Model provider cost

Host DeepSeek-R1 on Azure

DeepSeek-R1 needs 8x 80GB+ GPUs, and Azure's current cheapest qualifying row is A100 PCIE at $29.38/hr.

8x 80GB+ GPUs 671B params Frontier, cluster-only MIT
Cheapest on this provider
$29.38/hr
A100 PCIE
Monthly estimate
$21,450/mo
730 hours at the current median
VRAM baseline
80GB
8x 80GB+ GPUs
Qualifying rows
4
Updated Jun 21, 2026

Azure rows that can host DeepSeek-R1

The cheapest tracked way to host DeepSeek-R1 on Azure is A100 PCIE at $29.38/hr. The overall tracked market floor is $8.01/hr on Vast.ai, so Azure is $21.37/hr above the current floor.

GPU VRAM Per GPU Estimated hourly Estimated monthly Updated
A100 PCIE 80GB $3.67/hr $29.38/hr $21,450/mo Jun 21, 2026
A100 SXM4 80GB $4.10/hr $32.77/hr $23,922/mo Jun 21, 2026
H100 NVL 94GB $6.98/hr $55.84/hr $40,763/mo Jun 21, 2026
H100 SXM 80GB $12.29/hr $98.32/hr $71,774/mo Jun 21, 2026

Why this setup does or does not fit

VRAM floor

8x 80GB+ GPUs

8x 80GB GPUs or larger, plus fast interconnects. Long prompts, batching, and KV cache can require extra headroom.

Model quality

Frontier, cluster-only

Potentially exceptional reasoning quality, but this is an engineering program more than a plug-in model choice.

Operational note

DeepSeek 671B

This is no longer a single-box deployment problem; networking, scheduling, and batching dominate.

DeepSeek-R1 on Azure FAQ

Can I host DeepSeek-R1 on Azure?

The cheapest tracked way to host DeepSeek-R1 on Azure is A100 PCIE at $29.38/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 Azure the cheapest provider for DeepSeek-R1?

The overall tracked market floor is $8.01/hr on Vast.ai, so Azure is $21.37/hr above the current floor.

How fresh is this Azure DeepSeek-R1 cost page?

This page recalculates from the latest tracked on-demand rows. The freshest qualifying Azure row shown here is from Jun 21, 2026.

Compare this setup