Cost Modeling

Three meters — per-token, provisioned units, GPU-hours — and the break-even thinking that decides between them, with utilization as the hidden variable.

Content last verified 2026-09.

Lessons

1. The Three Meters
2. Break-Even Thinking
3. The Hidden Costs
4. A Worked Frame

Sources

• Amazon Bedrock User Guide — Provisioned Throughput
• Azure AI Foundry — quota and provisioned throughput (Microsoft Learn)
• Vertex AI — consumption options for generative models
• Vertex AI generative AI pricing