Overview
Nvidia GB200
|
Nvidia H200
|
|
|---|---|---|
| Summary | Grace CPU + Blackwell GPU superchip with unified memory architecture. | Extends the H100 with doubled memory for large-model inference and training. |
| Architecture | Grace Hopper Blackwell | Hopper |
| Memory | Up to 13.4TB HBM3e | 141GB HBM3e |
| Memory Bandwidth | 576,000 GB/s | 4,800 GB/s |
| Performance | -- | 1,979 TFLOPS (FP16) |
| Release Date | Q1 2024 | Q4 2023 |
| Performance Segment | High Performance | High Performance |
| Datasheet | Link | Link |
Price comparison
GB200 Pricing
We're tracking 8 cloud providers for the GB200, and the pricing spread is significant. While the average sits at $20.14/hr, the lowest price is currently $10.50/hr per GPU (on-demand).
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.
Sorting and filtering
Click "View all offerings" to access the full list with sortable columns and filters for billing type, GPU count, vCPUs, and RAM.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
| Provider | GPUs | Billing | Total/h | |
|---|---|---|---|---|
CoreWeave
|
4x | On-Demand Pay-as-you-go pricing. No term commitments. | $42.00 | View |
Oracle Cloud
|
4x | On-Demand Pay-as-you-go pricing. No term commitments. | $64.00 | View |
Azure
|
4x | On-Demand Pay-as-you-go pricing. No term commitments. | $108.16 | View |
|
Azure
|
4x | Spot Variable spot pricing with potential interruptions. | $108.16 | View |
FluidStack
|
1x | Custom Custom terms negotiated with the provider. | Custom | View |
Gcore
|
4x | Custom Custom terms negotiated with the provider. | Custom | View |
CUDO
|
1x | Custom Custom terms negotiated with the provider. | Custom | View |
Crusoe
|
72x | On-Demand Pay-as-you-go pricing. No term commitments. | Custom | View |
Nebius
|
4x | Custom Custom terms negotiated with the provider. | Custom | View |
| No offerings matching your filters. | ||||
H200 Pricing
There is a 92% difference between the highest and lowest listings for the H200. You can pay up to $13.78/hr, but the market floor is currently $1.00/hr per GPU (spot instance).
How we sort results
Default ranking
Our algorithm weighs five factors to find the most relevant matches for you:
- Price: We blend total hourly price with price-per-GPU to balance affordability and value.
- Specs: We favor offers with higher CPU, RAM, and GPU Memory.
- Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
- Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
- Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.
Sorting and filtering
Click "View all offerings" to access the full list with sortable columns and filters for billing type, GPU count, vCPUs, and RAM.
Transparency and funding
Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.
Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.
| Provider | GPUs | Billing | Total/h | |
|---|---|---|---|---|
Runpod
Our sponsor
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.59 | View |
Theta EdgeCloud
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $2.49 | View |
DigitalOcean
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.44 | View |
Together
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $4.99 | View |
Koyeb
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.00 | View |
|
Runpod
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $4.39 | View |
|
Theta EdgeCloud
|
2x | On-Demand Pay-as-you-go pricing. No term commitments. | $4.98 | View |
Civo
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.49 | View |
Hyperstack
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.50 | View |
|
Nebius
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $4.50 | View |
Sesterce
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $4.85 | View |
|
Crusoe
|
8x | On-Demand Pay-as-you-go pricing. No term commitments. | $34.32 | View |
|
FluidStack
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $2.30 | View |
Oblivus
|
1x | On-Demand Pay-as-you-go pricing. No term commitments. | $3.99 | View |
|
Runpod
|
2x | On-Demand Pay-as-you-go pricing. No term commitments. | $7.18 | View |
| No offerings matching your filters. | ||||
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Alternative GPUs
Here's how these GPUs compare against alternatives:
Nvidia GB200
vs
Nvidia B200
Nvidia GB200
vs
Nvidia GH200
Nvidia H200
vs
Nvidia H100
Nvidia H200
vs
Nvidia B200
Our data for Nvidia GB200 was last updated on March 25, 2026, and for Nvidia H200 on March 25, 2026.