Loading prices…
Gaudi 2 rental prices
Intel · Gaudi · 96 GB HBM2e · OAM · 2022
2 providers · 2 configurations · prices as of Nov 10, 2026, 19:01 UTC
Lowest on-demand
$1.10per GPU·h · ≈ $803/month
at DenvrMedian on-demand
$1.16/GPU·h
across 2 providers
Lowest spot
—
interruptible
FP16/BF16 cost
$2.55/PFLOP·h
#38 of 76 GPUs for value
Providers
2
2 configurations
Price history
Daily Gaudi 2 prices per GPU-hour. The shaded period is reconstructed from public archives: the version history of SkyPilot's price catalogs, Internet Archive copies of providers' pricing pages and the open gpu-price-feed project (fewer providers than live data). After that, PetaPrice's own tracking.
Lowest on-demandMedian on-demand
Price by provider
Cheapest On-demand Gaudi 2 offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Thin vertical line = median across providers ($1.10).
Every provider we track
Pricing
Size
Host
Provider HQ
2 providers · 2 configurations
Sort
DenvrOn-demand🇨🇦 HQ in Canadavia Shadeformfrom · On-demandCheapest$1.10/GPU·hCheapest- 8× GPU · PCIe152 vCPU · 940 GB RAM · 27,000 GB disk$1.10 /GPU·h$8.80 /hOn-demand🇺🇸 US, Houston, TX● availableRent ↗
SesterceOn-demand🇫🇷 HQ in Francevia Sestercefrom · On-demand+10%$1.21/GPU·h+10%- 8× GPU · PCIe152 vCPU · 940 GB RAM · 27,000 GB disk$1.21 /GPU·h$9.68 /hOn-demandUSA-Houston-1● availableRent ↗
What can the Gaudi 2 run?
Memory for the weights plus one 32K-token sequence of context, how many GPUs hold it, and what that replica costs at the cheapest in-stock on-demand rate.
| Model | Params | Memory | GPUs | $/hr | $/mo |
|---|---|---|---|---|---|
gpt-oss-20b OpenAI · 20.9B | 20.9B · 3.6B active | 20 GiB | 1 | $1.10 at Denvr | $803 |
Gemma 3 27B Google · 27.4B | 27.4B | 28 GiB | 1 | $1.10 at Denvr | $803 |
Qwen3-32B Alibaba · 32.8B | 32.8B | 39 GiB | 1 | $1.10 at Denvr | $803 |
Llama 3.3 70B Instruct Meta · 70.6B | 70.6B | 76 GiB | 1 | $1.10 at Denvr | $803 |
gpt-oss-120b OpenAI · 117B | 117B · 5.1B active | 110 GiB | 2 | $2.20 at Denvr | $1,606 |
Qwen3-235B-A22B Alibaba · 235B | 235B · 22B active | 225 GiB | 4 | $4.40 at Denvr | $3,212 |
DeepSeek-R1 DeepSeek · 684B | 684B · 37B active | 640 GiB | 8 | $8.80 at Denvr | $6,424 |
Kimi K3 Moonshot AI · 2.78T | 2.78T · 104B active | 2.53 TiB | 32 | $35.20 at Denvr | $25,696 |
Assumes 90% of each GPU's memory is usable and rounds up to 1, 2, 4, 8… GPUs for tensor parallelism (up to 64). $/hr is the GPU count times the cheapest in-stock on-demand rate per GPU; check that the provider rents instances that large. Serving many requests at once needs more memory for context.
Alternatives to the Gaudi 2
GPUs with similar compute and memory, and their lowest on-demand price right now.
TPU v5p95 GB · 0.459 PF FP16$4.20/h$9.15/PFLOP·h
RTX PRO 6000 Blackwell Max-Q96 GB · 0.439 PF FP16$1.21/h$2.77/PFLOP·h- A100 SXM 80GB80 GB · 0.312 PF FP16$1.00/h$3.20/PFLOP·h
- A100 PCIe 80GB80 GB · 0.312 PF FP16$1.11/h$3.56/PFLOP·h
- L40S48 GB · 0.362 PF FP16$0.38/h$1.05/PFLOP·h
- RTX PRO 6000 Blackwell96 GB · 0.504 PF FP16$1.25/h$2.48/PFLOP·h
Gaudi 2 pricing questions
How much does it cost to rent an Gaudi 2?
On-demand Gaudi 2 prices start at $1.10 per GPU-hour (Denvr). The median across 2 providers is $1.16, and the most expensive is $1.21. Running one GPU around the clock costs about $803 per month at the lowest price.
How much compute do you get per dollar with the Gaudi 2?
At $1.10 per hour and 0.432 PF of dense FP16/BF16, the Gaudi 2 costs $2.55 per PFLOP-hour. That ranks 38 of 76 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
What are the Gaudi 2's key specs?
96 GB HBM2e with 2,450 GB/s of memory bandwidth, Gaudi architecture (2022), OAM form factor, 600 W. Dense peak: 0.432 PF FP16 / BF16, 0.865 PF FP8, 0.011 PF FP32.
How current are these prices?
Prices were collected on Nov 10, 2026, 19:01 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.