MiniMax prices H3, the model the community calls Hailuo 3, per second of output: $0.08 at 768P on its own platform, with the first five reference images free. Replicate passes that list price through; fal lists $0.06 at 768p and Kie.ai $0.04.
On APIMODELS there are two ways to run it. minimax-h3 is the full tier with native 2K and reference video; its per-second price is on the model page. minimax-h3-lite runs the H3 model at 768P for $0.02 per second and at 480P for $0.01, the lowest price for H3 we found anywhere, with one real trade-off described below.
USD per second of output, checked 2026-09-30. Promotions are marked and not treated as list prices.
| Provider | 480P | 768P | Notes |
|---|---|---|---|
| MiniMax official | — | $0.08 | 5 reference images free |
| Replicate | — | $0.08 | 4–15 s |
| EvoLink | — | $0.076 | official × 0.95 |
| fal | $0.05 | $0.06 | list price |
| Kie.ai | — | $0.04 | half of official |
| APIMODELS minimax-h3-lite | $0.01 | $0.02 | draft tier, 1–15 s |
H3 Lite is affordable because it is a draft tier, and it behaves like one on the hardest shots. On animation, talking heads, slow camera moves, product turns and subtle expressions it holds up; on live-action footage with fighting, running, dancing or fast camera work, faces and limbs deform, and rewriting the prompt does not fix it. It also stops at 768P, takes no reference video, and a clip takes several minutes. Over the last 30 days of external traffic it served 661 calls at a 99.2% success rate, so it is dependable for what it is.
A practical split: iterate on prompts with H3 Lite at 480P for a cent a second, then render the chosen shot on minimax-h3 or at MiniMax directly when it needs 2K or large movement.
cURL
curl -X POST https://api.apimodels.app/v1/video/generations \
-H "Authorization: Bearer $APIMODELS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-lite",
"prompt": "A cartoon fox waves at the camera, slow push-in, warm light",
"resolution": "480p",
"duration": 6
}'Python
import requests
H = {"Authorization": "Bearer YOUR_APIMODELS_KEY"}
r = requests.post("https://api.apimodels.app/v1/video/generations", headers=H, json={
"model": "minimax-h3", # full tier: 2K and reference video
"prompt": "The dancer from video 1 performs the same move on a rooftop at sunset",
"reference_video_urls": ["https://example.com/move.mp4"],
"resolution": "2k", "duration": 8,
})
print(r.json()) # poll GET /v1/video/generations?task_id=...At 768P, H3 is $0.08 per second on MiniMax’s own platform, $0.06 on fal and $0.04 on Kie.ai. On APIMODELS, minimax-h3-lite runs H3 at $0.02 per second at 768P and $0.01 at 480P. The full minimax-h3 tier, with native 2K and reference video, is priced on its model page.
Yes. H3 is MiniMax’s model name; Hailuo is the consumer app, and "Hailuo 3" is what most people search for. OpenRouter lists it as hailuo-3.
For final live-action shots with large or fast movement, for anything above 768P, and for jobs that need a reference video. Use minimax-h3 or MiniMax directly for those.
