Skip to main content

MiniMax H3 API

MiniMax H3 is a text to video, image to video and reference to video model by MiniMax, available on the Venice API as minimax-h3-text-to-video. Requests are anonymized, so the provider never sees your identity.

MiniMax H3 API pricing

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

MiniMax H3 specifications

How to use the MiniMax H3 API

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

MiniMax H3 API FAQ

How much does the MiniMax H3 API cost?

From 0.10to0.10 to 0.16 per second of video, depending on resolution, duration and audio. A 5-second 768p clip with audio costs $0.50. 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 model ID?

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

Is the MiniMax H3 API private?

MiniMax H3 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

What resolutions and durations does MiniMax H3 support?

Resolutions: 768p, 2K. 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 API use?

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

Related models