WAN / Video generation

Wan 3.0

API integration ↗

wan-3.0

Generate video from text, frame constraints or reference material.

Output: Video
Resolution: 480P / 720P / 1080P
Output duration: 2–30 seconds / Automatic (mode-dependent)
Integration: HTTP / asynchronous tasks

CAPABILITIES

Capabilities & limits

Supported modes

Text to videoOpening frameClosing frameOpening + closing framesReference media

Before you use this model

Combine text, opening and closing frames, or reference media according to mode rules. With reference video, billing uses trusted input video duration plus output duration. Turning off generated audio does not imply a lower price.

Specifications & defaults
Parameter	Supported values / default
Resolution	480P / 720P / 1080P
Output duration	2–30 seconds / Automatic (mode-dependent)
Aspect ratio	16:9 · 4:3 · 1:1 · 3:4 · 9:16 · adaptive
Prompt limit	20000 Unicode code points
Definition defaults (subject to mode rules)	duration: 5 · resolution: 720P · aspect_ratio: adaptive
Reference media limits	10 images / 5 videos / 5 audio clips

Media limits do not mean all inputs can be combined in every mode. Consult the full field reference for sizes, formats and incompatible combinations.

Explore the models supported by ByteSOTA. Availability depends on your account permissions; check /v1/models for enabled models, configurations and defaults.

Full request fields and limits (Chinese) ↗

CREATIVE WORKFLOWS

Use cases

Create a shot from a written scene.
Control composition with frame images.
Work with reference video after checking input and output metering.

Concept artwork, not model output. This page does not yet include a verified generated sample.

PRICING / USD

Price the specification you need.

Prices are in USD, with a date shown for official reference rates. Missing prices do not mean free usage. Existing tasks are billed using the prices recorded when they were created.

Loading current prices…

Pricing ↗

API INTEGRATION

API example

Send HTTP requests from your server using the model and parameters you choose. ByteSOTA must first enable your account, API key and model permissions.

HTTP 202 means accepted. Save the task ID and follow next_poll_after_seconds. Generation status, result availability and billing status are separate facts.

HTTP / cURL

curl --request POST 'https://bytesota-api.businessmodelcraft.com/v1/videos/generations' \
  --header 'Authorization: Bearer YOUR_PLATFORM_API_KEY' \
  --header 'Content-Type: application/json' \
  --header 'Idempotency-Key: example-wan-3.0-text-480P-001' \
  --data-raw '{
    "model": "wan-3.0",
    "prompt": "A kitten walks along a garden path as the camera follows slowly.",
    "duration": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }'

Query result

HTTP / cURL

curl 'https://bytesota-api.businessmodelcraft.com/v1/tasks/vid_ABCDEFGHIJKLMNOP' \
  --header 'Authorization: Bearer YOUR_PLATFORM_API_KEY'

Copy this example into your project. It does not run on this page, and the API key shown is a placeholder.

Specifications and examples: model definitions and the public API integration guide.

Read the full API guide (Chinese) ↗