Managed APIs vs Self-Hosting

The consumption spectrum from serverless tokens to your own GPU fleet: what you inherit at each step, and the drivers that actually decide it.

Content last verified 2026-09.

Lessons

1. The Spectrum
2. What You Inherit
3. The Decision Drivers

Sources

• Amazon Bedrock User Guide — Provisioned Throughput
• Azure AI Foundry — Foundry Models overview (deployment options)
• Vertex AI — consumption options for generative models
• Amazon Bedrock User Guide — Protect your data using Amazon VPC and AWS PrivateLink