HappyHorse 1.0 API

HappyHorse 1.0 is a video generation model ranked #1 on the Artificial Analysis Text-to-Video Leaderboard. Live on EvoLink with 4 variants (text-to-video, image-to-video, reference-to-video, video-edit) and per-second billing from $0.179/s.

Model Type:

✓Text to Video (T2V)Image to Video (I2V)Reference to Video (R2V)Video Edit (EDIT)

Price: $0.179 - 0.318(~ 12.15 - 21.6027 credits) per second of video

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

Use the same API endpoint for all versions. Only the model parameter differs.

Prompt

171 (suggested: 2,000)

Aspect Ratio

Quality

Duration5s

3s15s

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Pricing

Model	Mode	quality	Price
Happy Horse 1.0 Text to Video	Video Generation	720p	$0.179/ second(12.15 Credits)
Happy Horse 1.0 Text to Video	Video Generation	1080p	$0.318/ second(21.6027 Credits)

Happy Horse 1.0 Text to Video

Video Generation

quality:720p

Price:

$0.179/ second

(12.15 Credits)

Happy Horse 1.0 Text to Video

Video Generation

quality:1080p

Price:

$0.318/ second

(21.6027 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

HappyHorse 1.0 API: Video Generation, Pricing, and Integration

HappyHorse 1.0 topped the Artificial Analysis Text-to-Video Leaderboard in April 2026, above Seedance 2.0 and Kling 3.0. Live now on EvoLink with per-second billing (from $0.179/s for 720p) and async delivery, on the same unified endpoint used for every other video model.

HappyHorse 1.0 AI video generation showcase — ranked #1 on Artificial Analysis

About HappyHorse 1.0

HappyHorse 1.0 is a video generation model that reached the top position on the Artificial Analysis Text-to-Video Leaderboard (No Audio) in April 2026. EvoLink offers 4 variants — text-to-video, image-to-video, reference-to-video (1~9 reference images), and video-edit — at 720p and 1080p resolutions.

HappyHorse 1.0 is available now on EvoLink through the same unified API gateway used for Seedance 2.0, Kling 3.0, Sora 2, and Veo 3.1 — one API key, one billing system, no additional vendor accounts. Per-second pricing starts at $0.179/s for 720p and $0.318/s for 1080p.

HappyHorse 1.0 API technical capabilities

Known and expected capabilities based on public leaderboard data and community reports

T2V

Text-to-Video

Generate video from text descriptions. HappyHorse ranked #1 for text-to-video quality on the Artificial Analysis leaderboard, above Seedance 2.0 and Kling 3.0.

I2V

Image-to-Video

Animate still images into video clips with natural motion. Community benchmarks indicate strong subject preservation and smooth transitions.

Audio

Multilingual Audio

Community reports indicate support for synchronized audio generation in 6+ languages, including dialogue lip-sync. Not yet officially confirmed.

Billing

Per-Second Billing

HappyHorse on EvoLink uses per-second billing for precise cost control. 720p starts at $0.179/s and 1080p at $0.318/s; video-edit is billed on (input + output) seconds, rounded up to 0.1s.

Async

Async Task Delivery

Production-ready async task handling with status tracking and webhook callbacks. The same delivery pattern used for all video models on EvoLink.

SDK

OpenAI SDK Compatible

Use existing OpenAI SDK integrations with minimal code changes. Just update the base URL and model parameter to route to HappyHorse.

HappyHorse 1.0 API capabilities

Text-to-Video Generation

HappyHorse 1.0 generates video from text prompts. On the Artificial Analysis leaderboard, it scored higher than Seedance 2.0 720p and Kling 3.0 in text-to-video quality. Describe scenes, motion, and style in natural language to produce clips for marketing, social content, or creative projects.

Image-to-Video Generation

HappyHorse 1.0 also supports image-to-video generation, turning still images into animated video clips. Community benchmarks show strong performance in preserving subject identity and adding natural motion to reference images.

