llm CLI
llm, Simon Willison's command-line tool for accessing LLMs, with plugins for local models (llama.cpp, Ollama) and prompt logging to SQLite.
Release history
llm CLI 0.36
Adds support for gpt-6-sol and gpt-6-luna endpoints
llm CLI 0.35
Adds GPT-6 Astra model support
llm CLI 0.34
Llm logs --usage Markdown output now includes response duration in milliseconds and human-readable form
llm CLI 0.33
Migrates to OpenAI Python library 3.x, switches HTTP client from httpx to httpx2
llm CLI 0.32.1
Pins OpenAI Python dependency to pre-3.0 to avoid requiring httpx on fresh installs
llm CLI 0.32
Major overhaul of how prompts, responses, tools, and logs are represented; Backwards-compatible
llm CLI 0.32rc1
Default model now GPT-5.6 Luna for users without a configured default
llm CLI 0.31.1
Fixes JSON error from OpenAI Chat Completion providers when tool calls have empty arguments
llm CLI 0.32a3
Tool calls now support pausable chains with unique IDs and human-in-the-loop resumption, enabling approval workflows before model invocation
llm CLI 0.32a2
Llm CLI now supports OpenAI's Responses API for reasoning-capable models, streaming visible reasoning summaries and enabling interleaved reasoning across tool calls