2026-11-02 · MondayPublished daily at 08:00
AI Daily
OpenAI to combine ChatGPT and Codex into a single token allowance starting in December

The author cites OpenAI’s help documentation, updated early in the morning, which says that starting in December, Plus and Pro users’ ChatGPT conversations and Codex usage will share a single token allowance; Instant chats will be unaffected. The author looks back at the earlier per-message billing model, the operational back-and-forth in which Codex Pro’s allowance was first reduced and then restored within a month, and the community’s response, including filing protest issues on GitHub. The author argues that the change is related to computing-cost pressures amid IPO expectations.
- 1
- 2
01Industry News
OpenAI to combine ChatGPT and Codex into a single token allowance starting in December
The author cites OpenAI’s help documentation, updated early in the morning, which says that starting in December, Plus and Pro users’ ChatGPT conversations and Codex usage will share a single token allowance; Instant chats will be unaffected. The author looks back at the earlier per-message billing model, the operational back-and-forth in which Codex Pro’s allowance was first reduced and then restored within a month, and the community’s response, including filing protest issues on GitHub. The author argues that the change is related to computing-cost pressures amid IPO expectations.
Original text02Tips and perspectives
OpenRouter tutorial: Build an AI code review script that verifies bugs in a Linux sandbox using the Responses API
OpenRouter published a tutorial introducing review.py, a 233-line script that uses only the standard library. It combines the Files API, Shell sandbox tool, and Apply Patch tool through the Responses API to upload changed files to a hosted Linux sandbox, have the model run checks to confirm bugs, and return V4A patches.
Original textClaude Code tip: Type ultrathink when a task gets harder to increase reasoning effort for the current turn
Addy Osmani shared a Claude Code tip: when a task is harder than expected, type ultrathink while Claude is working to increase reasoning effort for the remainder of that turn. This feature is available in the latest version of the terminal. He cited a post by @dmwlff, which noted that ultrathink has returned to the Claude Code CLI after being disabled because it seemed odd and potentially confusing.
Original text