Unified API Access via EvoLink

Access HappyHorse through the same EvoLink API endpoint used for Seedance 2.0, Kling 3.0, Sora 2, and 40+ other models. One API key, one billing system, and the same async task delivery pattern you already use.

EvoLink unified API access for HappyHorse

How HappyHorse 1.0 compares to other video models on EvoLink

HappyHorse 1.0 leads the Artificial Analysis leaderboard, but each model has different strengths. Here is how it fits alongside the video models already available on EvoLink.

HappyHorse vs Seedance 2.0

HappyHorse 1.0 scored higher than Seedance 2.0 720p on the Artificial Analysis text-to-video leaderboard. Both support reference-to-video and video editing, but Seedance 2.0 accepts a wider mix of references (9 image + 3 video + 3 audio vs. HappyHorse's 1~9 images). Choose Seedance 2.0 for video/audio references; choose HappyHorse for top-of-leaderboard text-to-video quality.

HappyHorse vs Kling 3.0

HappyHorse 1.0 also ranked above Kling 3.0 on the same leaderboard. Kling 3.0 is a strong choice for repeatable short-form prompt-first production at $0.075/s. HappyHorse 1.0 starts at $0.179/s for 720p — higher per-second cost in exchange for top-ranked output quality.

Why route through EvoLink

On EvoLink, HappyHorse plugs into your existing workflow without a new vendor account, a new billing path, or a new integration. Switch between HappyHorse, Seedance, Kling, and Sora with one model parameter change.

How to integrate HappyHorse API through EvoLink

The same three-step integration used for every video model on EvoLink.

Get your API key

Sign up on EvoLink and create an API key from your dashboard. Free credits are included with every new account — use them to test HappyHorse 1.0 right away.

Submit a generation task

Send a POST request to /v1/videos/generations with your text prompt or image reference. The API returns a task ID for async tracking. The same endpoint and request format used for Seedance, Kling, and Sora.

Retrieve your video

Poll the task status endpoint or configure a webhook callback. Once complete, download your video file. Iterate on prompts using the same API structure for fast production cycles.

View API Docs

HappyHorse 1.0 vs Seedance 2.0 vs Kling 3.0

Pre-launch comparison based on Artificial Analysis leaderboard data and publicly available information.

	HappyHorse 1.0	Seedance 2.0	Kling 3.0
Artificial Analysis Ranking	#1	#2	Lower
Text-to-Video	✓	✓	✓
Image-to-Video	✓	✓	✓
Video-to-Video Editing	✓ (video-edit variant)	✓	—
Native Audio	Reported (6+ languages)	✓ (multi-language lip-sync)	—
@-Reference System	✓ (1~9 reference images)	✓ (9 img + 3 vid + 3 audio)	—
API Pricing	Per-second (from $0.179/s)	Per-second (from $0.025/s)	Per-second ($0.075/s)
API Availability	Live on EvoLink	Live on EvoLink	Live on EvoLink

Full release-watch analysis: HappyHorse 1.0 →

HappyHorse API FAQ

Everything you need to know about the product and billing.

HappyHorse 1.0 is a video generation model ranked #1 on the Artificial Analysis Text-to-Video Leaderboard (No Audio) as of April 2026. EvoLink offers 4 variants: text-to-video, image-to-video, reference-to-video (1~9 reference images), and video-edit, at 720p and 1080p.

Yes. HappyHorse 1.0 is live on EvoLink with all 4 variants — text-to-video, image-to-video, reference-to-video, and video-edit. Sign up for an account to receive free credits and start generating today.

HappyHorse 1.0 scored higher than Seedance 2.0 720p on the Artificial Analysis text-to-video leaderboard. Both support reference-to-video and video editing, though Seedance 2.0 accepts a wider mix of references (9 image + 3 video + 3 audio vs. HappyHorse's 1~9 images). Both are live on EvoLink's unified API.

