Which mode does HappyHorse 1.1 pick for my request?

HappyHorse 1.1 reads the mode from the request shape: a prompt with no media runs text-to-video, exactly one image in image_urls runs image-to-video (first frame), and one to nine images in reference_image_urls run reference-to-video. The prompt is required for text-to-video and reference-to-video, and optional for image-to-video.

What resolutions, ratios, and durations does HappyHorse 1.1 support?

HappyHorse 1.1 supports 720p and 1080p, nine aspect ratios for text-to-video and reference-to-video, and any integer duration from 3 to 15 seconds (default 5). In image-to-video, orientation is derived from the first-frame image, so aspect_ratio is ignored.

How do bracket Image-N references work?

In HappyHorse 1.1 reference-to-video mode you can pass one to nine reference images and cite them in the prompt with bracket Image-N tags. HappyHorse 1.1 maps each tag to the matching image, so you control which reference drives subject, style, or background.

How is HappyHorse 1.1 different from version 1.0?

This release improves on 1.0 with better prompt understanding, smoother motion, stronger subject consistency, and higher overall quality. The request shape and resolution-by-second pricing model stay familiar, so upgrading is a one-line model id change.

Where is the full API reference?

The full parameter list, error codes, and runnable cURL examples live at /docs/happyhorse-1-1.

Is HappyHorse 1.1 free or paid?

Paid. Completed generations are charged at the rates in this page's pricing table. Eligible new accounts may receive promotional test credits; availability and amount are shown at signup or in the dashboard. Technical or provider failures are refunded automatically, except where this page documents a charged output-moderation block.

Does HappyHorse 1.1 require a monthly subscription?

No. Pricing is pay-as-you-go: $1 buys 1,000 credits and credits never expire. Cost scales with what you generate rather than with a recurring fee.

How do I get a HappyHorse 1.1 API key?

Sign up and create a key in the dashboard, no card required. Pass it as a Bearer token in the Authorization header.

HappyHorse 1.1 — Text, Image & Reference to Video

Q: How much does HappyHorse 1.1 cost?

HappyHorse 1.1 pricing is per-second by resolution. See the current 720p and 1080p rates in the pricing table on this page. The routing mode never changes the rate, and failed jobs refund automatically.

HappyHorse 1.1 by Alibaba turns text, a first-frame image, or up to nine reference images into 3–15s video. 720p or 1080p, nine aspect ratios, async endpoint.

Highlights: 3–15 s · 720p / 1080p · up to 9 references
Best for: Character consistency, UGC, ads
Input: Text, image, or reference images
Output: Video (mp4)

Input

Prompt*

Optional in image-to-video · use bracket Image-N tags to cite references

Resolution

Default 720p

Aspect ratio

Ignored in image-to-video

Duration (seconds)5

3 to 15 · default 5

Estimated cost~$0.908908 credits

Result

Try one of these prompts

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost

$0.908908 credits

One 5-second sample at the cheapest tier.

Testing budget guide

Add credits

$10

≈ 11 tests

$50

≈ 55 tests

$100

≈ 110 tests

720P: $0.182; Price · 1 second
1080P: $0.242; Price · 1 second

What is the HappyHorse 1.1 API?

HappyHorse 1.1 is Alibaba Cloud's unified video model, exposed on reAPI as one async endpoint that picks its mode from the request shape: a prompt alone for text-to-video, exactly one first-frame image for image-to-video, or 1 to 9 reference images for reference-to-video. Clips run 3 to 15 seconds at 720p or 1080p across nine aspect ratios, and prompts take up to 5,000 non-CJK characters (2,500 for CJK). Billing depends only on resolution and duration, so the routing mode never changes the rate.

Generating video from text, a first-frame image, and reference images

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Animate any photo with HappyHorse 1.1

Pass a single first-frame image and a motion prompt. HappyHorse 1.1 returns a 3 to 15 second clip and reads orientation straight from the image — no aspect-ratio guesswork, no model swap.

Generate a clip

Compose new scenes with HappyHorse 1.1 reference images

Send one to nine reference images alongside a prompt. HappyHorse 1.1 fuses subject, style, and props into a brand-new scene — cite specific frames with bracket Image-N tags for product shots, character reskins, and stylized social posts.

Ship social video from a single prompt

Describe the shot and HappyHorse 1.1 returns it in any of nine aspect ratios at 720p or 1080p. One endpoint covers Reels, Shorts, and TikTok without a storyboard or an edit timeline.

Why reAPI for HappyHorse 1.1

One endpoint, three modes

HappyHorse 1.1 auto-routes text-to-video, image-to-video, and reference-to-video by request shape. A prompt alone runs T2V, one first-frame image runs I2V, and one to nine reference images run R2V. No model swap, no second integration.

Pricing by resolution × seconds

HappyHorse 1.1 bills per-second by resolution. See the current 720p and 1080p rates in the pricing table on this page. The routing mode never changes the rate, and failed jobs refund automatically.

Sharper than the last release

Over version 1.0, HappyHorse 1.1 lands better prompt understanding, smoother motion, stronger subject consistency, and higher overall quality — so it holds a scene together across the full 3 to 15 second clip.

HappyHorse 1.1 vs Runway Gen-4

How HappyHorse 1.1 on reAPI compares to Runway Gen-4 for text, image, and reference-driven video.

Capability

HappyHorse 1.1 on reAPI

Runway Gen-4

Input modes

Text, image, and reference-to-video from one model id

Text and image-to-video

Reference images

Up to 9, with bracket Image-N citations in the prompt

Single reference image guidance

Resolution

720p and 1080p

Up to 1080p, plan-gated tiers

Clip length

3 to 15 seconds per request

5 or 10 second base clips, extendable

Pricing model

Per-second by resolution — routing mode is free

Credit packs tied to subscription plans

Access

OpenAI-style async endpoint, pay-as-you-go credits

First-party API plus web app, plan-based limits

Comparison reflects publicly documented Runway Gen-4 behavior as of mid-2026 and may change. Model details reflect this page.

Ship in three steps

step 01
Create an API key
Sign up and grab a key from the dashboard. Free credits cover your first generations — no card required.
Open
step 02
Submit a video task
POST to /api/v1/videos/generations with model = happyhorse-1-1. The endpoint returns a task ID immediately.
Open
step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. Download the output video and ship it.
Open

docs/api/happyhorse-1-1

API reference

Drop-in code and the full parameter table.

View full reference

curl -X POST https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1-1",
    "prompt": "A coastal road at sunset, slow-motion camera push-in",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

HappyHorse 1.1 is Alibaba's unified video generation model, served through one endpoint on reAPI. A single model id (happyhorse-1-1) auto-routes text-to-video, image-to-video, and reference-to-video based on which inputs the request carries.