Início
Recursos
Meus trabalhos
Models
Biblioteca de vozes
Desenvolvedores
Blog
Português
Preços
Entrar
Models/Video/Wan 3.0 Prime

Alibaba: Wan 3.0 Prime

  • Text to video
  • Image to video
  • Native audio
API referenceUse in Gerador de vídeo IA

One of two Wan 3.0 tiers. Capabilities, resolutions and duration ceiling match the standard tier exactly; this one is markedly faster end to end.

Two to 30 seconds, the longest single clip on the platform — Seedance and MiniMax H3 both stop at 15.

Strengths

  • 2 to 30 seconds, the longest clip in the video line
  • 480p / 720p / 1080p
  • Native audio output

Limitations

  • Accepts neither reference video nor reference audio
  • No 21:9, 4:5 or 5:4
  • Rate limited to 5 RPM

Capabilities

Capability
Value
Text to videoYes
Image to videoYes
First/last frame–No
Reference video–No
Native audioYes
Lip sync–No
Motion transfer–No

Specs and limits

ParameterValue
Aspect ratio16:9 · 4:3 · 1:1 · 3:4 · 9:16

How it is billed

按秒计费，分辨率越高越贵，生成前实时估价

Standard pricesCredits
720p · 5 秒85
1080p · 5 秒169

Figures come from the same estimator the generation form calls before you spend anything.

Alternatives

  • Wan 3.0When there is no hurry — same capabilities, slower end to end.
  • Seedance 2.0 ProWhen a reference video has to drive the camera work; Wan 3.0 takes no video input.

Call it

# Set LISTENHUB_API_KEY firstcurl -X POST "https://api.marswave.ai/openapi/v1/video-generation/generate" \-H "Authorization: Bearer $LISTENHUB_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "wan3.0-video-prime","content": [{"type": "text","text": "A cinematic aerial shot of a quiet coastal city at sunrise"}]}'
  • API reference
  • SDK & CLI
  • Agent Skills

Similar models

  • Seedance 2.0 Pro
  • Seedance 2.0 Fast
  • PPixVerse
  • Wan 3.0
  • MiniMax H3