Seedance 2.5 is live — 30-second cinematic video with native audio & real-person referencesfrom $0.071/s

Wan 3.0 — 30-Second Omni-Modal Video Generation

Wan 3.0 is Alibaba's next-generation video model, now in public beta. Wan 3.0 generates single-pass clips up to 30 seconds, takes text, images, audio, video and even documents as input, and holds characters, voices, and style stable with fine-grained reference control. Wan 3.0 is coming soon to reAPI.

Coming soon — the API for this model is not available yet.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Tell a 30-second story in one pass

Most video models stop near 10 seconds; Wan 3.0 is announced to generate up to 30 seconds in a single pass, enough for a full scene with a beginning, middle, and end. Instead of stitching clips and fighting continuity drift, you describe the whole arc once and Wan 3.0 renders it as one take. When the API opens, the same single-pass generation ships here on reAPI.

Preview the docs

Feed Wan 3.0 anything — even documents

Wan 3.0 accepts the four base modalities — text, images, audio, and video — and, for the first time in the Wan family, documents: doc, xls, ppt, pdf, and md files can drive a generation. A slide deck becomes a product explainer; a report becomes a narrated summary clip. Wan 3.0 turns the material you already have into video without a storyboard step.

Keep characters, voices, and style locked

Wan 3.0 extends reference generation to fine-grained control: characters, props, voices, spatial relations, and style are announced to stay stable across shots. And editing goes further than re-rendering — Wan 3.0 supports modifying the visuals, the plot, and the dialogue of a clip. Recurring characters and brand looks survive from one generation to the next.

Why reAPI

A generational leap in one pass

Wan 3.0 moves the Wan family from short clips to 30-second single-pass scenes with audio, character consistency, and real-world rendering upgrades announced across the board. If your pipeline stitches 5-second segments today, Wan 3.0 collapses that workflow into one request.

Omni-modal in, video out

Text, images, audio, video, and documents all drive the same model. Wan 3.0 routes by what you provide — no separate products for text-to-video, image-to-video, reference-to-video, or editing — so one integration covers every mode when Wan 3.0 lands on reAPI.

Pay-as-you-go at launch

When Wan 3.0 opens here, billing follows the platform standard: per completed generation, scaled by resolution and duration, with failed jobs refunded automatically. No subscription — credits are pay-as-you-go and never expire.

Wan 3.0 vs Wan 2.7

Wan 3.0 succeeds the shipping Wan 2.7 generation. The rows below compare what Alibaba announced at the Wan 3.0 public beta against what Wan 2.7 documents on reAPI today — announced behavior on one side, shipping behavior on the other.

Capability
Wan 3.0 (announced)
Wan 2.7 on reAPI
Status
Public beta since August 6, 2026; vendor API opens fully soon. Coming soon to reAPI.
Live on reAPI today — playground, docs, and per-second pricing.
Max duration
Up to 30 seconds in a single pass.
2 to 15 seconds for base modes; reference and editing modes cap shorter.
Resolutions
480P, 720P, and 1080P.
720P and 1080P.
Input modalities
Text, image, audio, video, plus documents: doc, xls, ppt, pdf, md.
Text, image, audio, and video.
Reference control
Fine-grained: characters, props, voices, spatial relations, and style announced to hold stable.
Reference images, videos, and per-subject voices keep subjects consistent.
Editing
Announced to modify visuals, plot, and dialogue.
Re-renders a source video against a prompt; audio_setting controls the soundtrack.

Wan 3.0 rows reflect Alibaba's public-beta announcement of August 6, 2026 and are provisional until the API is generally available. Wan 2.7 rows reflect its documented behavior on reAPI at the time of writing.

Get ready for Wan 3.0 in three steps

  1. step 01

    Create an API key

    Sign up and create a key in the dashboard now — no card required. The same key works for every reAPI model, including Wan 3.0 at launch.

    Open
  2. step 02

    Preview the request shape

    The docs preview shows the provisional Wan 3.0 request: a prompt or media input, a resolution tier, and a duration up to 30 seconds. Fields are finalized when the vendor API opens.

    Open
  3. step 03

    Go live at launch

    When Wan 3.0 ships, the model id, parameters, and per-second rates are finalized on this page and the playground goes live. Integrations built against the preview shape need at most a field-level touch-up.

    Open

Frequently asked questions

Common questions about this model.

Wan 3.0 is Alibaba's next-generation video model (Tongyi Wanxiang 3.0). It opened public beta on August 6, 2026, and is announced to generate up to 30 seconds of video in a single pass from text, images, audio, video, and documents, with fine-grained reference control over characters, props, voices, spatial relations, and style.

Related models

Explore more models in the same category.

View all models
start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.

Get API keyPreview the docs