MiniMax H3

Video Generation
minimax/hailuo-3

MiniMax 新一代全模态视频生成模型,原生输出带同步音轨。支持文本、图片、视频、音频混合输入,可用首帧/尾帧锚定画面,或用参考图/参考视频/参考音频引导风格。4-15 秒任意整数时长,768P 与 2K 两档分辨率,7 种画幅(含自适应)。

Duration
4-15s
Audio
Supported
Released
2026-07-31
Generation Modes
t2vText to Videoi2vImage to Videov2vVideo to Video
Resolutions
768p2k
Aspect Ratios
21:916:94:31:13:49:16adaptive
Capabilities
Video Input
Available Providers
MiniMaxBedrock2
Supported Protocols
openai

Pricing

From $0.08/s
ResolutionModeAudioPrice / Second
768pAnyAny$0.08/s
2kAnyAny$0.13/s
All other combinations$0.13/s

Billed per second of generated video. Supported parameter combinations and prices are determined by the live API and may vary by model version.

Providers

MiniMax
Protocols
openai/v1/videos
Bedrock2
Protocols
openai/v1/videos

Code Examples

import time
import requests
BASE = "https://api.ofox.ai/v1/videos"
HEADERS = {"Authorization": "Bearer YOUR_OFOX_API_KEY"}
# Create the generation task
task = requests.post(BASE, headers=HEADERS, json={
"model": "minimax/hailuo-3",
"prompt": "A golden retriever running on the beach at sunset",
"duration": 4,
"resolution": "768p",
"generate_audio": True,
"provider": {"type": "minimax"},
# Or: "provider": {"type": "novita"}
}).json()
# Poll until the task reaches a terminal state
while True:
task = requests.get(f"{BASE}/{task['id']}", headers=HEADERS).json()
if task["status"] in ("completed", "failed", "cancelled", "expired"):
break
time.sleep(10)
# Prefer mirror_urls (persistent) then fall back to unsigned_urls (24h)
print((task.get("mirror_urls") or task.get("unsigned_urls") or [None])[0])

Frequently Asked Questions

MiniMax H3 on Ofox.ai costs from $0.08 per second of generated video. The exact rate depends on resolution, generation mode, and audio. Pay-as-you-go, no monthly fees.