Host DeepSeek-R1 on RunPod
DeepSeek-R1 needs 8x 80GB+ GPUs, and RunPod's current cheapest qualifying row is A100 PCIE at $11.12/hr.
RunPod rows that can host DeepSeek-R1
The cheapest tracked way to host DeepSeek-R1 on RunPod is A100 PCIE at $11.12/hr. The overall tracked market floor is $8.01/hr on Vast.ai, so RunPod is $3.11/hr above the current floor.
| GPU | VRAM | Per GPU | Estimated hourly | Estimated monthly | Updated |
|---|---|---|---|---|---|
| A100 PCIE | 80GB | $1.39/hr | $11.12/hr | $8,118/mo | Jun 21, 2026 |
| A100 SXM4 | 80GB | $1.49/hr | $11.92/hr | $8,702/mo | Jun 21, 2026 |
| H100 PCIE | 80GB | $2.89/hr | $23.12/hr | $16,878/mo | Jun 21, 2026 |
| H100 NVL | 94GB | $3.19/hr | $25.52/hr | $18,630/mo | Jun 21, 2026 |
| H100 SXM | 80GB | $3.29/hr | $26.32/hr | $19,214/mo | Jun 21, 2026 |
| H200 | 141GB | $4.39/hr | $35.12/hr | $25,638/mo | Jun 21, 2026 |
| B200 | 192GB | $5.89/hr | $47.12/hr | $34,398/mo | Jun 21, 2026 |
Why this setup does or does not fit
8x 80GB+ GPUs
8x 80GB GPUs or larger, plus fast interconnects. Long prompts, batching, and KV cache can require extra headroom.
Frontier, cluster-only
Potentially exceptional reasoning quality, but this is an engineering program more than a plug-in model choice.
DeepSeek 671B
This is no longer a single-box deployment problem; networking, scheduling, and batching dominate.
DeepSeek-R1 on RunPod FAQ
Can I host DeepSeek-R1 on RunPod?
The cheapest tracked way to host DeepSeek-R1 on RunPod is A100 PCIE at $11.12/hr.
What GPU memory does DeepSeek-R1 need?
Our baseline for DeepSeek-R1 is 8x 80GB+ GPUs. The practical recommendation is 8x 80GB GPUs or larger, plus fast interconnects.
Is RunPod the cheapest provider for DeepSeek-R1?
The overall tracked market floor is $8.01/hr on Vast.ai, so RunPod is $3.11/hr above the current floor.
How fresh is this RunPod DeepSeek-R1 cost page?
This page recalculates from the latest tracked on-demand rows. The freshest qualifying RunPod row shown here is from Jun 21, 2026.