NVIDIA B200 · 180 GB VRAM/GPU
B200 · Serverless · fixed
- USD 0.1663/minute compute time
Component price — not a total
Standard
scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions
Compare GPU prices across providers. Every price links to its official source and shows when it was last verified.
199 matching offerings · 331 billing options · filtered
| GPU | Provider | Type | Plan | Price | Location |
|---|---|---|---|---|---|
| NVIDIA B200 180 GB VRAM/GPU · fixed | Baseten.co B200 | Serverless Dedicated Deployments | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | |||||
| H100 80 GB VRAM/GPU · fixed | Baseten.co H100 | Serverless Dedicated Deployments | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | |||||
| A100 80 GB VRAM/GPU · fixed | Baseten.co A100 | Serverless Dedicated Deployments | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | |||||
| 1× NVIDIA B200 180 GB VRAM/GPU · fixed | Beam.cloud B200 | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× L40S 48 GB VRAM/GPU · fixed | Beam.cloud L40S | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× A100 80 GB VRAM/GPU · fixed | Beam.cloud A100 80GB | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× H100 80 GB VRAM/GPU · fixed | Beam.cloud H100 | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× NVIDIA RTX PRO 6000 Blackwell 96 GB VRAM/GPU · fixed | Beam.cloud RTX PRO 6000 | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× NVIDIA H200 141 GB VRAM/GPU · fixed | Beam.cloud H200 | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× A6000 48 GB VRAM/GPU · fixed | Beam.cloud A6000 | Serverless Serverless | Standard scale to zero 1 ms increments · bills code running |
Component price — not a total | unknown |
| The Serverless committed-spend option is presented as “With committed spend Book a call →” without a published amount; it was omitted. | |||||
| 1× A100 80 GB VRAM/GPU · fixed | Cerebrium A100 (80GB) | Serverless Serverless | Standard scale to zero 1 second increments · bills actual compute time |
Component price — not a total | EU compute EU-constrained Sweden |
3 geography evidence items
| |||||
| 8× NVIDIA H200 141 GB VRAM/GPU · fixed | CoreWeave NVIDIA HGX H200 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 43.92/hour | EU compute Spain |
| Europe spot instance rental · spot bills running |
≈ EUR 17.97/hour | ||||
| North America on-demand instance rental bills running |
≈ EUR 43.92/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 18.22/hour | ||||
3 geography evidence items
| |||||
| 8× NVIDIA RTX PRO 6000 Blackwell 96 GB VRAM/GPU · fixed | CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 17.41/hour | EU compute Spain |
| Europe spot instance rental · spot bills running |
≈ EUR 9.586/hour | ||||
| North America on-demand instance rental bills running |
≈ EUR 17.41/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 9.656/hour | ||||
3 geography evidence items
| |||||
| 8× NVIDIA B200 180 GB VRAM/GPU · fixed | CoreWeave NVIDIA HGX B200 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 59.9/hour | EU compute Spain |
| Europe spot instance rental · spot bills running |
≈ EUR 30.36/hour | ||||
| North America on-demand instance rental bills running |
≈ EUR 59.9/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 29.7/hour | ||||
3 geography evidence items
| |||||
| 8× L40S 48 GB VRAM/GPU · fixed | CoreWeave NVIDIA L40S | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 15.67/hour | unknown |
| North America on-demand instance rental bills running |
≈ EUR 15.67/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 6.861/hour | ||||
1 geography evidence item
| |||||
| 8× NVIDIA B300 270 GB VRAM/GPU · fixed | CoreWeave NVIDIA HGX B300 | GPU VM On-demand GPU Instances | Europe spot instance rental · spot bills running |
≈ EUR 31.95/hour | unknown |
| North America spot instance rental · spot bills running |
≈ EUR 31.21/hour | ||||
1 geography evidence item
| |||||
| 8× L40 48 GB VRAM/GPU · fixed | CoreWeave NVIDIA L40 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 8.707/hour | unknown |
| North America on-demand instance rental bills running |
≈ EUR 8.707/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 5.459/hour | ||||
1 geography evidence item
| |||||
| 8× A100 80 GB VRAM/GPU · fixed | CoreWeave NVIDIA A100 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 18.81/hour | unknown |
