llm-echo 0.5 counts tool, system, and reasoning tokens
Original title: llm-echo 0.5
The debug model still only echoes prompts and does not call a real language model.
Simon Willison released llm-echo 0.5 while preparing a new LLM release. The plugin provides an echo model that repeats prompts without involving an LLM. Simulated token counts now include tool calls, system prompts, and reasoning tokens.
- An example run with thinking enabled reported 2 input and 24 output tokens.
- Willison revisited the plugin while testing pull requests for a new LLM release.
From the original article
Release: llm-echo 0. 5 I'm working towards a new LLM release, and testing PRs caused me to revisit the llm-echo debug plugin. This plugin provides a "model" which doesn't involve an LLM at all - it just repeats back the prompts that have been fed to it.
simonwillison.net
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.