img_uuid, then poll or receive HTTPS callbacks for the result.HappyHorse 1.1 API for Video Generation
Access the HappyHorse 1.1 API through the independent GoEnhance Open API for text-to-video, first-frame image-to-video, or a separate reference-image workflow. Submit an asynchronous task, save the returned
Create an API Key
Choose the Right HappyHorse API Mode
Text-to-Video
Send model: happyhorse-1-1 with a required prompt and no image_url. Select a documented ratio, duration, and resolution for the generated video.
First-Frame Image-to-Video
Add image_url to animate a first frame. The image must be JPEG, PNG, or WEBP, at least 300px, under 10MB, and within the documented 1:2.5 to 2.5:1 ratio range.
Reference-Image Video
Use model: happyhorse-1-1-ref with 1–9 URLs in image_urls. Refer to each source in the prompt as [Image 1], [Image 2], and so on.
Validate the selected request mode before sending work to your production queue.
HappyHorse 1.1 API Capabilities and Limits
Two standard input modes
Use a prompt alone for text-to-video or add one <code>image_url</code> for first-frame image-to-video.
Separate multi-reference model
Use <code>happyhorse-1-1-ref</code> with 1–9 required reference-image URLs; it does not support pure text-to-video.
3–15 second duration
Set <code>duration</code> to an integer from 3 through 15 seconds. The documented default is 5 seconds.
720p or 1080p output
Choose <code>720p</code> or <code>1080p</code>. The documented default is <code>720p</code>.
Portrait, square, and landscape ratios
The standard route supports 16:9, 9:16, 1:1, 4:3, and 3:4. Reference mode also lists 4:5 and 5:4.
Polling and callbacks
Persist <code>img_uuid</code>, poll the job-detail endpoint, or provide a public HTTPS callback URL for status updates.
GoEnhance documents per-second pricing at $0.02 per token and currently labels these rates as a limited-time offer.
HappyHorse 1.1 API Pricing
720p: $0.104 per second
720p generation uses 5.2 tokens per second. A 5-second request uses 26 tokens, or $0.52 at the documented conversion.
1080p: $0.144 per second
1080p generation uses 7.2 tokens per second, equal to $0.144 per generated second.
Estimate by duration
Multiply the selected per-second rate by the requested 3–15 second duration. Check the live API reference before production batches because promotional pricing can change.
Integrate the HappyHorse 1.1 API
1
1. Create and protect an API key
Create a GoEnhance key and send it as bearer authorization from trusted server-side code.
2
2. Select the model
Choose
happyhorse-1-1 for prompt-only or first-frame generation, or happyhorse-1-1-ref for 1–9 reference images. 3
3. Build and validate the payload
Provide the required prompt, then validate image fields, duration, resolution, ratio, and callback URL for the chosen mode.
4
4. Submit the video task
POST to
https://api.goenhance.ai/api/v1/videos/generations and store the returned img_uuid. 5
5. Track status
Poll
GET https://api.goenhance.ai/api/v1/jobs/detail?img_uuid=... or receive status changes at a public HTTPS callback. 6
6. Handle the terminal result
Process success and failure idempotently, verify the returned asset, and avoid duplicate downstream work when polling and callbacks overlap.
Connect structured generation requests to review, storage, and delivery workflows.
Developer Use Cases for the HappyHorse API
Campaign video variants
Generate short motion concepts from structured prompts for creative review and downstream editing.
Product and brand motion
Animate an approved first frame while your backend controls duration, resolution, and completion handling.
Character interaction studies
Use the reference model to describe how subjects from approved source images should appear together in one scene.
Storyboard previsualization
Turn shot descriptions into reviewable clips before committing to a larger production workflow.
Localized creative pipelines
Parameterize prompts for regional variants while keeping task submission and monitoring consistent.
Automated asset queues
Connect generation, job-state persistence, callbacks, storage, and human approval in a backend service.
Answers about pricing, request modes, input limits, and asynchronous task handling.