model in this table as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
What can a video-to-video API do?
Video-to-video models take an input video URL and return a transformed one: restyling, editing by prompt, upscaling, or extending footage. Each model’s page documents its exact inputs with runnable code examples.
How do I call a video-to-video model via the API?
Every model shares the same request shape: POST https://queue.modelrunner.run/<owner>/<alias> with an Authorization: Key header and an {"input": {...}} body, then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps this in a single subscribe() call. Each model page shows copy-paste cURL, JavaScript, and Python examples with that model's real inputs.
Can I run video-to-video models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and every video-to-video model in the catalog becomes a tool your AI assistant can call with the run_model tool — authorized via OAuth, no API key pasted into config.