HappyHorse 1.1 API Pricing: $0.16 per Second at 720p

TL;DR

• HappyHorse 1.1 is Alibaba's video model. On HiAPI it has three endpoints (text-to-video, image-to-video, and reference-to-video), and all three cost the same: $0.16 per second at 720p and $0.21 per second at 1080p.
• Clips run 3 to 15 seconds, billed per second. Text-to-video includes native audio at no extra charge. A 5-second 720p clip is $0.80.
• resolution defaults to 1080p, so if you leave it out you pay $0.21/s. Failed tasks are not charged.

Price table

Live HiAPI prices, checked October 15, 2026.

1.1 costs less than 1.0. At 1080p it drops from $0.288 to $0.21 per second, about 27% cheaper, so new projects should use 1.1.

Cost by duration

$10 covers 62 seconds at 720p or 47 seconds at 1080p. Reference images cost nothing extra on reference-to-video: one image or nine, the price is the same.

What you get

A 3-second vertical product teaser. The audio was generated by the model:

VIDEO

Product-drop teaser, vertical 9:16: a chunky retro running sneaker in cream and burnt orange rotates slowly on a matte black turntable, hard rim lighting carving its silhouette, fine dust particles drifting in the beam, dark studio background with plenty of empty space above for a title overlay. Punchy, cinematic. Native audio: a low bass hum and one soft whoosh as the shoe completes its turn.

Generate with this prompt → (3 seconds, 720p, 9:16)

happyhorse-1.1/text-to-video, 720p, 9:16, 3 seconds, with audio, $0.48.

The phrase "plenty of empty space above for a title overlay" keeps the top of the frame clear, so a title added in editing doesn't fight the product for space.

How it compares

One 5-second 720p clip on each model:

What sets HappyHorse 1.1 apart: one price across all three endpoints, up to 9 reference images, and a wide choice of aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 21:9, 9:21).

API call

curl -X POST https://api.hiapi.ai/v1/tasks \
  -H "Authorization: Bearer $HIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.1/text-to-video",
    "input": {
      "prompt": "A neon-lit street after rain, reflections on the wet pavement, cyberpunk mood, slow sideways tracking shot",
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "duration": 5
    }
  }'

That is a 5-second 720p clip for $0.80. The three endpoints differ only in their inputs:

• Text-to-video: just prompt.
• Image-to-video: image_urls with one start frame (short side at least 300 px, up to 20 MB). prompt is optional. There is no aspect_ratio; the output follows the start frame.
• Reference-to-video: reference_image with 1–9 images (short side at least 400 px). Refer to them in the prompt as [Image 1], [Image 2], and so on, in order.

The call returns a taskId. Poll GET /v1/tasks/{taskId} for the result, and download output[0].url right away, since it is a temporary link.

FAQ

Does audio cost extra?

No. HappyHorse 1.1 pricing depends only on resolution and duration.

Why is my bill higher than expected?

Most likely you didn't set resolution. It defaults to 1080p at $0.21/s. Set 720p explicitly while you iterate, and you pay $0.16/s.

Are reference images charged on reference-to-video?

No. The number of reference images doesn't change the price.

Am I charged for failed tasks?

No. You are billed only for clips that generate successfully.

To try it, generate a clip on the HappyHorse 1.1 model page. Every model's price is on the pricing page.