MiniMax / minimax/minimax-h3
MiniMax H3 - access through LLMTR
MiniMax H3 generates video from a text description and can take reference material in the same request: a first frame, a last frame, or a reference image. Output runs from 5 to 15 seconds at 2K and is priced per second. The first five reference images are free and each additional image is billed separately. It suits product reveals, character-consistent scenes, and animations that continue from an existing frame.
Technical specifications
| Canonical ID | minimax/minimax-h3 |
|---|---|
| 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 | INPUT_IMAGE | PER_IMAGE | $0.040000 |
| VIDEO_GENERATIONS | OUTPUT_VIDEO | PER_SECOND | $0.130000 |
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","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 Max minimax/minimax-h3-max