A10G · 24 GB VRAM/GPU
A10G · Serverless · fixed
- USD 0.02012/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 serverless GPU providers with per-second billing and scale-to-zero, with every price linked to its source.
108 matching offerings · 169 billing options · filtered
| GPU | Provider (reverse sort) | Plan | Price (sort by this column) | Location |
|---|---|---|---|---|
| A10G 24 GB VRAM/GPU · fixed | Baseten.co A10G | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | ||||
| T4 16 GB VRAM/GPU · fixed | Baseten.co T4 | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | ||||
| L4 24 GB VRAM/GPU · fixed | Baseten.co L4 | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | ||||
| NVIDIA B200 180 GB VRAM/GPU · fixed | Baseten.co B200 | Standard scale to zero · dedicated 1 minute increments · bills deploying, scaling up, scaling down, making predictions |
Component price — not a total | unknown |
| | ||||
| H100 MIG 40 GB VRAM/GPU · opaque provider tier | Baseten.co H100 MIG | 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 | 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 | 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 | 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 GeForce RTX 5090 32 GB VRAM/GPU · fixed | Beam.cloud RTX 5090 | 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 | 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 | 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 | 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 | 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× RTX 4090 24 GB VRAM/GPU · fixed | Beam.cloud RTX 4090 | 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 | 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 | 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× L4 VRAM unknown · fixed | Cerebrium L4 | 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
| ||||
| 1× NVIDIA RTX PRO 6000 Blackwell VRAM unknown · fixed | Cerebrium RTX PRO 6000 | Standard scale to zero 1 second increments · bills actual compute time |
Component price — not a total | unknown |
1 geography evidence item
| ||||
| 1× NVIDIA B200 VRAM unknown · fixed | Cerebrium B200 | Standard scale to zero 1 second increments · bills actual compute time |
Component price — not a total | unknown |
1 geography evidence item
| ||||
| 1× H100 VRAM unknown · fixed | Cerebrium H100 | 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
| ||||
| 1× NVIDIA H200 VRAM unknown · fixed | Cerebrium H200 | 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
| ||||
| 1× A100 40 GB VRAM/GPU · fixed | Cerebrium A100 (40GB) | 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
| ||||
| 1× A10 VRAM unknown · fixed | Cerebrium A10 | 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
| ||||
| 1× A100 80 GB VRAM/GPU · fixed | Cerebrium A100 (80GB) | 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
| ||||
| 1× L40S VRAM unknown · fixed | Cerebrium L40s | 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
| ||||
| 1× T4 VRAM unknown · fixed | Cerebrium T4 | 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
| ||||
| 1× NVIDIA B200 180 GB VRAM/GPU · fixed | Fal.ai B200 | 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 | 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 | 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 | 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 | 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× L4 24 GB VRAM/GPU · fixed | Google Cloud NVIDIA-L4 | NVIDIA-L4 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 Belgium · Netherlands |
| NVIDIA-L4 Zonal redundancy scale to zero 100 ms increments · 1 minute minimum · bills entire instance lifecycle |
Component price — not a total | |||
5 geography evidence items
| ||||
| 1× NVIDIA RTX PRO 6000 Blackwell 96 GB VRAM/GPU · fixed | Google Cloud NVIDIA RTX Pro 6000 | 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
| ||||
| 1× T4 8 GB VRAM/GPU · fixed | Inferless Nvidia T4 Shared | Standard scale to zero 1 second increments · bills model loading, healthy state, request processing |
≈ EUR 0.2884/hour | unknown |
| Enterprise pricing is listed as discounted or custom and has no published price; omitted from the catalog. | ||||
| 1× A10 24 GB VRAM/GPU · fixed | Inferless Nvidia A10 Dedicated | Standard scale to zero · dedicated 1 second increments · bills model loading, healthy state, request processing |
≈ EUR 1.069/hour | unknown |
| Enterprise pricing is listed as discounted or custom and has no published price; omitted from the catalog. | ||||
| 1× A100 80 GB VRAM/GPU · fixed | Inferless Nvidia A100 Dedicated | Standard scale to zero · dedicated 1 second increments · bills model loading, healthy state, request processing |
≈ EUR 4.674/hour | unknown |
| Enterprise pricing is listed as discounted or custom and has no published price; omitted from the catalog. | ||||
| 1× A100 40 GB VRAM/GPU · fixed | Inferless Nvidia A100 Shared | Standard scale to zero 1 second increments · bills model loading, healthy state, request processing |
≈ EUR 2.335/hour | unknown |
| Enterprise pricing is listed as discounted or custom and has no published price; omitted from the catalog. | ||||
| 1× T4 16 GB VRAM/GPU · fixed | Inferless Nvidia T4 Dedicated | Standard scale to zero · dedicated 1 second increments · bills model loading, healthy state, request processing |
≈ EUR 0.5799/hour | unknown |
| Enterprise pricing is listed as discounted or custom and has no published price; omitted from the catalog. | ||||
| 1× A10 12 GB VRAM/GPU · fixed | Inferless Nvidia A10 Shared | Standard scale to zero 1 second increments · bills model loading, healthy state, request processing |
≈ EUR 0.5329/hour | unknown |
| Enterprise pricing is listed as discounted or custom and has no published price; omitted from the catalog. | ||||
| 1× L40S 48 GB VRAM/GPU · fixed | Koyeb L40S | Always-on always on 1 second increments |
≈ EUR 1.045/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 1.045/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 1× A100 80 GB VRAM/GPU · fixed | Koyeb A100 | Always-on always on 1 second increments |
≈ EUR 1.393/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 1.393/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 1× RTX 4000 Ada 20 GB VRAM/GPU · fixed | Koyeb RTX-4000-SFF-ADA | Always-on always on 1 second increments |
≈ EUR 0.4354/hour | EU compute EU-constrained Germany |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 0.4354/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 3 geography evidence items
| ||||
| 2× NVIDIA H200 141 GB VRAM/GPU · fixed | Koyeb 2x H200 | Always-on always on 1 second increments |
≈ EUR 5.224/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 5.224/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 8× A100 80 GB VRAM/GPU · fixed | Koyeb 8x A100 | Always-on always on 1 second increments |
≈ EUR 11.14/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 11.14/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 4× H100 80 GB VRAM/GPU · fixed | Koyeb 4x H100 | Always-on always on 1 second increments |
≈ EUR 8.707/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 8.707/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 1× L4 24 GB VRAM/GPU · fixed | Koyeb L4 | Always-on always on 1 second increments |
≈ EUR 0.6095/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 0.6095/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 8× H100 80 GB VRAM/GPU · fixed | Koyeb 8x H100 | Always-on always on 1 second increments |
≈ EUR 17.41/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 17.41/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 1× A100 80 GB VRAM/GPU · fixed | Koyeb A100 SXM | Always-on always on 1 second increments |
≈ EUR 1.872/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 1.872/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 1× NVIDIA RTX PRO 6000 Blackwell 96 GB VRAM/GPU · fixed | Koyeb RTX-PRO-6000 | Always-on always on 1 second increments |
≈ EUR 1.916/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 1.916/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||
| 4× A100 80 GB VRAM/GPU · fixed | Koyeb 4x A100 SXM | Always-on always on 1 second increments |
≈ EUR 7.488/hour | unknown |
| Scale-to-Zero scale to zero 1 second increments |
≈ EUR 7.488/hour | |||
| Long-term reservations offer up to 50% off, but exact public commitment prices are not published. 1 geography evidence item
| ||||