Skip to content
GPU Finder

Inferentia2 Cloud GPU Pricing

Compare Inferentia2 prices across 1 cloud providers. On-demand from $0.76/hr.

Providers:1
Price range:$0.76 — $19.47/hr
Spot price:from $0.08/hr
Instances:46
Updated:

Inferentia2 market snapshot

verified

No Inferentia2 is confirmed in stock across tracked providers at the moment.

near its 6-month lowat $0.76/hr the Inferentia2 floor price is near its 6-month low — 6-month range $0.76–$0.76/hr.

Bottom line: a relatively good time to rent — the floor price is near its 6-month low.

30-day reliability depth

GPU Finder does not treat availability as a static yes/no flag. For Inferentia2, current stock badges are paired with a 30-day reliability score computed from AvailabilityRecord history, measuring how much covered time each tracked row was reported available.

0
scored rows with enough history
0%
of visible rows have a 30-day score
deepest covered window on this page

This page has live pricing and current stock rows, but not enough retained availability history yet to publish 30-day reliability percentages.

Caveat: scores stay hidden until a row has at least 48covered hours, and some provider APIs expose coarse capacity levels instead of exact stock counts. Use the score as historical depth beside current availability, not as a guarantee that a GPU will still be allocatable when you click through.

Price History & Comparison

Loading chart...

Spot pricing decision guide

Treat spot as a risk-adjusted capacity decision, not just a cheaper number.

Sparse spot history
On-demand floor
$0.76

per GPU-hour

Spot floor
$0.08

90% below on-demand floor

30-day trend
falling

fake/equal spot rows suppressed

Volatility
volatile

median hidden until ≥3 rows across ≥2 providers

Cheapest trusted spot capacity is on AWS; 0 providers currently report spot-adjacent stock.

30-day reliability context is still sparse for the trusted spot rows on this GPU. See the 30-day reliability depth module for the broader availability history.

There is a valid spot or interruptible row, but not enough trusted history to overstate the signal.

Good fit: checkpointed batch jobs, flexible training, and experiments that can restart. Avoid for production serving, deadline-bound runs, or jobs that cannot tolerate eviction.

Source caveat: Runpod exposes explicit spot fields; Vast is labeled interruptible/bid-floor. Lambda is treated as on-demand-only unless a verified spot field is added.

Pricing by Provider

ProviderInstance TypeGPUsOn-DemandSpot / interruptibleVisit
AWSinf2.xlarge1
$0.76
$0.16
Visit
AWSinf2.xlarge1
$0.76
$0.08
Visit
AWSinf2.xlarge1
$0.76
$0.13
Visit
AWSinf2.xlarge1
$0.83
$0.08
Visit
AWSinf2.xlarge1
$0.91
$0.23
Visit
AWSinf2.xlarge1
$0.95
$0.26
Visit
AWSinf2.xlarge1
$0.99
N/AVisit
AWSinf2.xlarge1
$0.99
$0.26
Visit
AWSinf2.xlarge1
$1.06
$0.22
Visit
AWSinf2.xlarge1
$1.06
$0.17
Visit
AWSinf2.xlarge1
$1.14
N/AVisit
AWSinf2.xlarge1
$1.14
$0.15
Visit
AWSinf2.8xlarge1
$1.97
$0.49
Visit
AWSinf2.8xlarge1
$1.97
$0.33
Visit
AWSinf2.8xlarge1
$1.97
$0.68
Visit
AWSinf2.8xlarge1
$2.16
$0.22
Visit
AWSinf2.8xlarge1
$2.46
$0.84
Visit
AWSinf2.8xlarge1
$2.56
N/AVisit
AWSinf2.8xlarge1
$2.56
$0.44
Visit
AWSinf2.8xlarge1
$2.75
$0.46
Visit

Get notified when Inferentia2 drops in price or reliability changes

One email per change, max once a day. We send a confirmation link first; one-click unsubscribe in every email.

Available From