AI FinOps research.

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

Start here

• AI FinOps - the operating model for measuring, allocating, optimizing, and reconciling LLM spend.
• LLM cost monitoring - what to track, how to tag it, and which dashboards actually matter.
• OpenAI cost optimization - the highest-leverage ways to lower API spend in production.
• 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.

Governance

• AI governance for finance leaders — the pillar guide: policy, allocation, accountability.
• What is AI governance? — plain-English definition for 2026.
• AI governance framework — the five-layer operating model and 90-day plan.

New and timely

• AI FinOps in 2026 - why cost optimization is shifting from isolated prompt tricks to an operating model.
• OpenAI Flex vs Batch - the 2026 playbook for moving low-priority work off the expensive standard path.
• Prompt caching in 2026 - why teams still leave money on the table even after "turning caching on."
• Reasoning tokens are the hidden line item on your AI bill - why invisible output spend is becoming a real production issue.
• Agent spend guardrails - the budgets, retry limits, and loop controls that keep agent workflows sane.
• Conversation state is a cost lever now - why state handling is becoming a real AI cost architecture problem.
• Multimodal costs sneak up faster than text costs - why image, audio, and realtime AI often need their own cost model.
• AI chargeback and showback are becoming real in 2026 - what has to be true before allocating AI spend internally.
• Evals need cost discipline too - why evaluation quality and evaluation economics now have to coexist.
• Background mode is an economics feature, not just a reliability feature - why async AI work changes cost architecture, not just uptime.
• Built-in tools are not free sidecars anymore - why search, retrieval, and code execution deserve their own budgets.
• Your GenAI telemetry schema is now a cost decision - why observability structure now shapes FinOps quality.

Optimization levers

• LLM cost per request - the unit economics metric and how to segment it.
• 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

• LLM cost monitoring: what to track and how to control it
• LLM cost dashboards - the five views that matter and the fields they need.
• Tracking LLM costs with OpenTelemetry GenAI conventions - gen_ai.* attributes and deriving cost from spans.
• How to track AI token usage - token types, per-request fields, and aggregation levels.
• Cache-read tokens: the baseline trap
• Cache invalidation cost: the hidden line item
• Scale Tier vs Flex vs Batch vs Standard
• LiteLLM vs Helicone vs LangFuse