Model detail
wan2.6-r2v
Wan's reference-to-video model uses people or objects as references, preserving appearance and voice consistency across generated scenes.
Model specs
- Model ID
-
wan2.6-r2v
- Context length
- –
- Max output
- –
- I/O modalities
- Released
- 2025-12
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /second
| Tier | Per second /second |
|---|---|
| 720p res == "720p" | $0.1000 |
| 1080p !(res == "720p") | $0.1500 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Wan's reference-to-video model uses people or objects as references
Wan's reference-to-video model uses people or objects as references, preserving appearance and voice consistency across generated scenes.
What should you check before using it?
Check duration, resolution, and aspect ratio limits
Model type: video. Verify supported features and quotas with the provider documentation. Released 2025-12-16.
Why use it through MixRoute?
One MixRoute key reaches wan2.6-r2v
One MixRoute key covers wan2.6-r2v, on the same account as the rest of the catalog. MixRoute serves wan2.6-r2v on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID wan2.6-r2v and re-run your integration tests.
09
FAQ
wan2.6-r2v is a video generation model from Alibaba. It accepts video, text, audio and returns video, audio.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.