MiniMax H3 Max is an August 2026 variant of MiniMax H3 offered at 480P or 768P. It generates 5-15 second clips from a prompt, optionally anchored by a first frame, a last frame or both. There are seven aspect ratio options, from 21:9 to 9:16, plus adaptive. The request is simpler than on H3: no reference clips or audio tracks, only a prompt and frames. The default is a 6-second clip at 768P, with durations adjustable up to 15 seconds.
Best for
- Animating a start image into a short social clip
- Transitions between two keyframes
- Low-resolution previews before a 2K render
- Plain text-to-video at modest resolution
Prompting tips
- Use first and last frames to lock the composition at both ends, then describe the motion in between.
- The minimum length is 5 seconds; set
durationanywhere up to 15. - Focus the prompt on movement and camera, since the frames already define the look.
- Move to MiniMax H3 when you need 2K or reference media.
FAQ
What does MiniMax H3 Max cost?
It is billed at from $0.104 per second. Failed generations are not charged, and the estimate is shown before the job runs.
What resolutions does MiniMax H3 Max support?
480P and 768P, with 768P as the default.
Can MiniMax H3 Max use a first and last frame?
Yes. Send a start image, an end image or both, and describe the motion that connects them.
How to call MiniMax H3 Max via API
curl https://jantaris.com/v1/generate?wait=60 \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-max",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9",
"resolution": "768P",
"duration": 6
}
}'import os, time, requests
API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}
task = requests.post(f"{API}/generate", headers=H, json={
"model": "minimax-h3-max",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9",
"resolution": "768P",
"duration": 6
}
}).json()
while task["status"] in ("queued", "running"):
time.sleep(3)
task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()
print(task["status"], task["cost"], [o["url"] for o in task["output"]])const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };
let task = await (await fetch(`${API}/generate`, {
method: "POST",
headers,
body: JSON.stringify({
"model": "minimax-h3-max",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9",
"resolution": "768P",
"duration": 6
}
}),
})).json();
while (task.status === "queued" || task.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));Parameters
| Parameter | Type | Allowed | Default |
|---|---|---|---|
prompt * | string | ||
aspect_ratio | string | 21:9 16:9 4:3 1:1 3:4 9:16 adaptive | 16:9 |
resolution | string | 480P 768P | 768P |
duration | integer | 5-15 | 6 |
image_url | string | ||
end_image_url | string |
The same schema is available from GET /v1/models/minimax-h3-max.
