All models / Video / minimax/h3-max
minimax/h3-max
model id: minimax/h3-max/{host_id}
Text in → Video out
Hosts
Don’t know how to select a host? Check Provider selection.
| Host | 480p | 768p | 1440p-sr | 1440p | 2160p | 4k-sr |
|---|---|---|---|---|---|---|
| MiniMax | $0.05 / s | $0.08 / s | — | — | — | — |
| SandBase | $0.01 / s 80% off | $0.016 / s 80% off | — | — | — | — |
| Atlas Cloud | $0.0475 / s 5% off | $0.076 / s 5% off | $0.1425 / s | $0.076 / s | $0.076 / s | $0.1948 / s |
| Fal | $0.05 / s | $0.08 / s | — | — | — | — |
| TOAPIS | $0.05 / s | $0.08 / s | — | — | — | — |
0% additional markup beyond our 2% platform fee.
“% off” discounts shown above are compared to Fal.ai’s price.
Playground
Only one of these two tabs is sent — a model can't take both a start/end image and reference files in the same call.
Output
Nothing generated yet
# create
import requests
resp = requests.post(
"https://videorouter.sh/api/v1/videos",
headers={"Authorization": "Bearer llmr_sk_...", "Content-Type": "application/json"},
json={"model": "minimax/h3-max", "prompt": "A drone shot flying over snowy mountains", "duration_secs": 5},
)
job = resp.json()
# poll
status = requests.get(
f"https://videorouter.sh/api/v1/videos/{job['id']}",
headers={"Authorization": "Bearer llmr_sk_..."},
).json()
print(status["status"]) # pending -> in_progress -> completed