H100 rental prices: cheapest $/hr today
The cheapest on-demand H100 rental today is $1.75/hr on Lium for the H100 (unspecified), updated 2026-10-06. 80-94 GB VRAM, NVIDIA.
Pricing at a glance
All current H100 offers
Provider, memory & availability
| GPU / provider | Billing | $/GPU-hour | GPUs / total per hour | Availability / details |
|---|---|---|---|---|
| H100 (unspecified)Prime Intellect80 GB VRAM | spot / interruptible | $0.94per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Latitude.sh80 GB VRAMg3-h100-small | reserved / committed12 months, annual plan; normalized over 8760 hours | $1.18per GPU-hour30-day comparison unavailable | 1× $1.18per node-hour | Out of stock2026-10-06Details
|
| H100 NVLMicrosoft Azure94 GB VRAMStandard_NC40ads_H100_v5 | spot / interruptible | $1.29per GPU-hour30-day comparison unavailable | 1× $1.29per node-hour | Not reportedView provider2026-10-06Details
|
| H100 NVLMicrosoft Azure94 GB VRAMStandard_NC80adis_H100_v5 | spot / interruptible | $1.29per GPU-hour30-day comparison unavailable | 2× $2.58per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Latitude.sh80 GB VRAMg3-h100-small | reserved / committed1 month, monthly plan; normalized over 720 hours | $1.71per GPU-hour30-day comparison unavailable | 1× $1.71per node-hour | Out of stock2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node d4093d0c-8d7c-448a-b4e0-a34e44468ea8; 8 GPUs on host | secure cloud | $1.75per GPU-hour30-day comparison unavailable | 1× $1.75per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node a18470e9-1cc0-4b74-a264-b487c83c5708; 2 GPUs on host | secure cloud | $1.75per GPU-hour30-day comparison unavailable | 1× $1.75per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Hyperstack80 GB VRAM | reserved / committedTerm and minimum volume not published in this table; confirm reservation quoteStarting rate; confirm terms | $1.75per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMTensorDock80 GB VRAM | spot / interruptible | $1.91per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 PCIeLium80 GB VRAMMarketplace node eae1f7b4-7c22-4493-bd9b-96708e730edf; 1 GPUs on host | secure cloud | $1.95per GPU-hour30-day comparison unavailable | 1× $1.95per node-hour | In stockView provider2026-10-06Details
|
| H100 PCIeRunPod80 GB VRAM | community cloud | $1.99per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Voltage Park80 GB VRAM | on-demand | $1.99per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Together AI80 GB VRAM | spot / interruptible | $1.99per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)GMI Cloud80 GB VRAM | on-demand | $2.00per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMMicrosoft Azure80 GB VRAMStandard_ND96is_H100_v5 | spot / interruptible | $2.04per GPU-hour30-day comparison unavailable | 8× $16.35per node-hour | Not reportedView provider2026-10-06Details
|
| H100 PCIeLium80 GB VRAMMarketplace node 10ab55c7-07bf-4ce3-aea5-ec78b4e95050; 1 GPUs on host | secure cloud | $2.05per GPU-hour30-day comparison unavailable | 1× $2.05per node-hour | In stockView provider2026-10-06Details
|
| H100 PCIeLium80 GB VRAMMarketplace node f22cd780-be84-4917-9663-aa07e92fd661; 1 GPUs on host | secure cloud | $2.05per GPU-hour30-day comparison unavailable | 1× $2.05per node-hour | In stockView provider2026-10-06Details
|
| H100 PCIeLium80 GB VRAMMarketplace node 2a7c4827-f845-4826-85b7-d94d6c20c19d; 1 GPUs on host | secure cloud | $2.05per GPU-hour30-day comparison unavailable | 1× $2.05per node-hour | In stockView provider2026-10-06Details
|
| H100 PCIeLium80 GB VRAMMarketplace node a667a78f-70ee-4c32-87ee-75d945025be5; 1 GPUs on host | secure cloud | $2.05per GPU-hour30-day comparison unavailable | 1× $2.05per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 4c0bcb6b-315c-4074-a623-3d92b8344746; 8 GPUs on host | secure cloud | $2.14per GPU-hour30-day comparison unavailable | 8× $17.12per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 76e45cf2-a539-4300-a1b9-7508e8250288; 8 GPUs on host | secure cloud | $2.15per GPU-hour30-day comparison unavailable | 8× $17.20per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node c7c9303c-7d26-4cac-92e0-d0bb3d7a1b95; 8 GPUs on host | secure cloud | $2.15per GPU-hour30-day comparison unavailable | 8× $17.20per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node f9683e96-4704-4f6e-9b21-07ce930988ec; 8 GPUs on host | secure cloud | $2.15per GPU-hour30-day comparison unavailable | 8× $17.20per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 3036ac08-b62b-448a-b7e6-2e9bce04921e; 8 GPUs on host | secure cloud | $2.15per GPU-hour30-day comparison unavailable | 8× $17.20per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 421aefbd-5003-478e-b64d-de3c2a1ce730; 8 GPUs on host | secure cloud | $2.15per GPU-hour30-day comparison unavailable | 8× $17.20per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 576f65a2-95fd-433a-b9a2-7b6177bca6f3; 8 GPUs on host | secure cloud | $2.15per GPU-hour30-day comparison unavailable | 8× $17.20per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node e5e5824b-d499-45ba-a7f2-bd1db156f6fa; 8 GPUs on host | secure cloud | $2.25per GPU-hour30-day comparison unavailable | 8× $18.00per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 22e5a896-ef5b-4997-8ec0-8e363c8b1670; 8 GPUs on host | secure cloud | $2.25per GPU-hour30-day comparison unavailable | 8× $18.00per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 77012bfc-3c3a-4180-b6ff-669f2c31959d; 8 GPUs on host | secure cloud | $2.25per GPU-hour30-day comparison unavailable | 8× $18.00per node-hour | In stockView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 19ae2e38-758a-4a35-8d72-e85978e072da; 8 GPUs on host | secure cloud | $2.25per GPU-hour30-day comparison unavailable | 8× $18.00per node-hour | In stockView provider2026-10-06Details
|
| H100 SXMTensorDock80 GB VRAM | on-demand | $2.25per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Daytona80 GB VRAMH100; GPU rate only, CPU/memory/disk billed separately | spot / interruptible | $2.27per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMMicrosoft Azure80 GB VRAMStandard_ND96isr_H100_v5 | spot / interruptible | $2.27per GPU-hour30-day comparison unavailable | 8× $18.17per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Vultr80 GB VRAM | spot / interruptible | $2.30per GPU-hour+0.0% over 30 days | 8× $18.40per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Spheron80 GB VRAM | spot / interruptible | $2.43per GPU-hour+17.4% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Prime Intellect80 GB VRAM | on-demand | $2.43per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Hyperstack80 GB VRAM | on-demand | $2.50per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Koyeb80 GB VRAM | serverless | $2.50per GPU-hour$0.000694/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 NVLRunPod94 GB VRAM | community cloud | $2.59per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Spheron80 GB VRAM | on-demand | $2.65per GPU-hour+0.4% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMRunPod80 GB VRAM | community cloud | $2.69per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMHyperstack80 GB VRAM | reserved / committedTerm and minimum volume not published in this table; confirm reservation quoteStarting rate; confirm terms | $2.72per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Massed Compute80 GB VRAM | on-demand | $2.73per GPU-hour+0.0% over 30 days | 1× $2.73per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Lium80 GB VRAMMarketplace node 6f358f2b-9aa6-4e86-9e3a-f4018db5f930; 8 GPUs on host | secure cloud | $2.75per GPU-hour30-day comparison unavailable | 8× $22.00per node-hour | In stockView provider2026-10-06Details
|
| H100 PCIeRunPod80 GB VRAM | secure cloud | $2.89per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 NVLMassed Compute94 GB VRAM | on-demand | $2.92per GPU-hour+0.0% over 30 days | 2× $5.84per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMImpossible Cloud80 GB VRAM286-H100; 96 GPUs quoted; 8 GPUs/node; availability by request | reserved / committed12 monthsStarting rate; confirm terms | $2.95per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Waitlist2026-10-06Details
|
| H100 (unspecified)OVHcloud80 GB VRAM | on-demand | $2.99per GPU-hour+0.0% over 30 days | 1× $2.99per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMMassed Compute80 GB VRAM | on-demand | $3.14per GPU-hour+8.7% over 30 days | 1× $3.14per node-hour | Not reportedView provider2026-10-06Details
|
| H100 NVLRunPod94 GB VRAM | secure cloud | $3.19per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMHyperstack80 GB VRAM | on-demand | $3.20per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMThunder Compute80 GB VRAM | on-demand | $3.20per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Scaleway80 GB VRAM | on-demand | $3.21per GPU-hour-3.6% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 PCIeLambda80 GB VRAM1x NVIDIA H100 PCIe | on-demand | $3.29per GPU-hour30-day comparison unavailable | 1× $3.29per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Latitude.sh80 GB VRAMg3-h100-small | on-demand | $3.37per GPU-hour30-day comparison unavailable | 1× $3.37per node-hour | Out of stock2026-10-06Details
