Skip to content

Model detail

wan3.0-video-prime

Provided by Alibaba
Pay-as-you-go Dynamic pricing 3 tiers

wan3.0-video-prime is an Alibaba Wan video-generation model in the prime tier, with the inputs indicated by its native model identifier. It accepts text, images, files, audio, and video and returns video.

Model specs

Model ID
wan3.0-video-prime
Context length
–
Max output
–
I/O modalities
Released
2026-08

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Tiered pricing

Unit: /second

Pricing updated

Tier Per second /second
480p res == "480p" $0.0680
720p (!(res == "480p")) && (res == "720p") $0.1400
1080p (!(res == "480p")) && (!(res == "720p")) $0.2800

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Video generation

wan3.0-video-prime is Alibaba's video generation model for text-to-video work. It accepts input such as text, image and video, and returns video. Its capabilities are broken down in the section just below. Render one short clip at your target resolution before planning a batch.

What should you check before using it?

Clips up to 30 seconds

wan3.0-video-prime generates clips up to 30 seconds long at 480p / 720p / 1080p. Confirm that your target duration and resolution appear in those limits before you plan a render.

Why use it through MixRoute?

One MixRoute key reaches wan3.0-video-prime

One MixRoute key covers wan3.0-video-prime, on the same account as the rest of the catalog. MixRoute supports calling wan3.0-video-prime through its OpenAI-compatible endpoint; point your client at https://api.mixroute.ai/v1 with the model ID wan3.0-video-prime and re-run your integration tests.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Vision input

wan3.0-video-prime can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

09

FAQ

wan3.0-video-prime is a video generation model from Alibaba. It accepts text, image, video, audio, file and returns video.

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.