MiniMax H3 Max API

MiniMax H3 Max is a text to video, image to video, reference to video and multi-angle video model by MiniMax, available on the Venice API as minimax-h3-max-text-to-video. It runs privately, with zero data retention.

MiniMax H3 Max API pricing

Model ID	Variant	Privacy	Price
`minimax-h3-max-text-to-video`	Text to video	Private	from $0.03 per second
`minimax-h3-max-image-to-video`	Image to video	Private	from $0.03 per second
`minimax-h3-max-reference-to-video`	Reference to video	Private	from $0.06 per second
`minimax-h3-max-multi-angle`	Multi-angle	Private	from $0.06 per second

Clip prices for minimax-h3-max-text-to-video with audio:

Duration	480p	768p	1080p
5s	$0.15	$0.24	$0.48
6s	$0.18	$0.29	$0.58
7s	$0.21	$0.34	$0.67
8s	$0.24	$0.38	$0.77
9s	$0.27	$0.43	$0.86
10s	$0.30	$0.48	$0.96
11s	$0.33	$0.53	$1.06
12s	$0.36	$0.58	$1.15
13s	$0.39	$0.62	$1.25
14s	$0.42	$0.67	$1.34
15s	$0.45	$0.72	$1.44

MiniMax H3 Max specifications

Spec	Value
Provider	MiniMax
Released	Aug 27, 2026
Privacy	Private
Modes	text to video, image to video, reference to video and multi-angle video
Resolutions	480p, 768p, 1080p
Durations	5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
Aspect ratios	16:9, 21:9, 4:3, 1:1, 3:4, 9:16
Audio	Always generated

How to use the MiniMax H3 Max API

Send requests to POST https://api.venice.ai/api/v1/video/queue with "model": "minimax-h3-max-text-to-video" and your API key.

# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/video/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-h3-max-text-to-video",
    "prompt": "Slow aerial drone shot over a misty mountain valley at golden hour",
    "duration": "5s",
    "resolution": "480P",
    "aspect_ratio": "16:9"
  }'

# 2. Poll until the MP4 is ready
curl https://api.venice.ai/api/v1/video/retrieve \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "minimax-h3-max-text-to-video", "queue_id": "<queue_id>" }' --output video.mp4

MiniMax H3 Max API FAQ

How much does the MiniMax H3 Max API cost?

From

0.03 to

0.19 per second of video, depending on resolution, duration and audio. A 5-second 768p clip with audio costs $0.24. Call POST /video/quote for the exact price before queueing. Prices are in USD and can be paid in DIEM at parity.

What is the MiniMax H3 Max model ID?

Use minimax-h3-max-text-to-video as the model parameter. Other variants: minimax-h3-max-image-to-video (Image to video), minimax-h3-max-reference-to-video (Reference to video), minimax-h3-max-multi-angle (Multi-angle).

Is the MiniMax H3 Max API private?

MiniMax H3 Max is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What resolutions and durations does MiniMax H3 Max support?

Resolutions: 480p, 768p, 1080p. Durations: 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s. Aspect ratios: 16:9, 21:9, 4:3, 1:1, 3:4, 9:16. Audio: always generated.

Which endpoint does the MiniMax H3 Max API use?

Queue a job with POST /video/queue, then poll /video/retrieve for the result.

Related models

Gemini Omni Flash 1.1 API: from $0.04 per second
Wan 3.0 Prime API: from $0.07 per second
Wan 3.0 Prime Pro API: from $0.33 per second
Wan 3.0 Pro API: from $0.24 per second

Explore

By modality