LLM Opex

Models

Hy4-preview: GPU memory and hosting cost

Open weights · 779.96 billion parameters · Mixture of experts · 1,048,576-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 1949.9 GB of GPU memory at bf16, the precision it ships in.

CloudCheapest instance that fitsGPUsAn hourA month, around the clock
OCIBM.GPU.MI355X.88 × MI355X 288 GB$68.80$50,224
Nebiusgpu-b300-sxm.8gpu-192vcpu-2768gb8 × B300 288 GB$76.00$55,480
AWS4 × p4de.24xlarge, joined by EFA8 × A100 80 GB in each$109.79$80,145
Azure4 × Standard_ND96amsr_A100_v4, joined by InfiniBand8 × A100 80 GB in each$131.08$95,688
Google Cloud2 × a3-ultragpu-8g, joined by GPUDirect RDMA8 × H200 141 GB in each$169.61$123,818
Alibaba Cloud3 × ecs.gn8v-8x.16xlarge, joined by eRDMA8 × GPU H 96 GB in each$175.47$128,095

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 Tencent

Similar size, open weights

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