AI FinOps research.

Field notes on reducing LLM spend without hiding quality regressions. Start with the full guide, then use the technique pages for specific levers.

Start here

• LLM cost optimization: a practical guide — the full playbook: routing, caching, compression, batch APIs, and provider arbitrage.
• Provider price benchmarks — current list-price references and methodology.
• Glossary — plain-English definitions for billing and optimization terms.

Optimization levers

• Model routing without quality regressions
• Semantic caching for LLMs
• Prompt caching: OpenAI vs Anthropic vs Bedrock
• Batch API routing: 50% off for the work that can wait
• Provider arbitrage: same model, different price

Accounting and tooling

• Cache-read tokens: the baseline trap
• LiteLLM vs Helicone vs LangFuse