Wan 3

About

Wan 3 is Alibaba Cloud Model Studio's unified premium video model on Sogni. Alibaba currently labels the upstream API as preview (as of August 2026). One model ID covers text-to-video, first-frame and first-and-last-frame animation, loose multimodal references, and audio-driven generation. A reference video conditions a new result; the provider API has no edit/extend task mode or task-type field.

It renders 2–30 second clips at fixed 30 fps in 480p, 720p, or 1080p. Choose a fixed 16:9, 4:3, 1:1, 3:4, or 9:16 canvas, use adaptive shape, or let smart duration select the timing. Most text- and image-led generations can use the full 30-second output. Video references are different: Alibaba bills both input and output duration, and their combined duration cannot exceed 30 seconds. Native audio is on by default and can be disabled without changing the rate.

Wan 3 accepts up to 10 images, 5 reference videos, and 5 reference audio clips. It can also use one public document up to 100 MB or one public webpage as context; PDF, DOCX, DOC, PPTX, PPT, Keynote, and Pages inputs are limited to 50 pages. Document and webpage context are mutually exclusive and cannot be combined with dedicated first/last-frame anchors.

Need mature themes? Wan 3 Uncensored — Sogni model ID wan3-uncensored — is the Wan 3 Enhanced Team's build of Alibaba's Wan 3 on a more permissive content policy, and it is Sogni's premiere mature-theme video model. It accepts mature-theme subject matter that standard Wan 3 declines and appears as the Wan 3 Uncensored option under Wan 3 version once the Sensitive Content Filter is turned off. It is priced separately and is pay as you go on every render. See the Wan 3 Uncensored page at /models/wan-3-uncensored for its own specs, pricing, and prompt guidance.

Prompting tips

Wan 3 accepts plain natural language and optional provider expansion. Make each visible beat and each reference role explicit.

• References — Name loose inputs as Image 1, Video 1, and Audio 1 in per-type order, and assign each one a clear role.
• Dialogue and sound — Quote the exact spoken words, identify the speaker, and describe voice, ambience, effects, and music in the same brief.
• Exact prompts — Keep prompt expansion on for ordinary creative briefs; disable it when exact wording is a hard requirement.
• Video references — Describe the motion, timing, identity, or style to borrow from Video 1 without promising source-preserving editing or frame-exact continuation.

Pricing

Wan 3 is a pay-as-you-go Premium Spark vendor model. Every clip uses purchased Spark, including for Sogni Unlimited members. Unlimited saves 5%; Unlimited Pro saves 10%.

Launch-sale rates before plan discounts (as of 2026-08-26): $0.0455 per billable second at 480p, $0.091 at 720p, and $0.182 at 1080p. That passes Alibaba's current 30% vendor promotion through to artists before the additional 5% Unlimited or 10% Unlimited Pro discount, which stacks on top of any active promotion. Alibaba schedules the promotion through September 23, 2026 at 16:00 UTC.

Wan 3 Uncensored (model ID wan3-uncensored) is priced separately; see its page. It runs $0.08 per billable second at 480p, $0.16 at 720p, and $0.32 at 1080p before the 5% Unlimited or 10% Unlimited Pro discount.

Text- and image-led requests bill output duration. Requests with reference video bill input plus output duration. Smart duration reserves the 30-second combined maximum before generation, then settlement uses Alibaba's reported input and output durations after completion. Native audio on or off uses the same rate.

API

One Sogni API key reaches every model in the catalog — call Wan 3 with the exact model id.

import { SogniClient } from '@sogni-ai/sogni-client';

const client = await SogniClient.createInstance({
  appId: crypto.randomUUID(),
  apiKey: process.env.SOGNI_API_KEY,
  network: 'fast',
});

const project = await client.projects.create({
  type: 'video',
  modelId: 'wan3.0-video',
  positivePrompt: 'A documentary presenter walks through a detailed workshop and says Welcome to the future as the camera tracks beside her',
  numberOfMedia: 1,
  duration: 8,
  ratio: '16:9',
  generateAudio: true,
  promptExtend: true,
  watermark: false,
});

const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24h

curl https://api.sogni.ai/v1/creative-agent/workflows \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SOGNI_API_KEY" \
  -d '{
    "input": {
      "title": "First render",
      "steps": [{
        "id": "step1",
        "toolName": "generate_video",
        "arguments": { "prompt": "A documentary presenter walks through a detailed workshop and says Welcome to the future as the camera tracks beside her", "videoModel": "wan3.0-video", "duration": 5 }
      }]
    },
    "confirm_cost": true
  }'

REST workflow alias: wan3.0-video. Pin the exact id with the SDK. Full reference at docs.sogni.ai.