llm 0.34

Simon Willison's Blog Tools
llm release command-line-tool performance-improvement open-source bug-fixes

Summary

Release of llm 0.34 introduces new features for logging response duration, includes bug fixes, and enhances performance of the llm logs command.

No content available
Original Article
View Cached Full Text

Cached at: 09/08/26, 12:22 AM

# Release: llm 0.34 Source: [https://simonwillison.net/2026/Sep/2/llm/](https://simonwillison.net/2026/Sep/2/llm/) One new feature: > - `llm logs \-\-usage`Markdown output now includes the response duration in milliseconds and as a human\-readable duration\.`llm logs \-\-short`includes a new`duration\_ms`field\.[\#1653](https://github.com/simonw/llm/issues/1653) Plus several contributed bug fixes, and a significant performance improvement to`llm logs`thanks to[waveplate](https://github.com/waveplate)on GitHub, see also[llm\-openrouter 0\.7\.1](https://simonwillison.net/2026/Sep/2/llm-openrouter/)\.

Similar Articles

llm 0.32a0

Simon Willison's Blog

This article announces the release of version 0.32a0 of the 'llm' command-line tool by Simon Willison, providing a monthly briefing on LLM developments.

llm 0.36

Simon Willison's Blog

Release of llm version 0.36, a command-line tool for interacting with AI models, announced by Simon Willison on September 22, 2026.

llm 0.35

Simon Willison's Blog

This article likely covers the release of LLM version 0.35, which is an update to a large language model.

LLM 0.32a0 is a major backwards-compatible refactor

Simon Willison's Blog

LLM 0.32a0 is a major backwards-compatible refactor of the Python library and CLI tool, shifting from simple text prompts to supporting sequences of messages and multi-part responses to better handle modern LLM capabilities like structured JSON and tool use.

llm 0.33

Simon Willison's Blog

Release 0.33 of the LLM tool includes upgrades to OpenAI dependencies, enhanced embedding key support, repeatable prompt templates, and reasoning summary options for Responses API models.