model: wan22_spicy through the independent GoEnhance API for prompt-only text-to-video or first-frame image-to-video. Submit a task, save the returned img_uuid, then poll or receive callback updates until completion.Wan 2.2 Spicy API for Video Generation
Access
Get API Key
Choose a Wan 2.2 Spicy API input mode
Text-to-video from a required prompt
POST to https://api.goenhance.ai/api/v1/videos/generations with model: wan22_spicy and a required prompt. Omit image_url for text-to-video.
Image-to-video from a first frame
Add a public image_url to use it as the first frame. The same endpoint and model identifier handle both input modes.
Validate the documented request contract before submitting an asynchronous video task.
Wan 2.2 Spicy API capabilities and fields
Exact model identifier
Set <code>model</code> to <code>wan22_spicy</code>; preserve the underscore exactly.
Required prompt
Provide a text <code>prompt</code> describing the requested video in either input mode.
Optional first frame
Provide <code>image_url</code> for image-to-video, or omit it for prompt-only generation.
Two resolution choices
Select <code>480p</code> or <code>720p</code>. The documented default is <code>720p</code>.
Bearer authentication
Send your GoEnhance API key in the <code>Authorization</code> header.
Optional callback
Provide a publicly accessible HTTPS <code>custom_callback_url</code> to receive task-status POST requests.
The current GoEnhance documentation lists fixed per-task pricing for the two supported resolutions.
Wan 2.2 Spicy API pricing
480p task pricing
Each 480p task costs 5 tokens, equal to $0.10 at the documented $0.02-per-token rate.
720p task pricing
Each 720p task costs 10 tokens, equal to $0.20 at the documented $0.02-per-token rate.
Cost before submission
Pricing is per task rather than per second: choose the resolution, then apply its fixed token charge.
Integrate the Wan 2.2 Spicy API in six steps
1
1. Create an API key
Create a GoEnhance key and send it as a bearer token in the Authorization header.
2
2. Choose the input mode
Use a prompt alone for text-to-video, or add
image_url for first-frame image-to-video. 3
3. Validate the payload
Require
model: wan22_spicy and prompt, then allow only 480p or 720p. 4
4. Submit the task
POST to
/api/v1/videos/generations and persist the returned img_uuid. 5
5. Track status
Poll
GET /api/v1/jobs/detail or receive POST updates at your HTTPS callback URL. 6
6. Handle the terminal result
Process success and failure idempotently, then validate and store the returned video asset.
Build repeatable video workflows around explicit inputs, fixed resolution pricing, and task status.
Developer use cases for the Wan 2.2 Spicy API
Campaign concept clips
Turn approved prompts into short visual concepts for creative review and downstream editing.
Product motion studies
Use an approved product image as the first frame for controlled motion exploration.
Social video pipelines
Generate visual source clips while your application handles queueing and asset delivery.
Storyboard animation
Animate a selected storyboard frame to test movement and atmosphere before production.
Localized creative variants
Parameterize prompts for regional concepts without changing the asynchronous integration layer.
Previsualization
Translate concise shot ideas into reviewable video outputs for planning and iteration.
Answers to common pricing, input-mode, task-status, and Alibaba API questions.