Baseten

𝐁𝐚𝐬𝐞𝐭𝐞𝐧 is an AI inference platform founded in 2019 by Tuhin Srivastava, Amir Haghighat, Philip Howes, and Pankaj Gupta after the team experienced model deployment problems firsthand at Gumroad. Headquartered in San Francisco, the platform handles dedicated GPU serving, multi-cloud routing, and autoscaling for AI products in production. Customers include Abridge, Writer, Clay, OpenEvidence, and Descript, with healthcare and voice AI representing two of the strongest verticals.

Key Capabilities:

✓ 𝐁𝐚𝐬𝐞𝐭𝐞𝐧 Inference Stack with custom kernels and advanced caching

✓ Cross-cloud high availability across multiple regions and providers

✓ Self-hosted and VPC deployment options for single-tenant workloads

✓ Truss open-source framework for ML model packaging

✓ Pre-optimized API access for Llama, Mistral, DeepSeek, and Whisper

✓ 𝐁𝐚𝐬𝐞𝐭𝐞𝐧 Chains for compound AI with granular hardware control

✓ 𝐁𝐚𝐬𝐞𝐭𝐞𝐧 Embeddings Inference for vector workloads

✓ Training pipeline with one-click deployment to inference infrastructure

✓ Auto-scaling with scale-to-zero for idle workloads

✓ Cold start optimization with 99.99% uptime target

✓ Forward deployed engineering support for production rollouts

✓ Python SDK and CLI for programmatic deployment control