← ResourcesHow-to
Guides
Step-by-step implementation guides for AI cost governance, usage monitoring, optimization, and alerting.
Setup5 min read
5-Minute Quickstart: Track Your First LLM Event
Create an ingestion key, send one usage event, and confirm it appears in your dashboard — in under five minutes.
What you needStep 1: Create an ingestion keyStep 2: Send your first eventStep 3: Confirm in the dashboard
Setup8 min read
Tracking OpenAI Costs with CostLynx
Three ways to track OpenAI spend: automatic provider sync, the TypeScript SDK helper, and the Python SDK helper — with attribution per feature and user.
Option A: Provider sync (OpenAI only)Option B: Python SDK (recommended for Python apps)Option C: TypeScript SDKAttribution fields
Setup7 min read
Tracking Anthropic Claude Costs with CostLynx
Track Claude API spend per feature and project with the Python SDK or TypeScript SDK — including cache read tokens.
How Anthropic tracking worksPython SDKTypeScript SDKAsync support
Setup8 min read
Tracking LLM Costs in FastAPI Applications
Instrument a FastAPI service to track LLM spend per endpoint, user, and feature — with async fire-and-forget tracking that never blocks responses.
InstallPer-endpoint trackingAuto-track all calls with lifespan middlewareEnvironment configuration
Setup7 min read
Tracking LangChain LLM Costs with CostLynx
Add a CostLynxCallbackHandler to any LangChain LLM to automatically track token usage after every response — no changes to your chain logic.
InstallCostLynxCallbackHandlerAttach to any LangChain LLMLCEL / chain composition
Foundations12 min read
Understanding Token Costs in Production LLM Systems
How input, output, cached, and reasoning tokens accumulate in production, and how to calculate per-request cost accurately across providers.
Cost per request: calculationInput vs output cost dynamicsPrompt caching: when it appliesReasoning tokens: the invisible cost layer
Governance14 min read
Building and Enforcing AI Budget Controls
How to structure org and project-level AI budgets, set threshold strategies, and maintain spend governance without blocking product delivery.
Step-by-step: structuring a budget hierarchyMapping budgets to real workloadsPractical examplesSoft vs hard enforcement
Optimization16 min read
Optimizing LLM Infrastructure Spend at Production Scale
Model selection, context management, caching, and request shaping strategies that reduce inference spend without degrading production quality.
Lever 1: Model selectionLever 2: Context window managementLever 3: Prompt cachingLever 4: Output shaping
Setup18 min read
Instrumenting LLM Usage Monitoring Across Your Stack
Step-by-step integration guide for capturing real-time usage events from OpenAI, Anthropic, and Google Gemini into a centralized cost tracking pipeline.
Step 1: Generate ingestion keysStep 2: Create projects and environmentsStep 3: Instrument your LLM call sitesStep 4: Handle retries and idempotency
Operations15 min read
Configuring AI Spend Alerts and Anomaly Detection
How to design, configure, and tune threshold alerts and anomaly detection rules for production AI spend — including timing expectations and operational runbooks.
Alert types and when to use eachStep-by-step: configuring your first alert rulesExample alert configurationsNotification design and routing
Need API reference? DocumentationLooking for definitions? Glossary