OpenAI Codex rust-v0.165.0

Codex rust-v0.165.0 adds a built-in Google Cloud Vertex AI provider, adds GPT-6.1 Terra to the model catalogs, and turns on memory v2 and mid-conversation reasoning-effort changes by default.

Why it matters

For developers using OpenAI's Codex coding agent, especially teams on Google Cloud, who can now point Codex at Vertex AI without a custom provider setup.

What's new

• New built-in Google Cloud Vertex AI provider, configured with model_provider = "gcp".
• GPT-6.1 Terra is now in the model catalogs.
• Memory v2 is on by default for fresh profiles and can import memories from other agents.
• Reasoning effort can now be changed during a conversation by default on supported models.
• Fixes include queued agent messages no longer restarting work after an interrupt or a switch to Plan mode, and a closed marketplace URL validation gap that could let Git reach a different host than the one checked.

Taken from the project's own release notes. Claims about speed or accuracy are the maker's unless stated otherwise.

Quick facts

Links

• Official site: https://developers.openai.com/codex
• Repository: https://github.com/openai/codex
• Release notes: https://github.com/openai/codex/releases/tag/rust-v0.165.0
• Docs: https://developers.openai.com/codex/ide

Related ranking

See how established tools compare in Best AI Coding Tools for Developers. New releases aren't scored until we review them against the rubric.

What we couldn't verify

• quick_facts.pricing (plan list carried from the earlier release, not re-checked)

Checked 2026-10-28 from the release notes's own pages. Prices and star counts change, so confirm on the official site. Listing here is not a ranking or an endorsement.