llm CLI adds GPT-6 Astra support in 0.35 release
Simon Willison's llm CLI tool now supports OpenAI's GPT-6 Astra model through a fresh release. This incremental update reflects the rapid cadence of frontier model launches and the tooling ecosystem's need to keep pace with new capabilities. For developers relying on llm as a unified interface to multiple LLM providers, GPT-6 Astra support expands their options without requiring custom integration work. The addition signals continued momentum in OpenAI's model lineup and underscores how open-source developer tools have become essential infrastructure for managing model proliferation.
Modelwire context
Analyst takeThe llm update itself is routine maintenance, but its September 7 timestamp matters: it arrives six days after OpenAI's staged Astra rollout began and just as the model enters broader developer hands. This suggests the tooling layer is now synchronized with capability distribution strategy rather than trailing it.
OpenAI's Astra launch has been deliberately sequenced since early September. The company delayed the model after the Hugging Face incident to shore up containment, then rolled it out to curated partners with explicit time-to-patch windows before public release. Willison's llm tool update accelerates that public availability by removing integration friction. This coordination between capability release and tooling availability reflects a maturing playbook: frontier models no longer ship in isolation. They arrive with infrastructure that makes them immediately usable, which compresses the window between 'early access' and 'production deployment' that OpenAI's staged approach was designed to create.
If Astra-related security disclosures or patch advisories spike in the 30 days following this llm release, it signals the staged rollout window collapsed faster than OpenAI intended. Conversely, if enterprise adoption of Astra through llm remains muted through October, it suggests the 'critical cyber capability' designation is actually constraining uptake despite tooling availability.
Coverage we drew on
This analysis is generated by Modelwire’s editorial layer from our archive and the summary above. It is not a substitute for the original reporting. How we write it.
MentionsSimon Willison · OpenAI · GPT-6 Astra · llm
Modelwire Editorial
This synthesis and analysis was prepared by the Modelwire editorial team. We use advanced language models to read, ground, and connect the day’s most significant AI developments, providing original strategic context that helps practitioners and leaders stay ahead of the frontier.
Modelwire summarizes, we don’t republish. Simon Willison originally reported this story as “llm 0.35”. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.