MiniMax H3 Max
MiniMax H3 Max is the premium tier of the H3 family, generating 5 to 15 second clips with native synchronised audio at 480P or 768P, billed per second of output. Steer a shot with a text prompt, a first frame, a first and last frame pair, or up to 9 reference images for character and product consistency; image inputs cost nothing extra. Reference clips and reference audio are not available on it, so use Seedance 2.5 for those. Pick base H3 when you need 2K, and Max when fidelity at 768P is what matters.
Pricing
Input
$3.00 / video
Output
—
Pay only for what you use. No subscriptions, no monthly minimum.
Specs
- Context
- —
- Max output
- 15s
- Latency
- Slow
- Category
- Video
Constraints & limits
Duration
Up to 30s (linear pricing)
Base price
For 5s clip
Auto-refund
On generation failure
The gateway auto-clamps requests to the model's limits where possible.
Quick start
Video generation is async, the sample submits then polls until done or failed (auto-refund on failure).
import os, time, requests
API = "https://api.thalam.ai/v1"
headers = {"Authorization": f"Bearer {os.environ['THALAM_KEY']}"}
# 1. Submit
submit = requests.post(
f"{API}/videos/generations",
headers=headers,
json={
"model": "minimax/minimax-h3-max",
"prompt": "A drone shot over a desert at golden hour.",
"duration": 5,
},
)
task_id = submit.json()["task_id"]
# 2. Poll until done (or auto-refund on failure)
while True:
poll = requests.get(f"{API}/videos/tasks/{task_id}", headers=headers).json()
status = poll["task"]["status"]
if status == "TASK_STATUS_SUCCEED":
print(poll["videos"][0]["video_url"])
break
if status == "TASK_STATUS_FAILED":
print(f"Failed: {poll['task'].get('reason', 'unknown')}")
break
time.sleep(5)Similar models
MiniMax H3
MiniMax's newest video model with native audio. 4 to 15 second clips at 768P or 2K, priced per second.
Kling V3.0 Pro I2V
Kling V3.0 Pro: image-to-video. Animate stills with the same engine as T2V.