# o10.io > The control plane for inference spend. o10 routes every AI inference call to the cheapest model that clears your quality floor — across Vercel AI Gateway, OpenRouter, Amazon Bedrock, and owned capacity. Shadow mode, evals, and Know Your Inference (KYI) governance. ## Canonical definitions - **AI inference**: Runtime execution of trained models on live inputs; dominates enterprise AI operational spend after deployment. - **AI tokens**: Units LLMs use to meter prompt and completion text for billing per million tokens — not cryptocurrency. - **LLM routing**: Policy-driven selection of model and venue per request based on cost, eval floor, and data residency. - **AI supply chain**: End-to-end path from sourcing inference capacity through evals, enforcement, KYI governance, to board assurance. - **Know Your Inference (KYI)**: Framework by Shen Pandi scoring inference on performance, economics, integration, strategy, and risk. ## Primary research - State of Inference Spend 2026: https://o10.io/research/state-of-inference-spend-2026 - KYI Whitepaper: https://o10.io/research/kyi-whitepaper ## Hubs - AI: https://o10.io/ai - AI inference: https://o10.io/ai-inference - AI tokens: https://o10.io/tokens - AI models: https://o10.io/ai-models - LLM routing: https://o10.io/routing - AI supply chain: https://o10.io/ai-supply-chain - Know Your Inference: https://o10.io/kyi - Inference spend: https://o10.io/inference-spend - AI FinOps: https://o10.io/ai-finops - Governance: https://o10.io/governance ## Content indexes - Direct answers (200 prompts): https://o10.io/answers - Glossary (500 terms): https://o10.io/glossary - Model catalog: https://o10.io/models - Pricing matrix: https://o10.io/pricing - Savings matrix: https://o10.io/savings - Routing matrix: https://o10.io/routing-matrix - Quick answers: https://o10.io/p - Workloads matrix: https://o10.io/workloads - Topics cross-index: https://o10.io/topics ## Optional - Full excerpts for LLM ingestion: https://o10.io/llms-full.txt - Sitemap: https://o10.io/sitemap-index.xml