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. Validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Why AxForge
| 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 — MiniMaxAI |
|---|---|
| Modalities | Text or image → video |
| Sizes | 33.1B |
| Licence | Commercial licence needed — the model's own licence; AxForge handles the licence where one is required |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge |
| Rental term | Hour, week, month or year |
| Hardware pricing | €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Full details, benchmarks and FAQ on the MiniMax-H3 page. Prices exclude VAT.
How it works
| 1 | Request deployment — describe your traffic, context needs and rental term. |
|---|---|
| 2 | You receive the configuration, hardware rental and managed-service price in writing before anything is billed. |
| 3 | AxForge deploys MiniMax-H3 on a dedicated DGX Spark reserved for you. |
| 4 | Point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | Adjust the term — hour, week, month or year — as your workload settles. |
Request deployment or sign in to start.
FAQ
Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated 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.
AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.
Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.