| Europe spot instance rental · spot bills running |
≈ EUR 8.28/hour | ||||
| North America on-demand instance rental bills running |
≈ EUR 18.81/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 8.402/hour | ||||
1 geography evidence item
| |||||
| 1× GH200 96 GB VRAM/GPU · fixed | CoreWeave NVIDIA GH200 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 5.66/hour | unknown |
| North America on-demand instance rental bills running |
≈ EUR 5.66/hour | ||||
1 geography evidence item
| |||||
| 8× H100 80 GB VRAM/GPU · fixed | CoreWeave NVIDIA HGX H100 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 42.87/hour | unknown |
| Europe spot instance rental · spot bills running |
≈ EUR 16.99/hour | ||||
| North America on-demand instance rental bills running |
≈ EUR 42.87/hour | ||||
| North America spot instance rental · spot bills running |
≈ EUR 17.16/hour | ||||
1 geography evidence item
| |||||
| 4× NVIDIA B200 186 GB VRAM/GPU · fixed | CoreWeave NVIDIA GB200 NVL72 | GPU VM On-demand GPU Instances | Europe on-demand instance rental bills running |
≈ EUR 36.57/hour | unknown |
| North America on-demand instance rental bills running |
≈ EUR 36.57/hour | ||||
1 geography evidence item
| |||||
| 8× L40S 48 GB VRAM/GPU · fixed | Crusoe l40s-48gb.8x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 10.45/hour | unknown |
| | |||||
| 1× A100 80 GB VRAM/GPU · fixed | Crusoe a100-80gb.1x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 1.741/hour | unknown |
| | |||||
| 4× A100 80 GB VRAM/GPU · fixed | Crusoe a100-80gb.4x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 6.966/hour | unknown |
| | |||||
| 10× L40S 48 GB VRAM/GPU · fixed | Crusoe l40s-48gb.10x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 13.06/hour | unknown |
| | |||||
| 1× L40S 48 GB VRAM/GPU · fixed | Crusoe l40s-48gb.1x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 1.306/hour | unknown |
| | |||||
| 2× L40S 48 GB VRAM/GPU · fixed | Crusoe l40s-48gb.2x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 2.612/hour | unknown |
| | |||||
| 8× A100 80 GB VRAM/GPU · fixed | Crusoe a100-80gb.8x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 13.93/hour | unknown |
| | |||||
| 4× L40S 48 GB VRAM/GPU · fixed | Crusoe l40s-48gb.4x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 5.224/hour | unknown |
| | |||||
| 2× A100 80 GB VRAM/GPU · fixed | Crusoe a100-80gb.2x | GPU VM On-demand GPU Instances | On-demand instance rental bills running |
≈ EUR 3.483/hour | unknown |
| | |||||
| 1× AMD Instinct MI300X 192 GB VRAM/GPU · fixed | DigitalOcean AMD MI300X | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 1.733/hour | unknown |
| | |||||
| 8× H100 80 GB VRAM/GPU · fixed | DigitalOcean NVIDIA H100 · 8 GPU | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 20.83/hour | unknown |
| | |||||
| 1× H100 80 GB VRAM/GPU · fixed | DigitalOcean NVIDIA H100 | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 2.952/hour | unknown |
| | |||||
| 8× NVIDIA H200 141 GB VRAM/GPU · fixed | DigitalOcean NVIDIA H200 · 8 GPU | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 23.96/hour | unknown |
| | |||||
| 1× L40S 48 GB VRAM/GPU · fixed | DigitalOcean NVIDIA L40s | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 1.367/hour | unknown |
| | |||||
| 8× AMD Instinct MI300X 192 GB VRAM/GPU · fixed | DigitalOcean AMD MI300X · 8 GPU | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 13.86/hour | unknown |
| | |||||
| 1× NVIDIA H200 141 GB VRAM/GPU · fixed | DigitalOcean NVIDIA H200 | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 2.995/hour | unknown |
| | |||||
| 1× RTX 6000 Ada 48 GB VRAM/GPU · fixed | DigitalOcean NVIDIA RTX 6000 | GPU VM GPU Droplets | On-demand instance rental 1 second increments · 1 minute minimum · bills provisioned |
≈ EUR 1.367/hour | unknown |
| | |||||
| 1× NVIDIA B200 180 GB VRAM/GPU · fixed | Fal.ai B200 | Serverless Serverless | B200 always-on always on 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 5.442/hour | unknown |
| B200 scale-to-zero scale to zero 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 5.442/hour | ||||
| The Serverless & Compute Pricing table publishes As low as amounts, but those discounted prices require sales contact and are omitted. | |||||
| 1× NVIDIA B300 288 GB VRAM/GPU · fixed | Fal.ai B300 | Serverless Serverless | B300 always-on always on 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 7.401/hour | unknown |
