Serverless GPUs for real-time inference that scale to zero
Cerebrium homepage
Cerebrium bills compute by the second while a container is running, with the GPU, vCPU and memory each priced separately, so a deployed app costs more than its GPU rate alone.
Platform plans sit on top of compute: a free tier, a flat monthly subscription, and custom enterprise pricing with volume discounts. Persistent storage is billed per GB-month.
| Price point | Configuration | Estimated cost |
|---|---|---|
| Small VM 1 vCPU, 1 GB RAM (CPU only) | 1 vCPU, 1 GB RAM (CPU only) | $22.73 /mo |
| Medium VM 4 vCPU, 8 GB RAM (CPU only) | 4 vCPU, 8 GB RAM (CPU only) | $113.94 /mo |
| Large VM 8 vCPU, 16 GB RAM (CPU only) | 8 vCPU, 16 GB RAM (CPU only) | $227.89 /mo |
| Block storage 100 GB beyond free allowance First 100 GB included | 100 GB beyond free allowance First 100 GB included | $5.00 /mo |
Heads up: Figures take each provider's closest plan to a common setup, and vary by region and usage. Verify before provisioning. More on how we price.
Each card leads with a per GPU per hour rate. We prefer configurations the provider reports as in stock, on-demand rates before reserved or spot, then take the lowest per-GPU rate among those.
We match the GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.
Cerebrium lists 9 GPU models across 40 configurations, including the H100, B200 and RTX PRO 6000. Prices start at $0.59 /GPU/hr on demand.
No GPU models match .
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Verify before provisioning. More on how we price. See Cerebrium's pricing.
Founded in Cape Town in 2021 and now headquartered in New York, Cerebrium runs serverless GPU infrastructure for real-time AI workloads: voice agents, image and video pipelines, LLM endpoints, and custom Python apps. Hardware is declared in a cerebrium.toml file and the code deploys as a container that scales from zero, with compute billed by the second.
Example customers include Tavus, Deepgram, Resemble AI. More here.
Cerebrium offers 4 of the 27 services we track.
Cerebrium covers 4 of the 6 compliance frameworks we track.
| Framework | Level | Checked | Source |
|---|---|---|---|
| SOC 2 | Type II | trust.cerebrium.ai | |
| ISO 27001 | trust.cerebrium.ai | ||
| HIPAA | trust.cerebrium.ai | ||
| GDPR | cerebrium.ai |
Heads up: Each row links to the provider's own statement, checked on the date shown. An attestation can cover one tier, one region or the platform alone rather than every service. Verify the scope before you rely on it.
Based on our records, Cerebrium operates in 3 locations across 2 countries.
Compare Cerebrium against other cloud providers.
Our data for Cerebrium was last updated on Sept. 24, 2026.
