MiniMax / minimax/minimax-h3-max
MiniMax H3 Max - access through LLMTR
MiniMax H3 Max is a fast video variant released jointly by MiniMax and fal.ai and post-trained on H3. It supports text-to-video and image-to-video modes, taking a first frame, a last frame, or both. Output runs from 5 to 15 seconds and is priced per second at 480P and 768P. Reference images beyond a first or last frame are not supported on this row; use the MiniMax H3 row for those.
Technical specifications
| Canonical ID | minimax/minimax-h3-max |
|---|---|
| Provider | MiniMax |
| Context window | Not available |
| Operations | VIDEO_GENERATIONS |
| Modalities | text, image, video |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| VIDEO_GENERATIONS | OUTPUT_VIDEO | PER_SECOND | $0.050000 |
| VIDEO_GENERATIONS | OUTPUT_VIDEO | PER_SECOND | $0.080000 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions \
-H "Authorization: Bearer llmtr-your_key" \
-H "Content-Type: application/json" \
-d '{"model":"minimax/minimax-h3-max","messages":[{"role":"user","content":"Hello"}]}'Related models
- MiniMax M3 minimax/minimax-m3
- MiniMax M3 (Free) minimax/minimax-m3-free
- MiniMax M2.7 minimax/minimax-m2.7
- MiniMax M2.7 Highspeed minimax/minimax-m2.7-highspeed
- MiniMax M2.7 (Free) minimax/minimax-m2.7-free
- MiniMax M2.5 minimax/minimax-m2.5
- MiniMax M2.5 Highspeed minimax/minimax-m2.5-highspeed
- MiniMax H3 minimax/minimax-h3