5 people reported
All time, since Sep 30, including 4 thumbs-up on GitHub.
High starting context usage
“The GPT-6.1 Sol thread therefore starts with roughly 160k+ additional context usage compared with the other models.”
Is this your bug? What gets counted gets fixed. Pile on.
Paste this into your agent. It files your report, with your error and version.
I hit this bug: rapsheet.dev/sheets/codex/issues/14721/file Follow it to file my report. Show me the text before you send.
No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends
Fresh GPT-6.1 Sol threads start at about 80% context. A new thread showed about 208k / 258k tokens after a prompt asking only for OK; GPT-6 Sol and GPT-6 Astra showed about 40k.
Is this your bug?
File my report- Where
- Codex Desktop
- Platforms
- Windows
- How bad
- Breaks a normal workflow.
Not quite your bug?
Original reports1, newest first
- [Codex Desktop] GPT-6.1 Sol starts fresh threads at ~208k/258k context while GPT-6 Sol/Astra start at ~40kOn GitHub#49641