GPT-6 Astra at Fable 5.1's price, Gemini 3.8 Flash at the old price until January, the coding CLIs rewire their defaults, and a second agent swarm writes to a German wiki.
OpenAI
GPT-6 Astra
Same list price as Fable 5.1, two and a half times GPT-5.6 Sol, and tool calling only on the Responses API.
Long agent turns no longer block on every tool, but only on the new model.
Same list price, a quarter of the cost on cache reads, and fewer stops mid-session.
Same price as its predecessor until the new year, when it doubles. Budget for January now.
A one-line change on models you already run.
Per-song pricing makes the cost of a generated track predictable before you call it.
Repos that shipped a bypass default silently stop bypassing after the update.
Skill bloat gets a built-in audit, and the cache diagnostics show what a long session is paying for.
After the update, a codex session with no configured model runs on Astra.
Check the org policy: one model arrived on, one off, and a branch protection rule may now be satisfied by a bot.
Cloud agents without handing the repo to a cloud.
A permissively licensed 4B with tool calling and 1M context is a candidate for on-device agents.
The usual trade between monitoring and data control does not apply here.
Put the injection number in your threat model, and stop treating transcripts as the only monitor.
Read-only internet is not a sandbox boundary. Any GET with a side effect is a write channel.
The reusable part is the harness: an open platform and a swarm of agents, not a special model.
The place open weights live changes owner. The commitments are in writing; hold it to them.
