Overview

AMD logo AMD MI210

Single-die CDNA 2 data center GPU for HPC and double-precision workloads.

Mid-Range Datacenter

AMD logo AMD MI455X

AMD's CDNA 5 flagship for frontier-scale training and inference in Helios rack systems.

High Performance Datacenter

Memory per GPU

6.8x more on MI455X
AMD logo MI210
64 GB HBM2e
AMD logo MI455X
432 GB HBM4

Memory bandwidth

14x higher on MI455X
AMD logo MI210
1,638 GB/s
AMD logo MI455X
23,300 GB/s

GPU interconnect

12x higher on MI455X
AMD logo MI210
Infinity Fabric 300 GB/s
AMD logo MI455X
Infinity Fabric 3,600 GB/s

Peak performance (FP16)

28x higher on MI455X
AMD logo MI210
181 TFLOPS
AMD logo MI455X
5,030 TFLOPS

Vendor peak figures. Sparsity and tensor-core conventions differ between vendors.

Precision support

AMD logo MI210
FP16 BF16 FP32 FP64 INT4 INT8
AMD logo MI455X
FP4 FP6 FP8 FP16 BF16 FP32 INT8

Highlighted formats are supported by only one of the two.

Architecture

AMD logo MI210
CDNA2
AMD logo MI455X
CDNA 5

Released

4 years newer on MI455X
AMD logo MI210
Q1 2022
AMD logo MI455X
Q3 2026

Price comparison

Cheapest on-demand

AMD logo MI210
Not sold on demand
AMD logo MI455X
--

Typical rate

AMD logo MI210
$1.04 / GPU / hr
AMD logo MI455X
--

Median across providers, one vote each, so a large catalog does not outweigh a small one.

Full price range

AMD logo MI210
$0.87 - $1.28 / GPU / hr
AMD logo MI455X
--

Lowest to highest listing per GPU-hour, across on-demand, spot, reserved and custom.

Providers listing it

4 more on MI455X
AMD logo MI210
1
AMD logo MI455X
5

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.

Offers and availability

How this list works

Order

Each provider appears once per GPU. We pick the one configuration that speaks for that provider, and rank on it in this order:

  1. Availability: in stock, then waitlist, then not reported, then out of stock. A price you can act on outranks a cheaper one you cannot.
  2. Billing type: on-demand first, then reserved, then spot, then quote-only. On-demand leads because it is the only rate you can hold without committing to anything.
  3. Price: the lowest per-GPU hourly rate the provider lists, converted to USD.

The configuration we pick is chosen the same way, availability before billing before price. The rest of that provider's configurations are on the GPU's own page.

Ties sort alphabetically. Reserved rates are not separated by term length, so a three-year commitment can sit above a one-month one: the label beneath each price says which you are looking at. Providers who publish no rate are listed last within their group.

Transparency and funding

  • Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
  • Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
  • Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Similar GPUs

Other comparisons in the same class:

View all GPUs

Our data for AMD MI210 was last updated on Aug. 24, 2026, and for AMD MI455X on Aug. 21, 2026.