- 🎬 Text-to-video tier of Alibaba's Wan 3.0 generation, released September 2026
- 📏 Alibaba states Wan 3.0 generates up to 30 seconds in one pass
- 🔧 Family covers text-, image-, and reference-to-video modes
- 🆕 Image-to-video supports first-frame and last-frame control
- 🏢 Served through Alibaba Cloud Model Studio via API
- 💬 Pro tier sits between the base Wan 3.0 and Prime Pro tiers
- 🌐 Catalog notes photorealistic output with strong subject coherence across frames
- 🎯 Same-day release as the Prime Pro tier and Pro reference variant
Alibaba Group is a Chinese multinational technology company founded in 1999 and headquartered in Hangzhou, Zhejiang. Originally built around e-commerce and cloud computing, Alibaba has become one of the most prolific contributors to open-weight AI research, developing the Qwen…
Explore 51 more models by Alibaba Group →Wan 3.0 Pro is the text-to-video entry in the Pro tier of Alibaba's Wan 3.0 video family, served through Alibaba Cloud Model Studio. It sits alongside the matching Wan 3.0 Pro image-to-video and Wan 3.0 Pro Reference endpoints, plus the higher Wan 3.0 Prime Pro tier released the same day.
The Wan 3.0 generation is documented by Alibaba as an all-in-one video model supporting text-to-video, image-to-video with first- and last-frame control, and reference-based generation. Its headline change over earlier Wan releases is single-pass length: Alibaba states that Wan 3.0 supports generation of up to 30 seconds in a single pass.
Compared with the Wan 2.7 and Wan 2.6 text-to-video models that preceded it in this catalog, the documented generational changes are the longer single-generation duration and the consolidation of text, image and reference conditioning into one model family. Venice's own description characterises the Wan line as photorealistic with strong subject coherence across frames.
Access to Wan 3.0 is through the Model Studio video generation API rather than downloadable weights. The base Wan 3.0 tier remains available for lighter workloads, while Wan 3.0 Prime and Prime Pro cover the upper end of the family.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Wan 3.0 Pro · Organic sellers
| Seller | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | 81.71 | $1.60 | 15 s | #1 | $0.1065 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.