OpenAI · 2026-10-27 · notable
Codex CLI 0.165.0 — built-in Vertex AI provider and GPT-6.1 Terra
Codex CLI 0.165.0 adds a built-in Google Cloud Vertex AI provider, puts GPT-6.1 Terra in the model catalog, turns on memory v2 for new profiles and lets users change reasoning effort mid-conversation by default.
Codex can now run on Google Cloud Vertex AI out of the box and picks up OpenAI's new Terra model.
What is it?
A built-in Google Cloud Vertex AI provider is the headline of Codex CLI 0.165.0, selected with model_provider = "gcp". GPT-6.1 Terra joins the model catalogs, and reasoning effort can now be changed mid-conversation by default on supported models.
How does it work?
Memory v2 is now on by default for new profiles and can import memories from other agents. The session picker gains a repository filter, and the agent command center groups sessions by directory, which helps when working across linked worktrees. The app-server API also gets experimental attached thread forks.
Why does it matter?
Teams that buy models through Google Cloud can point Codex at Vertex AI without a custom provider config. The release also closes a marketplace URL check gap that could let Git connect to a different host than the one validated, and stops retries when a provider reports a model as not found.
Who is it for?
developers who use the Codex agent in the terminal, especially on Google Cloud
Try it
npm i -g @openai/codex@0.165.0