| B300 scale-to-zero scale to zero 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 7.401/hour | ||||
| The Serverless & Compute Pricing table publishes As low as amounts, but those discounted prices require sales contact and are omitted. | |||||
| 1× H100 80 GB VRAM/GPU · fixed | Fal.ai H100 | Serverless Serverless | H100 always-on always on 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 3.474/hour | unknown |
| H100 scale-to-zero scale to zero 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 3.474/hour | ||||
| The Serverless & Compute Pricing table publishes As low as amounts, but those discounted prices require sales contact and are omitted. | |||||
| 1× NVIDIA RTX PRO 6000 Blackwell 96 GB VRAM/GPU · fixed | Fal.ai RTX PRO 6000 | Serverless Serverless | RTX PRO 6000 always-on always on 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 2.603/hour | unknown |
| RTX PRO 6000 scale-to-zero scale to zero 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 2.603/hour | ||||
| The Serverless & Compute Pricing table publishes As low as amounts, but those discounted prices require sales contact and are omitted. | |||||
| 1× NVIDIA H200 141 GB VRAM/GPU · fixed | Fal.ai H200 | Serverless Serverless | H200 always-on always on 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 3.918/hour | unknown |
| H200 scale-to-zero scale to zero 1 second increments · bills setup, idle, running, draining, terminating |
≈ EUR 3.918/hour | ||||
| The Serverless & Compute Pricing table publishes As low as amounts, but those discounted prices require sales contact and are omitted. | |||||
| 1× NVIDIA B200 180 GB VRAM/GPU · fixed | Fireworks AI B200 180 GB GPU | Dedicated GPU On-Demand Deployments | Always on always on · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 8.707/hour | unknown |
| Scale to zero scale to zero · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 8.707/hour | ||||
| | |||||
| 1× NVIDIA H200 141 GB VRAM/GPU · fixed | Fireworks AI H200 141 GB GPU | Dedicated GPU On-Demand Deployments | Always on always on · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 6.095/hour | unknown |
| Scale to zero scale to zero · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 6.095/hour | ||||
| | |||||
| 1× NVIDIA B300 288 GB VRAM/GPU · fixed | Fireworks AI B300 288 GB GPU | Dedicated GPU On-Demand Deployments | Always on always on · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 10.45/hour | unknown |
| Scale to zero scale to zero · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 10.45/hour | ||||
| | |||||
| 1× H100 80 GB VRAM/GPU · fixed | Fireworks AI H100 80 GB GPU | Dedicated GPU On-Demand Deployments | Always on always on · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 6.095/hour | unknown |
| Scale to zero scale to zero · dedicated 1 second increments · bills active GPU replicas |
≈ EUR 6.095/hour | ||||
| | |||||
| 1× NVIDIA RTX PRO 6000 Blackwell 96 GB VRAM/GPU · fixed | Google Cloud NVIDIA RTX Pro 6000 | Serverless Cloud Run GPU Services | NVIDIA RTX Pro 6000 No zonal redundancy scale to zero 100 ms increments · 1 minute minimum · bills entire instance lifecycle |
Component price — not a total | EU compute EU-constrained Netherlands |
| NVIDIA RTX Pro 6000 Zonal redundancy scale to zero 100 ms increments · 1 minute minimum · bills entire instance lifecycle |
Component price — not a total | ||||
3 geography evidence items
| |||||
| 4× A100 80 GB VRAM/GPU · fixed | Hugging Face GCP NVIDIA A100 x4 | Dedicated GPU Inference Endpoints | Always on always on · dedicated 1 minute increments · 1 minute minimum · bills initializing, running |
≈ EUR 12.54/hour | unknown |
| Scale to zero scale to zero · dedicated 1 minute increments · 1 minute minimum · bills initializing, running |
≈ EUR 12.54/hour | ||||
| GPU rows do not publish system memory, so systemMemoryGb remains null. | |||||
| 8× A100 80 GB VRAM/GPU · fixed | Hugging Face AWS NVIDIA A100 x8 | Dedicated GPU Inference Endpoints | Always on always on · dedicated 1 minute increments · 1 minute minimum · bills initializing, running |
≈ EUR 17.41/hour | unknown |
| Scale to zero scale to zero · dedicated 1 minute increments · 1 minute minimum · bills initializing, running |
≈ EUR 17.41/hour | ||||
| GPU rows do not publish system memory, so systemMemoryGb remains null. | |||||