LLM Opex Every way to run an LLM, every cloud

Models

Seed-OSS-36B-Instruct: GPU memory and hosting cost

Open weights · 36.15 billion parameters · 524,288-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 90.4 GB of GPU memory at bf16, the precision it ships in.

CloudCheapest instance that fitsGPUsAn hourA month, around the clock
Google Cloudg4-standard-481 × RTX PRO 6000 96 GB$4.50$3,285
AzureStandard_NC144ds_xl_RTXPRO6000BSE_v61 × RTX PRO 6000 96 GB$6.38$4,657
Alibaba Cloudecs.gn8v.4xlarge1 × GPU H 96 GB$7.31$5,337
AWSp4d.24xlarge8 × A100 40 GB$21.96$16,029

More from Other

Similar size, open weights

List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.