hailuo3 (2K)
hailuo3 (2K)10 credits per second, plus 2 credits per reference image; reference video billed at the same per-second rate as output (capped at 15 seconds)
hailuo3 (768P)
Source checked: 2026-09-13 · Provider endpoint, not an independently benchmarked model.
These are source observations, not interchangeable quotes. Token, compute-time, output-duration and per-request prices cannot be compared by the number alone. Input charges and optional features may add to the total.
10 credits per second, plus 2 credits per reference image; reference video billed at the same per-second rate as output (capped at 15 seconds) · USD $0.01 per credit. Professional/HDR output and reference-input surcharges may apply.
| credit_value_usd | 0.01 |
|---|
Unlisted settings, region availability, deposits, taxes and commercial terms remain unverified. Confirm the exact endpoint before purchase.
Fast, Pro, editing and audio variants remain separate. Match the exact configuration before comparing costs.
Source-listed endpoints and pricing conditions. Variants are not unique base models; account quotes do not enter cheapest-price rankings.
Counts describe collected endpoints, not unique models or a guarantee of complete coverage. Price evidence may be a numeric rate or source billing text. Providers with no published endpoints are still awaiting collection.
4 endpoints · 1/1
Variants listed separately. Open a model to check units and conditions.
hailuo3 (2K)15 credits per second, plus 2 credits per reference image; reference video billed at the same per-second rate as output (capped at 15 seconds)
hailuo3 (768P)10 credits per second, plus 2 credits per reference image; reference video billed at the same per-second rate as output (capped at 15 seconds)
minimax/hailuo-3MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text
minimax/hailuo-3-maxMiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai. Derived through additional training from MiniMax H3, it is designed for faster text-to-video and image-to-video g