# Codex can now suggest your next message: composer predictions beta **URL:** \ **Category:** Codex\ **Created:** [October 9, 2026, 8:01pm UTC](https://community.openai.com/t/codex-can-now-suggest-your-next-message-composer-predictions-beta/1404842 "2026-10-09T20:01:32Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![sps](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sps/32/7736_2.png) [@sps](https://community.openai.com/u/sps)\ **Post date:** [October 9, 2026, 8:01pm UTC](https://community.openai.com/t/codex-can-now-suggest-your-next-message-composer-predictions-beta/1404842/1 "2026-10-09T20:01:32Z")
[Composer predictions](https://help.openai.com/en/articles/20001601-composer-predictions-in-codex) are now in beta for personal ChatGPT Pro users aged 18+ in the Codex desktop app. After Codex responds, it can suggest a follow-up based on the current conversation. > **Click here for more details** > > - **Where:** Local and SSH threads with GPT-6 Astra or GPT-6.1 Sol, in all supported regions. > - **How:** Press **Tab** to accept a suggestion, review or edit it, then send. Accepting a prediction does not send it automatically. > - **Control:** Enabled by default for eligible users. Switch it off under **Settings → General → Composer → Show predictions**. > - **Cost:** During beta, generating predictions costs nothing extra and uses no Codex limits or credits. Sending a message still follows normal usage and billing. Predictions use context already in the current thread. They don’t independently retrieve memories or information from connected apps, and a suggestion won’t appear after every response. ---
**Author:** ![platypus](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/platypus/32/759972_2.png) [@platypus](https://community.openai.com/u/platypus)\ **Post date:** [October 9, 2026, 8:05pm UTC](https://community.openai.com/t/codex-can-now-suggest-your-next-message-composer-predictions-beta/1404842/3 "2026-10-09T20:05:12Z")
AI prediction for AI predictions.