RentGPU RentGPU
Trouver un GPU →
by MiniMax

MiniMax: MiniMax M3.

multimodal open weights 1M ctx
Cheapest input
$0.28/M
on DeepInfra
Cheapest output
$1.1/M
on DeepInfra
Hosted equiv.
~$0.4/hr
@ 100 tok/s on DeepInfra

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.28 $1.1 Launch ↗
Together AI hosted inference $0.3 $1.2 Launch ↗
OpenRouter api aggregator $0.3 $1.2 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run MiniMax: MiniMax M3?
MiniMax: MiniMax M3 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access MiniMax: MiniMax M3?
MiniMax: MiniMax M3 is available via Fireworks AI, Together AI, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run MiniMax: MiniMax M3?
API pricing starts at $0.3/M input tokens and $1.2/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is MiniMax: MiniMax M3 open-source or proprietary?
MiniMax: MiniMax M3 is open-weight under the license. You can download and self-host it.