Cerebrium
Free tierServerless GPU infrastructure for real-time AI with sub-second cold starts and instant autoscaling
Paid·Technical·API available
Key strengths
Sub-second to low-second cold starts with GPU/memory snapshottingPay-per-second serverless GPU pricing with no idle costsElastic autoscaling across 12+ GPU types and multiple regionsNo infrastructure rewrites — bring your own code or DockerfileSOC 2, HIPAA, GDPR, ISO 27001 compliance99.999% uptime with multi-region failoverOpenTelemetry-native observability
Paid only · from $100 USD/mo
Facts verified against cerebrium.ai on
Recent changes
- Free tier: now available
- Plans updated: Pay-per-second compute pricing. Hobby plan is free (+ compute costs). Standard plan is $100/month + compute. Enterprise is custom. GPU rates range from $0.000164/s (T4) to $0.00167/s (B200). Memory at $0.00000222/GB/s, storage at $0.05/GB/mo (first 100GB free).
Get alerts when Cerebrium changes
Free. We'll email you when pricing, the free tier, API access or open-source status changes.
No ratings yet
Technical Use Cases
Cerebrium is optimized for ML engineers and developer teams running latency-sensitive, production-scale AI workloads on serverless GPU infrastructure.
Primary workload types:
- LLM inference: Deploy large language models using vLLM, SGLang, or TensorRT-LLM with elastic autoscaling and pay-per-second billing — no idle GPU costs between requests
- Real-time voice agents: Low-latency voice pipelines via native integrations with Twilio, Pipecat, and LiveKit; sub-second cold starts keep response times tight
- Image & video generation: Run diffusion models and video workloads across 12+ GPU types (T4 through B200) scaled to demand
- Custom inference containers: Bring any Dockerfile or existing codebase; no platform-specific rewrites needed
Operational strengths for engineering teams:
- GPU/memory snapshotting for fast cold starts without pre-warming fleets
- OpenTelemetry-native observability for tracing and monitoring
- Multi-region failover with 99.999% uptime
- SOC 2, HIPAA, GDPR, ISO 27001 compliance for enterprise and regulated deployments
- WandB integration for experiment tracking; FastAPI for custom endpoint logic
Alternatives
See all alternatives