Skip to main content

Overview

Wan Animate LoRA is an asynchronous character animation model. It uses one source image as the character reference and one motion video as the movement reference, then returns a generated MP4 video.

Endpoint and authentication

Base URL:
All requests require your APIXO API key:
Submit requests also require:

Copy-paste async quickstart

The response contains a taskId. Save it and poll the status endpoint until state becomes success or failed.

Request body

Parameters

string
default:"async"
Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.
string
Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.
object
required
Wan Animate LoRA input parameters.

Poll for result

Processing response:
Success response:
After state becomes success, parse resultJson and read its resultUrls array.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.
See Webhooks for delivery requirements and retry behavior.

Billing

Wan Animate LoRA is billed per generated video second. The selected resolution determines the unit price, and billable duration is detected from video_urls[0]. If the reference video is shorter than 5 seconds, billing uses 5 seconds. Longer videos are billed by their detected duration. For current route and market comparison pricing, see Pricing.

Latency and polling

Actual latency may vary by reference video duration, resolution, queue load, and current route health.
Video generation can take several minutes. For production workloads, use callback mode to avoid frequent polling.

Errors and troubleshooting

See Error Codes for the full error reference.