1Route video integration
Start with one video. AI-assisted setup, reference media, models and downloads.
See the unified video API for shared fields, errors and delivery. The complete catalog and OpenAPI cover all models.
Let AI help with the setup.
Copy the instructions to your AI. It will check your tools, then help configure or implement the integration.
Confirm the model and cost before testing. Execution requires an AI tool that can run code or call external tools.Choose your starting point
| Your situation | Next step |
|---|---|
| You want AI assistance | Connect with AI |
| You need step-by-step instructions | Your first video |
| You have an application or workflow | Unified video API |
| You use MJ / Seedream images on Video | Image endpoints, pricing and downloads |
| You use MiniMax video models | MiniMax models and prices · Integration |
| You use per-request Seedance models | Models, prices and integration |
| You use the newly added mixed video models | Mixed Video Models and billing |
| You already submitted a task | Tasks and downloads |
Create a key in the video console: 阿里官转 for WAN3 direct models, or 低价混合 for MiniMax and the mixed video models. Check enabled models with your key and do not submit paused variants. For WAN3 direct models only, start with 480p and 2 seconds after confirming cost; use wan3.0-video-480p for text-only input. Other models have separate duration limits; do not reuse the two-second example.
This is documentation, not an online generation canvas. An AI tool that can run code can help set up a client.
Save your result
Persist the task ID, wait for completion, then immediately save the MP4. Cached videos last about 10 minutes after becoming ready; individual signed URLs last up to 5 minutes. Your client should download automatically.
For MJ / Seedream images on Video, MJ uses a Midjourney group key. Seedream belongs to a separate group that is currently hidden and requires separate access. Billing is per generation or per image, and image links last 7 days. Other image models use the separate image documentation. Image and video retention rules differ.