GPU model
AWS Inferentia2 (Inf2): specs, VRAM and rental prices
AWS Inferentia2 (Inf2): 32 GB of chip memory (HBM), rented from $0.76 per chip-hour on demand (AWS). Specs from AWS, prices as of Oct 29, 2026.
Inferentia2 is an AWS-designed chip for running trained models. AWS announced Inf2 instances as generally available on Apr 13, 2023. Each chip has 32 GB of HBM, and an instance holds 1 to 12 chips.
Prices were last checked Oct 29, 2026. A listing not re-checked for 7 days is greyed and left out of every lowest-price figure; after 14 days it is removed from the page.
AWS Inferentia2 (Inf2) specifications
| Specification | Inferentia2 (Inf2) | Source |
|---|---|---|
| Architecture | AWS Inferentia2, 2 NeuronCores per chip | aws.amazon.com |
| GPU memory | 32 GB | aws.amazon.com |
| Memory type | HBM | aws.amazon.com |
| Memory bandwidth | 816.7 GB/s (derived: 9.8 TB/s ÷ 12 chips) | aws.amazon.com |
| FP16 / BF16 peak | 190 TFLOPS | aws.amazon.com |
| FP8 peak | Not published | aws.amazon.com |
| Chip-to-chip interconnect | 192 GB/s NeuronLink | aws.amazon.com |
| Typical board power | Not published | aws.amazon.com |
AWS prints the 190 TFLOPS FP16 figure as “up to” per chip. Memory bandwidth is the 9.8 TB/s AWS prints for a 12-chip instance divided by 12. AWS publishes no chip power rating. Not published on the pages cited here: FP8 throughput; Chip power.
Sources: AWS Inf2 instances page · AWS Inferentia page · Inf2 general availability post (Apr 13, 2023). Every figure above is copied from these AWS pages; nothing is estimated.
Inferentia2 rental prices by provider
Lowest listed price by pricing type
| Pricing | $ per chip-hour | Provider | Checked |
|---|---|---|---|
| On-demand | $0.76 | AWS | Oct 29, 2026 |
On-demand price by provider
Each provider’s lowest fresh on-demand listing, $ per chip-hour.
Every listed Inferentia2 price
| Provider | Configuration | Pricing | $ per chip-hour | Region | Checked | Source |
|---|---|---|---|---|---|---|
| AWS | 1 chip per instance · 32 GB each inf2.xlarge |
On-demand | $0.76 Listed $0.76/hr per 1-chip instance |
us-east-1 | aws.amazon.com | |
| AWS | 12 chips per instance · 32 GB each inf2.48xlarge |
On-demand | $1.08 Listed $12.98/hr per 12-chip instance |
us-east-1 | aws.amazon.com |
Download: current prices (CSV) · current prices (JSON) · daily history (CSV) · price-change feed (RSS). Free to reuse with attribution under CC BY 4.0.
Compare the Inferentia2 with other GPUs
- Inferentia2 vs L4: specs side by side with the lowest listed rental price for each.
- Inferentia2 vs Trainium1: specs side by side with the lowest listed rental price for each.
Price history
The history chart appears once there are two daily snapshots of an on-demand price. Tracking began Oct 15, 2026; there is no on-demand snapshot for this GPU yet.
Embed this chart
<iframe src="https://datacentercensus.com/embed/gpu-prices/inferentia2" title="AWS Inferentia2 (Inf2) rental prices" width="100%" height="500" style="border:0;max-width:640px" loading="lazy"></iframe>
<p style="font:13px/1.4 system-ui,sans-serif;margin:6px 0 0">Source: <a href="https://datacentercensus.com/gpu-prices/inferentia2">Data Center Census</a></p>
<script>addEventListener("message",function(e){if(e.origin==="https://datacentercensus.com"&&e.data&&e.data.dcc){document.querySelectorAll('iframe[src^="https://datacentercensus.com/embed/"]').forEach(function(f){if(f.contentWindow===e.source)f.style.height=e.data.h+"px"})}})</script>Free with the credit line. Preview the embed.
