Skip to main content
AgentMeter is cost infrastructure for AI agent businesses. It helps you discover every cost source, track spend by customer and agent step, react before spend runs away, and bill customers from usage data.

​
What AgentMeter does

AgentMeter gives engineering and operations teams a cost layer for production agents:
  • Capture LLM calls from OpenAI, Anthropic, and Vercel AI through the SDK.
  • Report non-LLM usage such as search requests, speech characters, vector lookups, and workflow executions.
  • Attribute usage to customer_id and step_name so cost reports map to customers and product workflows.
  • Price usage on the server from builder-owned pricing tables instead of trusting application code to send dollars.
  • Enforce cost controls with budget limits, customer throttles, routing rules, failover rules, alerts, and recommendations.

​
Start here

  1. Quickstart - install the SDK and send your first event.
  2. TypeScript SDK - auto-instrument Node.js agent runtimes.
  3. Python SDK - auto-instrument Python agent runtimes.
  4. Cost attribution - choose stable customer and step identifiers.
  5. API overview - understand the SDK-facing HTTP surface.

​
Core model

AgentMeter is SDK-first. Your application keeps calling model and tool providers directly. The SDK emits cost-shaped telemetry in the background, and the backend calculates cost from your pricing tables.
LayerResponsibility
SDKCapture usage, attach customer context, report telemetry, enforce cached pre-call rules.
BackendValidate events, price usage, store events, evaluate post-call rules, reconcile budgets.
DashboardConfigure keys, pricing, rules, alerts, invoices, and customer-facing portal links.

​
Privacy posture

AgentMeter does not need prompt text, completions, raw tool arguments, emails, phone numbers, or user messages. Use opaque identifiers and stable labels for all telemetry fields. See Privacy and PII before sending production data.