BentoML
Free tierRun AI inference at scale — deploy any model anywhere with full control and no complexity.
Free tier available·Technical·API available·Open source
Key strengths
Deploy any model (open-source or custom) across any cloud or on-prem infrastructureInference-optimized auto-scaling with cold-start acceleration and scale-to-zeroFramework-agnostic: supports vLLM, TRT-LLM, JAX, SGLang, PyTorch, TransformersEnterprise-grade security with SOC 2 Type II, ISO 27001, and HIPAA complianceFull observability with LLM-specific metrics, CI/CD, canary/shadow/A/B testing
Free tier + paid plans
San Francisco, USA
Founded 2019
Self-hostable
No ratings yet
No content available for this audience yet.