img_uuid, then poll or receive callbacks until the task succeeds or fails.Wan 3.0 API for Video Generation
Access Wan 3.0 through the independent GoEnhance Open API for text-to-video, first-frame, and start-end-frame generation. Submit an asynchronous request, persist the returned
Get API Key
Choose the right Wan 3.0 API request mode
Prompt and frame-guided generation
POST to https://api.goenhance.ai/api/v1/videos/generations with model: wan-3-0. Use a prompt alone, add image_url for a first frame, or add image_end_url with it for a final frame.
A separate route for reference materials
Use model: wan-3-0-refs for ordered reference images, videos, audio, a document, or a web page. Do not mix reference materials with first- or last-frame inputs; the modes are mutually exclusive.
Validate the documented fields before a task enters your video pipeline.
Wan 3.0 API capabilities and request fields
Required model and prompt
For the standard route, set <code>model</code> to <code>wan-3-0</code> and provide a text <code>prompt</code>.
First and last frames
Add <code>image_url</code> for a first frame. <code>image_end_url</code> is optional but must be used together with <code>image_url</code>.
Aspect ratio
Choose adaptive, 16:9, 4:3, 1:1, 3:4, or 9:16. The documented default is adaptive; 21:9 is not listed.
Duration
Choose any integer from 2 through 30 seconds. The documented default is 5 seconds.
Resolution and audio
Select 480p, 720p, or 1080p; GoEnhance defaults to 720p. <code>generate_audio</code> defaults to true and carries no extra generation charge.
Seed and callback
Optionally set a seed from 0 through 2147483647 and provide a public HTTPS <code>custom_callback_url</code> for status updates.
Both Wan 3.0 routes use the same per-second rates. Estimate cost as the selected rate multiplied by requested duration.
Wan 3.0 API pricing
480p pricing
2.91 tokens per generated second, equal to $0.0582 per second at the documented $0.02-per-token rate.
720p pricing
5.82 tokens per generated second, equal to $0.1164 per second at the documented $0.02-per-token rate.
1080p pricing
11.64 tokens per generated second, equal to $0.2328 per second at the documented $0.02-per-token rate.
Integrate the Wan 3.0 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. Select one input mode
Use
wan-3-0 for prompt or first/last frames, or wan-3-0-refs for reference materials. 3
3. Validate the request
Check required fields, frame dependencies, duration, resolution, ratio, and reference limits before submission.
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 updates at a public HTTPS callback URL. 6
6. Handle completion
Process success and failure idempotently, verify the returned asset, and account for refunded tokens when a reference job fails upstream.
Build repeatable video-generation workflows around explicit inputs and terminal task states.
Developer use cases for the Wan 3.0 API
Campaign video variants
Generate short concept clips from structured prompts for creative review and downstream assembly.
Product motion
Animate an approved first frame while your application controls prompt, framing, and completion handling.
Storyboard transitions
Provide first and last frames to explore motion between two approved visual beats.
Reference-led creative
Use the separate reference route when a workflow depends on ordered images, videos, audio, a document, or a web page.
Localized content pipelines
Parameterize prompts for regional variants without changing the asynchronous task handler.
Previsualization
Turn concise shot descriptions into reviewable motion concepts before full production.
Answers to common pricing, request-mode, validation, task-status, and Alibaba API questions.