Dedicated model · Available as managed deployment
MiniMax's open-weight video model: a 33B image-and-text-to-video generator for short clips with strong motion and prompt adherence. Available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only, as an OpenAI-compatible endpoint on hardware only you use, hosted in the EU.
Why MiniMax-H3
| Text or image to video | Start from a prompt or a still image and generate a short clip with coherent motion, the open counterpart to hosted video APIs. |
|---|---|
| Open weights, your hardware | Video generation on a system reserved for you: no per-clip vendor pricing, no content leaving the EU. |
| Licence reviewed | MiniMax-H3 ships under its own model licence; AxForge reviews it with you and deploys under it where it applies. |
Specifications
| Model | MiniMax-H3 by MiniMaxAI |
|---|---|
| Modalities | Text or image → video |
| Sizes | 33.1B |
| Released | 2026-07 |
| Popularity | 5.3M downloads / month on HuggingFace |
| Licence | Commercial licence needed (the model's own licence); AxForge handles the licence where one is required |
| Availability | Available as managed deployment, operated by AxForge on hardware reserved for you |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Region | Málaga, Spain (eu-es-1) |
| Pricing | Hardware from €0.85/hour, rental term: Hour, week, month or year. Managed service quoted per deployment. Request deployment and we confirm both in writing. |
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the model card in the catalogue and the official card on HuggingFace.
Deployment
| System | A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory), reserved for you |
|---|---|
| Commercial model | Hour, week, month or year. Hardware from €0.85/hour, managed service quoted per deployment |
| Endpoint | OpenAI-compatible /v1 on your own machine, only your traffic |
| Location | Hosted in the EU: Málaga, Spain (eu-es-1) |
| Data handling | Zero prompt retention, same policy as the serverless API |
The model is validated on AxForge hardware and deployed on your system. After deployment, your endpoint speaks the OpenAI API with the model name you receive with the deployment.
Data & privacy
Prompts and completions are processed in memory in the EU, not written to disk, not logged, not retained, and never used to train anything. We keep only request metadata (token counts, timestamps, status) for billing and operations. The full policy is at axforge.ai/privacy.
FAQ
Not on the serverless API. It is available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
A dedicated DGX Spark handles the 33B model for short clips; for higher throughput AxForge scopes a multi-GPU system with you.
Short clips of a few seconds at the model's native resolution; length, resolution and throughput are confirmed with the deployment.
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the official model card.
A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) rented by the hour, week, month or year, running MiniMax-H3 behind an OpenAI-compatible endpoint on your own machine, hosted in the EU with zero prompt retention.
Hardware from €0.85/hour, by the hour, week, month or year; the managed service is quoted per deployment. Request deployment and we confirm both in writing.
Explore