llm-echo 0.5 adds simulated token usage for tool calls, system prompts and reasoning
Overview
Simon Willison releases llm-echo 0.5, a debug plugin for the LLM tool whose "echo" model repeats prompts without calling a language model.
The new version updates its simulated token usage counts to include tool calls, system prompts and reasoning tokens. In an example run with the --usage flag, the plugin reports 2 input tokens and 24 output tokens.
Written by AI from the articles below · updated Oct 18, 8:16 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Simon WillisonBlogllm-echo 0.5 updates simulated token usage for tool calls, system prompts and reasoning
AISimon Willison releases llm-echo 0.5, a debug plugin whose "echo" model repeats prompts without using an LLM. The new version counts simulated token usage for tool calls, system prompts and reasoning tokens. An example run with the --usage flag reports 2 input and 24 output tokens.
Heat Trend
Not enough continuous observations to show a trend yet.