On Oct 9 OpenAI opened composer predictions in beta in the Codex desktop app for personal ChatGPT Pro users. After each response Codex may prefill your next message from the current thread; press Tab to accept and edit before sending. Local and SSH threads only, with GPT-6 Astra and GPT-6.1 Sol; generating predictions does not count toward usage limits during the beta.
Key Takeaways
- ✓Personal ChatGPT Pro (18+), Codex desktop app, local and SSH threads only
- ✓Supported models: GPT-6 Astra and GPT-6.1 Sol
- ✓Predictions are free during beta; sent messages bill normally
- ✓Tab accepts without sending; disable via Settings → General → Composer → Show predictions
- ✓Announcement post: ~3,250 likes and ~230K views within hours
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
OpenAI shipped composer predictions in beta in the Codex desktop app on Oct 9, 2026. After Codex finishes a response it may prefill a complete suggested next message based on the current thread and how you talk to it. Press Tab to accept, edit, then send; nothing is sent automatically and predictions never advance a task on their own. Availability: personal ChatGPT Pro accounts (18+), local and SSH threads, GPT-6 Astra and GPT-6.1 Sol only. Predictions use only the current thread's context and do not query memory or connected apps themselves. During the beta, generating predictions is free and does not count toward Codex usage limits; sent messages bill normally. Turn it off under Settings → General → Composer → Show predictions. OpenAI published no accuracy or acceptance-rate metrics.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.