LLM Opex

Models

MiniMax-M1-40k: GPU memory and hosting cost

Open weights · 456.09 billion parameters · Mixture of experts · 10,240,000-token context · licence apache-2.0

No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.

Run it yourself

It needs 1140.2 GB of GPU memory at bf16, the precision it ships in.

CloudCheapest instance that fitsGPUsAn hourA month, around the clock
Crusoemi300x.8x8 × MI300X 192 GB$27.60$20,148
OCIBM.GPU.MI300X.88 × MI300X 192 GB$48.00$35,040
AWS2 × p4de.24xlarge, joined by EFA8 × A100 80 GB in each$54.89$40,073
Azure2 × Standard_ND96amsr_A100_v4, joined by InfiniBand8 × A100 80 GB in each$65.54$47,844
Nebiusgpu-b200-sxm-a.8gpu-160vcpu-1792gb8 × B200 180 GB$68.00$49,640
Together AIhgx-b200.8gpu8 × B200 180 GB$74.32$54,254
Alibaba Cloud2 × ecs.gn8v-8x.16xlarge, joined by eRDMA8 × GPU H 96 GB in each$116.98$85,397
Google Cloud2 × a3-ultragpu-8g, joined by GPUDirect RDMA8 × H200 141 GB in each$169.61$123,818

Several servers: the model is sized across identical servers that hold it together, on instance types whose vendor documents a network between servers; the price is all of them. It is shown where no one server holds the model, or where it costs less than the one that does.

More from MiniMax

Similar size, open weights

List prices collected 21 November 2026, refreshed every three hours. No negotiated rates or taxes.