Skip to content
EVENT / TOPICHistorical

llm-echo 0.5 Adds Token Counting for Tool Calls, System Prompts and Inference

1 reports1 sources10/18/2026 updated

Current overview (not historical)

AI overview

Simon Willison released llm-echo 0.5, a lightweight model that simply echoes back the prompt it receives. The update introduces a new token‑counting scheme that includes tool calls, system prompts, and inference tokens. In the example output, the model reports 2 input tokens and 24 output tokens, reflecting the expanded counting rules. This change provides a more realistic token usage estimate for users testing LLM workflows without invoking a full language model.

Written with AI from the reporting · updated 10/19/2026

Latest developmentOct 19, 07:16
llm-echo 0.5 released with updated simulated token usage counts
Explore the timeline, relations and evidence
Expand the detailed fact route and sources

Story route

A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.

  1. 1Unclassified fact stationOct 18, 00:00recorded Oct 19, 08:55single sourcerevised

    llm-echo 0.5 更新模拟 token 使用计数

    Read original source ↗ Simon WillisonReplay this moment in the explorer
    Evidence & revisions · 1 source records
    Subject：
    llm-echo
    Action：
    更新模拟 token 使用计数
    Object：
    tool calls, system prompts, and reasoning tokens
    Occurred (fact side)：
    Oct 18, 00:00
    Simon Willison ↗Report pageRevision 2 · currently revised
    Published (valid side)：
    Oct 19, 07:16
    First seen (known side)：
    Oct 19, 08:55
    Fact stationSingle source · one-sided claimRevised

    Copy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.

Uncertainty marks flag where to check the sources; they are not proven causation.

Report timeline

Explore every side through dated source reports.

Oct 19
  1. Simon WillisonRelated fact: single sourceSource report revised
    llm-echo 0.5 released with updated simulated token usage counts

    Report first recorded Oct 19, 08:55

    The llm-echo debug plugin now simulates token usage counts that account for tool calls, system prompts, and reasoning tokens. The plugin provides a model that repeats back user prompts without involving an LLM.

    Read original source ↗

Event discussion

Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.

Open GitHub Discussions