|
| H100 (unspecified)Cerebrium80 GB VRAM | serverless | $3.40per GPU-hour$0.000944/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMRunPod80 GB VRAM | secure cloud | $3.49per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMJarvislabs80 GB VRAM | on-demand | $3.49per GPU-hour+29.7% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMScaleway80 GB VRAM | on-demand | $3.58per GPU-hour30-day comparison unavailable | 4× $14.31per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMDataCrunch80 GB VRAM | on-demand | $3.77per GPU-hour+16.1% over 30 days | 1× $3.77per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Crusoe80 GB VRAM | on-demand | $3.90per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMModal80 GB VRAM | serverless | $3.95per GPU-hour$0.001097/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Daytona80 GB VRAMH100; GPU rate only, CPU/memory/disk billed separately | on-demand | $3.95per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMLambda80 GB VRAM8x NVIDIA H100 SXM | on-demand | $3.99per GPU-hour30-day comparison unavailable | 8× $31.92per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Together AI80 GB VRAM | on-demand | $3.99per GPU-hour30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMLambda80 GB VRAM4x NVIDIA H100 SXM | on-demand | $4.09per GPU-hour30-day comparison unavailable | 4× $16.36per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMLambda80 GB VRAM2x NVIDIA H100 SXM | on-demand | $4.19per GPU-hour30-day comparison unavailable | 2× $8.38per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMLambda80 GB VRAM1x NVIDIA H100 SXM | on-demand | $4.29per GPU-hour30-day comparison unavailable | 1× $4.29per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)DigitalOcean80 GB VRAMgpu-h100x1-80gb | on-demand | $4.41per GPU-hour30-day comparison unavailable | 1× $4.41per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)DigitalOcean80 GB VRAMgpu-h100x8-640gb | on-demand | $4.41per GPU-hour30-day comparison unavailable | 8× $35.28per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Nebius80 GB VRAM | on-demand | $4.50per GPU-hour+16.9% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)fal80 GB VRAM | serverless | $4.50per GPU-hour$0.001250/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)RunPod80 GB VRAMFlex worker | serverless | $4.79per GPU-hour$0.001331/sec30-day comparison unavailable | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Replicate80 GB VRAM | serverless | $5.49per GPU-hour$0.001525/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Google Cloud80 GB VRAM | spot / interruptible | $5.57per GPU-hour-5.2% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)CoreWeave80 GB VRAM | on-demand | $6.16per GPU-hour+0.0% over 30 days | 8× $49.24per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Baseten80 GB VRAM | serverless | $6.50per GPU-hour$0.001806/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMAWS80 GB VRAMp5.48xlarge | on-demand | $6.88per GPU-hour30-day comparison unavailable | 8× $55.04per node-hour | Not reportedView provider2026-10-06Details
|
| H100 NVLMicrosoft Azure94 GB VRAMStandard_NC40ads_H100_v5 | on-demand | $6.98per GPU-hour30-day comparison unavailable | 1× $6.98per node-hour | Not reportedView provider2026-10-06Details
|
| H100 NVLMicrosoft Azure94 GB VRAMStandard_NC80adis_H100_v5 | on-demand | $6.98per GPU-hour30-day comparison unavailable | 2× $13.96per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMAWS80 GB VRAMp5.48xlarge | spot / interruptible | $7.22per GPU-hour30-day comparison unavailable | 8× $57.76per node-hour | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Fireworks AI80 GB VRAM | serverless | $8.00per GPU-hour$0.002222/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 (unspecified)Google Cloud80 GB VRAM | on-demand | $9.80per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| H100 SXMMicrosoft Azure80 GB VRAMStandard_ND96is_H100_v5 | on-demand | $11.06per GPU-hour30-day comparison unavailable | 8× $88.49per node-hour | Not reportedView provider2026-10-06Details
|
| H100 SXMMicrosoft Azure80 GB VRAMStandard_ND96isr_H100_v5 | on-demand | $12.29per GPU-hour30-day comparison unavailable | 8× $98.32per node-hour | Not reportedView provider2026-10-06Details
|
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
On-demand and secure rates do not require a reservation. Community and spot capacity can be interrupted. Prices are per GPU per hour, before storage/egress. Every row shows its update date.
