FinOps guides on LLM and cloud pricing

Practical FinOps guides on LLM and cloud pricing: batch and cache economics, model selection, and what the published rate cards leave out. Every figure is recomputed from the catalogue at build time. Data snapshot: 2026-09-06.

• Batch API economics: when the -50% applies
• How we compute cost per request
• Open weights against proprietary APIs: the cost gap in numbers
• Prompt caching: the discount nobody budgets for
• Quality per dollar: the models that beat their price class
• Bedrock, Vertex, Azure or direct: what the channel changes