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.
What it is
llm 0.35 is a point release of Simon Willison's llm tool, the command-line and Python interface for querying multiple LLM providers from one CLI.
What it does
It registers the new `gpt-6-astra` model ID, following OpenAI's GPT-6 Astra launch, so it can be called with `llm -m gpt-6-astra` alongside every other model llm already supports.
Why it matters
Anyone scripting comparisons across providers gets same-day access to a brand-new frontier model through the same CLI they already use for Claude, Gemini, and open-weight models, instead of writing a one-off API client.
How to use it
Run `llm install -U llm` (or upgrade via pip/uv) to pull 0.35, then call `llm -m gpt-6-astra "your prompt"` once you've set an `OPENAI_API_KEY`.
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.
llm-gemini 0.34 Adds Gemini 3.8 Flash With Three Thinking Levels
llm-gemini 0.34 adds support for Google's new gemini-3.8-flash model with low, medium, and high thinking levels to Simon Willison's LLM command-line tool.
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.