RentGPU RentGPU
Encontrar GPU →
by MiniMax

MiniMax: MiniMax M2.5.

text open weights 205K ctx
Cheapest input
$0.15/M
on MiniMax Platform
Cheapest output
$1.15/M
on MiniMax Platform
Fastest
81 tok/s
on OpenRouter
Hosted equiv.
~$0.41/hr
@ 100 tok/s on MiniMax Platform

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
MiniMax Platform api direct $0.15 $1.15 Launch ↗
DeepInfra hosted inference $0.15 $1.15 Launch ↗
OpenRouter api aggregator $0.15 $1.15 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 80.7 — 6197 ms
FAQ

Frequently asked.

How do I run MiniMax: MiniMax M2.5?
MiniMax: MiniMax M2.5 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 M2.5?
MiniMax: MiniMax M2.5 is available via MiniMax Platform, DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run MiniMax: MiniMax M2.5?
API pricing starts at $0.15/M input tokens and $1.15/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is MiniMax: MiniMax M2.5 open-source or proprietary?
MiniMax: MiniMax M2.5 is open-weight under the license. You can download and self-host it.