HappyHorse 1.0 also ranked above Kling 3.0 on the Artificial Analysis leaderboard. Kling 3.0 is $0.075/s with proven short-form production workflows; HappyHorse 1.0 is $0.179/s for 720p — higher per-second cost in exchange for top-ranked output quality. Both are live on EvoLink.

HappyHorse 1.0 on EvoLink uses per-second billing: 720p starts at $0.179/s and 1080p at $0.318/s. Video-edit is charged on (input + output) seconds, rounded up to 0.1s. Per-second rates are consistent across the 4 variants and visible in the pricing table on this page.

On EvoLink, HappyHorse 1.0 supports 4 modes: text-to-video, image-to-video, reference-to-video (1~9 reference images), and video-edit (prompt + optional reference images). Each variant has its own playground and API endpoint on this page.

Yes. HappyHorse 1.0 uses the same API key, endpoint, and billing system as Seedance 2.0, Kling 3.0, Sora 2, and all other models on EvoLink. No additional vendor setup required.

Sign up on EvoLink, create an API key, and call the unified video API with model = happyhorse-1.0-text-to-video (or one of the other 3 variants). The endpoint, auth, and async delivery format are identical to Seedance, Kling, and Sora — switch by changing one parameter.

Pricing, playground, and the API reference for all 4 variants are live on this page. For deeper analysis of model capabilities and benchmarks, read the HappyHorse release-watch blog post.

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/videos/generations

Create Video

Happy Horse 1.0 Text-to-Video (happyhorse-1.0-text-to-video) generates a 3~15 second video purely from a text prompt. Supports 720P / 1080P resolutions and 5 aspect ratios.

Asynchronous processing — use the returned task ID to .

Generated video links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: happyhorse-1.0-text-to-video

Video generation model name. Fixed value for this endpoint.

Examplehappyhorse-1.0-text-to-video

promptstringRequired

Text description of the video to generate.

Notes

Up to 2500 Chinese characters or 5000 non-Chinese characters; excess is auto-truncated.
Detailed shot-by-shot descriptions yield better multi-shot narratives, e.g. "Shot 1 [0~3s] wide angle: ...; Shot 2 [3~6s] medium shot: ...".

Example

A miniature city built from cardboard and bottle caps comes to life at night. A cardboard train slowly passes through, dotted with tiny lights illuminating the path ahead.

qualitystringOptionalDefault: 720p

Output resolution tier. Directly affects billing.

Value	Description
720p	Standard quality (1.0x price)
1080p	HD quality (1.778x price)

Example720p

aspect_ratiostringOptionalDefault: 16:9

Output video aspect ratio.

Value	Description
16:9	Landscape (default)
9:16	Portrait
1:1	Square
4:3	Standard
3:4	Portrait standard

Example16:9

durationintegerOptionalDefault: 5

Output video duration in seconds. Directly affects billing.

Notes

Range: 3~15 (any integer).
Total cost = base_price × duration × resolution_multiplier.

Example5

seedintegerOptional

Random seed for deterministic outputs. Pass 0 or omit to use a random seed.

Notes

Range: 0 ~ 2147483647 (0 is treated as unset)
Same seed + same prompt may still produce slightly different results due to model probabilistic nature.

Example42

callback_urlstringOptional

HTTPS callback URL to be invoked when the task finishes.

Notes

Triggered on completion / failure / cancellation.
HTTPS only, no internal IPs.
Max length: 2048 chars. Timeout: 10s, max 3 retries.

Examplehttps://your-domain.com/webhooks/happyhorse-task

Request Example

{
  "model": "happyhorse-1.0-text-to-video",
  "prompt": "A majestic eagle soaring through mountain peaks at sunset, cinematic lighting",
  "quality": "720p",
  "aspect_ratio": "16:9",
  "duration": 5,
  "seed": 42
}

Response Example

{
  "created": 1745726400,
  "id": "task-unified-1745726400000000000-aBcDeFgH-happyhorse-1.0-text-to-video",
  "model": "happyhorse-1.0-text-to-video",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": false
  },
  "type": "video"
}