How these prices are collected
- What counts
- Only prices a provider publishes on a public pricing page or in its public price list, opened by the Census on the day shown. A marketplace is listed under the same rule as every other provider: it must publish per-GPU-hour prices publicly, with no login, and its rows are shown with the type Marketplace. Quotes and “contact sales” rows are not listed, and neither are purchase prices.
- $ per GPU-hour
- The listed price per GPU-hour. Where a provider lists a price per instance, the Census divides it by the GPUs in that instance and shows the original figure under it. Nothing else is converted or estimated. Google TPUs and AWS Trainium and Inferentia chips are priced per chip-hour on the same terms, with “chip” in place of “GPU”.
- Pricing types
- On-demand, spot (including tiers a provider calls preemptible or low-priority), reserved with the term the provider states, and marketplace. Reserved rows without a stated term are not listed. A marketplace row is the lowest per-GPU-hour price its public page shows for that GPU, which comes from third-party hosts and changes often. Marketplace rows are a separate type: they appear in the table, filters, downloads and feeds, but never in the “lowest on-demand” or “lowest spot” figures.
- Variants
- SXM, PCIe, NVL and similar versions are kept separate when the provider names them. A provider that does not name the variant is shown without one.
- Freshness
- Every listing carries the date it was last confirmed, and the daily run re-opens each one. If a listing goes 7 days without a re-check it stays on the page greyed, labelled with the date it was last confirmed, and drops out of the “lowest” figures and the calculator’s default results. At 14 days without a re-check it is taken off the site; the daily history still holds it.
- History
- Each daily run saves a snapshot, so the model pages can chart the lowest listed on-demand price over time and the change log can show what moved. History began Oct 15, 2026.
- Differences between providers
- Listed prices are not like for like: regions, minimum instance sizes, networking, storage, commitments and availability differ and are not priced here. Check the provider before relying on a figure.
Providers checked but not listed
- Vast.ai: Its pricing page loads live "from" prices from a public JSON file whose terms allow display and citation with attribution but require a data license for bulk collection, redistribution or use in any index, benchmark or derivative product. The Census republishes prices as open data, so it does not list Vast.ai without that license.
- Voltage Park: Its pricing pages say "Contact for pricing" for every GPU; one homepage line says "Starting at $1.99/hr" without a GPU model or unit.
Inferentia2: common questions
How much VRAM does the Inferentia2 have?
AWS lists 32 GB of GPU memory for the AWS Inferentia2 (Inf2), which is HBM, with memory bandwidth of 816.7 GB/s (derived: 9.8 TB/s ÷ 12 chips). The specification table on this page shows each figure with the page it came from.
How much does it cost to rent an Inferentia2 per hour?
The lowest listed on-demand price among listings checked in the last 7 days is $0.76 per chip-hour at AWS, checked Oct 29, 2026. 2 fresh listings from 1 providers are shown in the table above, including spot, reserved and marketplace prices.
Which providers list Inferentia2 prices?
AWS.
Which architecture is the Inferentia2 built on, and when was it announced?
The AWS Inferentia2 (Inf2) uses the AWS Inferentia2 architecture and was announced or launched in 2023, according to the AWS page cited in the specifications.
Related: All GPU prices · GPU comparisons · Rental cost calculator · H100 · H200 · B200 · B300 · GB200 NVL72 · GB300 NVL72 · A100 · L40S · RTX PRO 6000 · L4 · T4 · MI300X · MI325X · MI355X · Trainium1 · Trainium2 · Trainium3 · TPU v5e · TPU v5p · TPU v6e · Ironwood · MI450 · Vera Rubin · Rubin CPX · Rubin Ultra
Cite this page
Last updated Oct 29, 2026. Figures may change as records are updated — include the date you retrieved them.
| APA | Data Center Census. (2026). AWS Inferentia2 (Inf2) specs and rental prices. Retrieved from https://datacentercensus.com/gpu-prices/inferentia2 |
|---|---|
| MLA | “AWS Inferentia2 (Inf2) specs and rental prices.” Data Center Census, Oct 29, 2026, https://datacentercensus.com/gpu-prices/inferentia2. |
| Link | https://datacentercensus.com/gpu-prices/inferentia2 |
Republishing a figure or table? Attribute it to Data Center Census with a link to this page. The underlying data is downloadable as JSON and CSV; the press kit has standing figures and contact details.