MiniMax H3 Max
MiniMax H3 Max for Video generation.
Explore MiniMax H3 Max for Video generation through the unified API. Supported interfaces and current availability are shown below.
- Video generation
Model details
- Context window
- 7K tokens
- Max output
- 1 tokens
- Input
- Text, images
- Output
- Video
- Capabilities
- Vision
- Interfaces
- OpenAI-style Video Generation
Pricing
Per second of generated video. The Inferray price is what you are charged — no gateway fee is added on top of it.
| Output | Price |
|---|---|
| 480p, with audio | $0.05 / second |
| 768p, with audio | $0.08 / second |
Why teams pick it
- MiniMax H3 Max for Video generation.
Call MiniMax H3 Max
MiniMax H3 Max answers on the API below — pick the one your code already speaks and just swap in your Inferray key.
/v1/videosOpenAI-style Video Generation · openai SDK or plain HTTP
curl https://api.inferray.com/v1/videos \
-H "Authorization: Bearer inferray_..." \
-H "Content-Type: application/json" \
--data-binary @- <<JSON
{
"model": "minimax-h3-max",
"prompt": "A quartz crystal on a workbench",
"seconds": ${VIDEO_SECONDS:?Set a supported duration for this model}
}
JSONMore from MiniMax
Questions about this model
- Is there a free tier for MiniMax H3 Max?
- No. You add credit and pay MiniMax H3 Max's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.
- Am I charged for failed requests?
- No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.
- Is MiniMax H3 Max included in Token Plans?
- No. MiniMax H3 Max is pay-as-you-go only; Token Plans cover the other text models in the catalog.
- Does MiniMax H3 Max support tool calling and vision?
- MiniMax H3 Max supports image input on Inferray. It does not support tool calling.
- Is it the real MiniMax H3 Max?
- Yes. A request for minimax-h3-max is answered by MiniMax H3 Max from MiniMax, billed at its published list price. Inferray never substitutes a different or smaller model.