# Wan 3.0

> Wan 3.0 is Alibaba Cloud’s third-generation all-in-one multimodal video model, generating whole-second clips from 2 to 30 seconds across 480P, 720P, and 1080P with optional audio output and reproducible seed control.

Canonical: https://routemux.com/alibaba/wan-3.0
Provider: Alibaba

## Key facts

| Field | Value |
| --- | --- |
| Model ID | alibaba/wan-3.0 |
| Official model ID | wan3.0-video |
| Input modalities | text, image |
| Output modalities | video |
| Capabilities | Video, Text To Video, Image To Video, Reference Audio, Reference Image, Reference Video, First Last Frame |
| Upstream release | 2026-08-24 |
| Availability | available |

## Pricing

- RouteMux: $0.0411 per second (from — tiered by duration/resolution)
- Official: $0.0411 per second
  - 480P: $0.0411 per second (official $0.0411)
  - 720P: $0.0822 per second (official $0.0822)
  - 1080P: $0.1644 per second (official $0.1644)

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_sora

## What is Wan 3.0

Wan 3.0 is Alibaba Cloud’s third-generation all-in-one multimodal video model, generating whole-second clips from 2 to 30 seconds across 480P, 720P, and 1080P with optional audio output and reproducible seed control.

Three input workflows are available on RouteMux: text-to-video from a prompt alone; image-to-video from a first frame with an optional last frame; or multimodal references — up to 10 reference images, 5 reference videos (1–15 seconds each, up to 15 seconds total, with reference_video_seconds + output_seconds <= 30), and 5 reference audio clips (1–15 seconds each, up to 15 seconds total), capped at 20 files per request. First/last frames and references cannot be combined.

Aspect ratio accepts 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, or adaptive (16:9 by default for text-to-video, adaptive with visual media). Toggle sound via audio (or generate_audio) at identical pricing, and pass seed (-1 or 0..2147483647) for repeatable results.

Billing is strictly output-only: whether you send text alone, start/end frames, or multiple reference images, videos, and audio clips, you pay solely seconds × resolution_rate with zero surcharge for reference media. Runs asynchronously on POST /v1/videos; failed jobs cost nothing.

## Key capabilities

- **2–30 whole seconds** — Span ultra-short 2-second inserts up to full 30-second sequences.
- **Zero reference surcharge** — Reference images, videos, and audio add no extra input fee.
- **480P, 720P & 1080P** — Three clear resolution tiers (default 720P), same price with or without audio.
- **Frames or 3-modality refs** — Start/end frame transitions, or up to 10 images + 5 videos + 5 audio clips.

## Sources

- [Alibaba Cloud Model Studio Documentation](https://help.aliyun.com/zh/model-studio/getting-started/models)
- [Wan Official Site](https://wan.video)

_Content reviewed by the RouteMux team on 2026-11-19._
