Cerebrium GPU Pricing
4 GPU instances across 1 regions.4 GPU models available — from $0.52/hr.
Serverless ML infrastructure platform offering per-second GPU billing with a Python-first API. Deploy models in minutes without managing infrastructure.
- Per-second billing
- Python-first API
- Fast deployment
- No infrastructure management
- Serverless limitations
- Cold start latency
Cerebrium currently lists 4 GPU instances across 4 GPU models and 1 regions. Pricing starts at $0.52/hr, while the median listing price is $2.95/hr. Compare by model, commitment type, and region before treating the cheapest row as the best choice.
GPU Models at Cerebrium
All Cerebrium GPU Instances
4 results| GPU Model | Instance | Count | VRAM | Region | Type | Price/hr | $/GPU/hr | |
|---|---|---|---|---|---|---|---|---|
| RTX 4090 | 1x-RTX-4090-cerebrium | 1× | 24GB | US-East | Serverless | $0.5220 | — | Rent |
| A100 80GB | 1x-A100-80GB-cerebrium | 1× | 80GB | US-East | Serverless | $2.1384 | — | Rent |
| H100 | 1x-H100-cerebrium | 1× | 80GB | US-East | Serverless | $2.9520 | — | Rent |
| H100 SXM | 8x-H100-SXM-cerebrium | 8× | 640GB | US-East | Serverless | $23.6160 | $2.9520 | Rent |
Compare Other Providers
Cerebrium vs … (Head-to-Head)
Cerebrium GPU Cloud — FAQ
Cerebrium GPU instances start from $0.52/hr. The average price is $7.31/hr. Prices depend on GPU model, region, and commitment type (on-demand vs spot).
Cerebrium offers 4 GPU models: RTX 4090, A100 80GB, H100, H100 SXM. Browse the full list above to compare prices per model.
GPU Tracker’s pricing comparisons are paired with true cost and risk signals. Read the methodology page for how refresh cadence, cost assumptions, and reliability indicators are defined.