H100 GPU rental price
NVIDIA H100 · 80 GB VRAM. Live per-GPU pricing aggregated across 7 providers and 7 regions.
The H100 (80GB HBM3) currently rents from $1.99 per GPU per hour on Aquanode, across 7 providers.
The cheapest H100 offer right now (RunPod, $1.99/GPU/hr) is about 38% below the market median of $3.19/GPU/hr.
H100 specs
H100 full specs
| Architecture | NVIDIA, launched 2022 |
| VRAM | 80GB HBM3 |
| Memory bandwidth | 3.35 TB/s |
| FP16 / BF16 tensor throughput | 989 TFLOPS (peak, dense) |
| FP8 tensor throughput | 1,979 TFLOPS (peak, dense) |
| Interconnect | NVLink 4, 900 GB/s bidirectional |
| TDP | Up to 700W (configurable) |
| Form factor | SXM |
Specs sourced from the vendor's public datasheet. See the source. For the full architecture story, see the H100 complete guide.
What fits in 80GB HBM3 of VRAM
| Model | Precision | Fits? |
|---|---|---|
| Llama 3 8B / similar 7-9B models | FP16 | ~16GB. Fits with plenty of headroom for a large KV cache. |
| Llama 3.1 70B | FP16 | ~140GB weights alone. Does not fit on one 80GB card; needs 2 GPUs. |
| Llama 3.1 70B | INT4 (AWQ/GPTQ) | ~35-40GB. Fits comfortably on a single card, room for context. |
| Mixtral 8x7B | FP16 | ~94GB weights. Just over the 80GB limit; INT4 (~24GB) fits easily. |
Approximate, based on published parameter counts and standard bytes-per-parameter rules of thumb (FP16 ≈ 2 bytes/param, INT4 ≈ 0.5-0.6 bytes/param). Real footprint also depends on KV-cache size and framework overhead.
Good for
The default choice for training and fine-tuning models up to the ~30-40B range on a single card, and for high-throughput FP8 inference. Its 1,979 TFLOPS dense FP8 figure and 900 GB/s NVLink make 8-GPU pretraining and serving runs practical. It's also the card with the deepest cloud/on-prem availability, so it's usually the cheapest per-FLOP hour to actually get.
Not good for
80GB isn't enough to hold a 70B-class model in FP16 on one card, and it has no native FP4 support, so it can't run the newest FP4-native model formats at full precision the way Blackwell parts can.
Get notified when the price drops
GPU supply moves hourly. Tell us what you're waiting for and we'll email you when a matching offer appears across any provider we track.
How this price is calculated
All prices on this page are normalized to a per-GPU hourly rate using each offer's authoritative GPU count, so that raw price is divided by the number of GPUs it actually covers; Akash reports its price as already per-GPU, so it is used as-listed. An offer with a missing, zero, or invalid GPU count is excluded entirely rather than published at a guessed rate.
No offers were excluded from this snapshot for a missing or invalid price. No offers were dropped as price outliers in this snapshot.
Only the cheapest qualifying offer per provider is shown in the table above. This page regenerates at most once per hour.
Frequently asked questions
How much does it cost to rent a H100?
Live H100 rental prices currently range from $1.99 to $3.49 per GPU per hour across 7 providers, with a median of $3.19 per GPU per hour.
Which provider has the cheapest H100?
RunPod currently offers the lowest H100 rate on Aquanode's marketplace at $1.99 per GPU per hour in Unknown.
How is the H100 price calculated?
All prices are normalized to a per-GPU hourly rate using each offer's authoritative GPU count, which the raw price is divided by; Akash reports its price as already per-GPU. Offers whose price can't be safely normalized, or whose rate is an extreme outlier against the rest of the market, are excluded.
How much does an H100 cost per hour?
Live H100 rental rates on Aquanode currently range from $1.99 to $3.49 per GPU per hour, with a median of $3.19/hr. See the live table above for current per-provider pricing.
How much VRAM does an H100 have?
The H100 has 80GB HBM3, with 3.35 TB/s of peak memory bandwidth.
Is renting cheaper than buying?
Renting avoids the upfront hardware cost and lets you match spend to actual usage. A rented H100 at $1.99/hr only costs money while it's running, whereas buying ties up capital in hardware that keeps depreciating whether it's in use or not. Which is cheaper depends on how continuously you'd run it; short or bursty workloads usually favor renting.
