Tools · Updated 19 Oct, 04:46 am IST
llm-echo 0.5 updated to simulate token usage including tool calls
Why it matters for readers: You can try out LLM-like behaviour locally and understand token reporting without using a commercial model.
- llm-echo is a debug plugin that provides a model which repeats back prompts rather than calling an LLM.1
- Version 0.5 updates the simulated token usage counts to account for tool calls, system prompts, and reasoning tokens.1
- Simon Willison notes this work came up while testing PRs for a new LLM release.1
- Example usage shown uses the uvx command with llm-echo to produce an echoed prompt and a token usage summary.1
Get a brief like this every morning
Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.
Get started