Cerebrium

Serverless GPU infrastructure for real-time AI workloads, enabling deployment of voice agents, video models, LLMs, and any AI workload with sub-second cold starts and instant autoscaling.

About Cerebrium

Cerebrium is a serverless infrastructure platform for AI applications. We make it easier for companies to build and deploy AI based applications. We offer Serverless GPU's with low cold start times, over 12 varieties of GPU chips, allow you to run large scale batch jobs, run realtime voice applications and much more. We are used by the teams at Tavus, CivitAI, Twilio and many more.

Customers typically experience 40% in cost savings when compared to using traditional cloud providers and can scale models to more than 10K requests per minute with minimal engineering overhead.

Products

  • Cerebrium

    Model Hosting & InferenceFrom $0.00000655

    View product

    Serverless GPU infrastructure for deploying voice agents, video models, LLMs, and any AI workload with sub-second cold starts and instant autoscaling.

Security and compliance

As reported by Cerebrium. Ask for audit reports before you buy.

  • SOC 2 Type ICompliant
  • HIPAACompliant
  • GDPRCompliant
  • ISOCompliant
  • TLSCompliant
  • Encryption at rest for all user data
  • TLS/SSL enforced for all services including Dashboard and Python package
  • Multi-Factor Authentication (MFA) enforced across all platforms
  • gVisor-based hardened container isolation for each workload
  • Role-based access controls with principle of least privilege for PHI
  • Comprehensive audit logging maintained for all activities potentially involving PHI
  • Regular vulnerability scans with remediation per incident response plan timelines
  • Annual business continuity and security incident exercises
  • Daily database backups enabled
  • Employee computers monitored via Vanta agent
  • Software dependencies audited by GitHub Dependabot
  • Regular employee access audits to internal systems
  • Access logs maintained across all infrastructure services
  • 99.999% uptime with multi-region failover routing
  • Request and response logging available
  • Secrets management
  • Purge request endpoint for immediate customer data deletion

SubprocessorsResemble AI

Is this your company?

Claim the profile to keep facts current, answer buyers and submit evidence for the next ranking review.

Claim Cerebrium