Hailuo H3
Hailuo H3 (MiniMax-H3) text-to-video and image-to-video. Output is always 2K.
Pass image_url for a first frame, optionally with image_end_url for a last frame. For reference-driven generation use the hailuo_h3_refs model instead — first/last frames and reference assets are mutually exclusive.
Pricing: billed per second — 2K is 7.15 tokens/s ($0.143/s). 768P (4.95 tokens/s) is coming soon.
Returns an img_uuid; poll GET /api/v1/jobs/detail (or use custom_callback_url) to get the generated video.
Headers
Body
Model name. Must be hailuo_h3.
hailuo_h3 Text prompt describing the video. Required. Max 7000 characters.
7000Optional first-frame image. JPG/PNG/WEBP/HEIC/HEIF, ≤30MB, 256–5760px, aspect ratio 0.4–2.5. When provided, runs image-to-video and the output ratio follows the image.
Optional last-frame image. Must be used together with image_url.
Output resolution. Only 2K is available today; 768P is coming soon.
2K Video duration in seconds. Any integer from 4 to 15.
4 <= x <= 15Aspect ratio. Text-to-video only; ignored when image_url is provided (the ratio then follows the input image).
21:9, 16:9, 4:3, 1:1, 3:4, 9:16 Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.
"https://your-server.com/goenhance/callback"