Compare H100 configurations
H100 purchase prices · Rent or buy calculator · Compare two GPUs
- Prime Intellect H100 pricing
- Latitude.sh H100 pricing
- Microsoft Azure H100 pricing
- Lium H100 pricing
- Hyperstack H100 pricing
- TensorDock H100 pricing
- RunPod H100 pricing
- Voltage Park H100 pricing
- Together AI H100 pricing
- GMI Cloud H100 pricing
- Daytona H100 pricing
- Vultr H100 pricing
- Spheron H100 pricing
- Koyeb H100 pricing
- Massed Compute H100 pricing
- Impossible Cloud H100 pricing
- OVHcloud H100 pricing
- Thunder Compute H100 pricing
- Scaleway H100 pricing
- Lambda H100 pricing
- Cerebrium H100 pricing
- Jarvislabs H100 pricing
- DataCrunch H100 pricing
- Crusoe H100 pricing
- Modal H100 pricing
- DigitalOcean H100 pricing
- Nebius H100 pricing
- fal H100 pricing
- Replicate H100 pricing
- Google Cloud H100 pricing
- CoreWeave H100 pricing
- Baseten H100 pricing
- AWS H100 pricing
- Fireworks AI H100 pricing
LLM memory estimates for this GPU
These models have an estimated inference footprint within 94 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.
| Model | 16-bit GB | 8-bit GB | 4-bit GB |
|---|---|---|---|
| Qwen2.5 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 32B | 79.9 ✓ | 40.6 ✓ | 20.9 ✓ |
| Qwen2.5 72B | 176.1 | 88.9 ✓ | 45.2 ✓ |
| Qwen2.5 Coder 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 Coder 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 Coder 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 Coder 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 Coder 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 Coder 32B | 79.9 ✓ | 40.6 ✓ | 20.9 ✓ |
| Qwen3 0.6B | 2.4 ✓ | 1.5 ✓ | 1.0 ✓ |
| Qwen3 1.7B | 5.4 ✓ | 3.0 ✓ | 1.8 ✓ |
| Qwen3 4B | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen3 8B | 20.4 ✓ | 10.6 ✓ | 5.6 ✓ |
| Qwen3 14B | 36.2 ✓ | 18.5 ✓ | 9.7 ✓ |
| Qwen3 32B | 79.9 ✓ | 40.6 ✓ | 20.9 ✓ |
| Qwen3 30B A3B | 73.8 ✓ | 37.1 ✓ | 18.8 ✓ |
| DeepSeek R1 Distill Qwen 1.5B | 4.4 ✓ | 2.3 ✓ | 1.2 ✓ |
| DeepSeek R1 Distill Qwen 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| DeepSeek R1 Distill Qwen 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| DeepSeek R1 Distill Qwen 32B | 79.9 ✓ | 40.6 ✓ | 20.9 ✓ |
| DeepSeek R1 Distill Llama 8B | 19.9 ✓ | 10.3 ✓ | 5.5 ✓ |
| DeepSeek R1 Distill Llama 70B | 170.9 | 86.3 ✓ | 43.9 ✓ |
| Mistral 7B v0.3 | 18.0 ✓ | 9.3 ✓ | 5.0 ✓ |
| Mixtral 8x7B v0.1 | 112.7 | 56.7 ✓ | 28.7 ✓ |
| Mixtral 8x22B v0.1 | 338.6 | 169.9 | 85.5 ✓ |
| Mistral Small 24B 2501 | 57.4 ✓ | 29.1 ✓ | 14.9 ✓ |
| Mistral Nemo 2407 | 30.2 ✓ | 15.5 ✓ | 8.2 ✓ |
| phi 4 | 36.2 ✓ | 18.6 ✓ | 9.8 ✓ |
Compare model memory requirements or change context and memory assumptions on a model's page.
When to choose H100
Use the model memory estimates above to check whether your weights, context and batch size fit within 80-94 GB. Then compare the exact variant, node size and software support. Capacity alone does not establish inference speed or training throughput.
If your workload fits within 80 GB, compare A100 rental prices from $0.89/GPU-hour. The smaller memory budget is the trade-off; price alone does not make the cards interchangeable.
H100 price changes
- 30 days: 3.0% across 21 matching firm-price configurations since 2026-09-06.
- 90 days: 5.0% across 14 matching firm-price configurations since 2026-07-08.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region. New listings are not counted as price changes.
Price history
on-demand rate per day · median on-demand rate per day (dashed), since 2026-07-05: $1.80 low · $2.89 high. Full ledger on the history hub.
FAQ
The cheapest H100 rental we have is $1.75 per GPU-hour on Lium (secure cloud), updated 2026-10-06.
80-94 GB depending on the variant (H100 (unspecified): 80 GB, H100 PCIe: 80 GB, H100 SXM: 80 GB, H100 NVL: 94 GB).
Lium has the cheapest verified on-demand rate today at $1.75 per GPU-hour; interruptible spot/community capacity starts at $0.94. Verified 2026-10-06.
Related
All 80 GB+ GPUs · GPUs under $2/hr · Price movers this week · Lium review · H100 vs A100 · H100 vs H200 · B200 vs H100 · Cloud GPU for batch inference · Best Cloud GPU for LLM Fine-Tuning · What is the price difference between the H100 and H200?
Should you rent or buy?
Compare H100 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates.