Spanlens monitors LLM usage across OpenAI, Anthropic, and Gemini, tracking requests, costs, latency, errors, and agent traces. It supports evaluations, alerts, and self-hosting.

Are you the developer of this app? Verify ownership to manage this listing.

Get a dedicated desktop app for Spanlens on Mac, Windows, and Linux with WebCatalog Desktop.

  • Launch Spanlens directly from your Dock or taskbar.
  • Work without distractions in a dedicated window, separate from your browser tabs.
  • Stay signed in to multiple Spanlens accounts and switch between them without logging out.

Learn more about WebCatalog Desktop

Spanlens is an open-source LLM observability and monitoring platform for tracking AI model usage in production. By routing model requests through its proxy or drop-in SDK, teams can monitor token usage, cost, latency, errors, and streaming responses across supported providers while keeping their existing SDK calls. The platform provides detailed traces of AI agent runs, including nested model calls, tools, and retrieval steps, as well as alerts for cost spikes, errors, and latency changes. Teams can manage prompt versions, compare model and prompt performance with evaluations and experiments, and run evaluation checks in CI. Spanlens also supports exact-match caching, OpenTelemetry, data export, and self-hosting.

Disclaimer: WebCatalog is not affiliated, associated, authorized, endorsed by or in any way officially connected to Spanlens. All product names, logos, and brands are property of their respective owners.