Provider pricing

TrueFoundry AI API pricing

TrueFoundry is a Kubernetes-native ML and LLM platform that runs in the customer's cloud. It bundles a unified LLM gateway, fine-tuning jobs, GPU autoscaling, and prompt management, with seat-based pricing plus a per-token gateway fee.

Founded2021
HeadquartersSan Francisco, CA
Tracked modelsDirectory

Best for

Platform teams standardizing LLM and ML infra across the org.

Strengths

  • Self-hosted in your own VPC — no data leaves your cloud
  • Unified gateway across 200+ models with cost guardrails
  • Auto-scaling GPU inference with cold-start optimization
  • Fine-tuning, RAG, and agent tooling in one stack