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
- Your app sends call metadata to Zexl, from the Python SDK or from Claude Code's telemetry.
- Zexl prices each call with the providers' published prices (or your own).
- Every 2 minutes, Zexl sorts each call into one category: useful, or one of the waste patterns.
- The dashboard and the MCP server show the result.
Ways to connect
| Way | Best for | Effort |
|---|---|---|
| Python SDK | Apps that use the OpenAI or Anthropic Python clients | One import and one environment variable |
| With your AI agent | Letting Claude Code or Cursor set it all up | Approve one link |
| Claude Code | Seeing what your own coding sessions cost | Five environment variables |
| Gateway | Any language, no code change | Coming 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.