Get started

What Zexl is

Zexl shows how much of your AI model spend did useful work, and how much was wasted. It names the waste in plain words, puts a dollar figure on each kind, and shows you the runs behind it.

Zexl only records metadata about each model call: the model, token counts, timings, the outcome, and salted hashes. Prompt and response text never leave your process. See What leaves your process.

What you get

  • Useful spend share. Of every dollar, how much produced something you used.
  • Waste by pattern. Retries, loops, abandoned responses, answers cut off and redone, and prompt caching not used. See Waste patterns.
  • Spend by feature, model, customer and person.
  • Run detail. One agent run, step by step, with the repeated or failed steps marked.
  • Budget and forecast. Where the month is likely to end, and when it passes your budget. See Forecast and budget.
  • Ask your AI assistant. The MCP server answers "what did we waste last week?" inside Claude Code, Claude Desktop or Cursor.

How it works

  1. Your app sends call metadata to Zexl, from the Python SDK or from Claude Code's telemetry.
  2. Zexl prices each call with the providers' published prices (or your own).
  3. Every 2 minutes, Zexl sorts each call into one category: useful, or one of the waste patterns.
  4. The dashboard and the MCP server show the result.

Ways to connect

WayBest forEffort
Python SDKApps that use the OpenAI or Anthropic Python clientsOne import and one environment variable
With your AI agentLetting Claude Code or Cursor set it all upApprove one link
Claude CodeSeeing what your own coding sessions costFive environment variables
GatewayAny language, no code changeComing soon

Supported today: OpenAI and Anthropic, in Python. More providers and a Node SDK are planned.

Guides

Practical guides on cutting AI spend, whether or not you use Zexl: How to reduce your LLM API costs, prompt caching, agent loops, and all guides.