llm 0.33 Upgrades to OpenAI Python 3.x and Ships the httpx2 Migration
llm 0.33 upgrades to the OpenAI Python library 3.x and switches its HTTP client dependency from httpx to httpx2, completing the fix that 0.32.1 only patched around.
What it is
llm 0.33 is the follow-up release to llm 0.32.1, Simon Willison's command-line and Python tool for talking to language models.
What it does
It upgrades the OpenAI Python library dependency to 3.x and switches llm's own HTTP client dependency from httpx to httpx2, instead of the temporary openai<3 pin that 0.32.1 used to keep fresh installs working.
Why it matters
The httpx2 move mirrors the same migration Anthropic's own claude-api SDK upgrade guide documents for anthropic 1.x, so anyone juggling both SDKs is now dealing with the same HTTP layer change on two fronts at once.
How to use it
Run `llm --version` after upgrading and check that plugins depending on the old httpx-based client (like custom OpenAI-compatible endpoints) still work; report breakage on the llm GitHub issues.
Reasoning Traces, Responses API, New SQLite Logs: LLM 0.32 Lands
LLM 0.32 is Simon Willison's command-line and Python tool for talking to language models, updated with visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, and support for the OpenAI Responses API.
llm 0.35 Adds Support for OpenAI's GPT-6 Astra Model
llm 0.35 adds support for OpenAI's gpt-6-astra model to Simon Willison's command-line and Python tool for talking to language models.
GPT-6 Astra Arrives, Priced to Match Fable 5.1's $10/$50 per Mtok
GPT-6 Astra is OpenAI's new model rolling out to ChatGPT tiers and the API, priced at $10 per million input and $50 per million output tokens, matching Claude Fable 5 and 5.1.