How to Use the Wan 3.0 Omni Reference API: Omni Reference integration guide (2026)

Wan 3.0 Omni Reference is an Omni Reference model by Alibaba: Generates videos up to 30 seconds with native audio from multimodal references — images, video, audio, documents, and web pages. Reproduces characters, props, and spatial relationships from your references at pixel-level fidelity, with a first/last-frame mode for precise control. On NamiFusion you can try it in the playground (exact quote shown before you submit), then call it through one unified REST API — a typical run costs about $1.00.

TL;DR

· Task type: Omni Reference, provided by Alibaba

· Pricing: about $1.00 per typical run ($1 = 100 credits), pay-as-you-go

· Getting started: playground (exact quote before submit) → create an API key → one POST request

· Tunable parameters: 12 (see the table below)

· No platform watermark; commercial use allowed (per the Terms of Service)

What can you build with Wan 3.0 Omni Reference?

Content automation: wire this model into your workflow and call it on demand through one unified API.

How do you call this API?

1. Sign up on NamiFusion and create a key on the API Keys page (signup bonus credits can only be used on selected models).

2. Submit a task with the cURL example below, passing your key as a Bearer token.

3. Poll the task status with the returned task_uuid and read the output URLs when completed.

# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/alibaba/wan-3.0/video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "resolution": "1080P",
    "aspect_ratio": "adaptive",
    "duration": 5,
    "generate_audio": true,
    "enable_thinking": false
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"

What parameters does it take?

prompt (Prompt): optional

images (Reference Images): optional

audios (Reference Audio): optional

first_frame (First Frame): optional

last_frame (Last Frame): optional

resolution (Resolution): optional, default "1080P"

aspect_ratio (Aspect Ratio): optional, default "adaptive"

duration (Duration (seconds)): optional, default 5

generate_audio (Generate Audio): optional, default true

enable_thinking (Thinking Mode): optional, default false

file (Reference Document): optional

link (Reference Web Page): optional

How do you write prompts for Wan 3.0 Omni Reference?

1. Subject first: lead with the actor and action, then add environment, lighting and style ("an astronaut sprinting through a neon street in the rain, cinematic, shallow depth of field").

2. Concrete nouns beat stacked adjectives: "85mm portrait lens, golden-hour backlight" works far better than "very beautiful, ultra high quality".

3. Change one variable per iteration: pin the seed to reproduce a result, tweak a single phrase at a time so you know what actually moved the output.

4. State negatives positively: instead of "no blur", ask for "sharp focus, crisp details".

How much does it cost?

Pay-per-use in credits. A typical run costs about $1.00 ($1 = 100 credits); the exact price varies with parameters like resolution or duration, and the playground shows the exact quote before you submit.