gpt-4o reports token limit error of 4096 tokens
Bug report
Thanks for filing an issue! Please answer the questions below so I can help you.
- iTerm2 version: 3.50
- OS version: MacOS 14.5
- Attach
[com.googlecode.iterm2.plist](/uploads/9ed8a4c0f3b5f8c847efba4fb005f624/com.googlecode.iterm2.plist)com.googlecode.iterm2.plist
here (drag-drop from finder into this window) - Attach a debug log, if possible.
- Attach a screen capture video if it would make the reproduction steps clearer.
PLEASE ATTACH YOUR PLIST FILE FOR BUG REPORTS! Seriously! I'll probably ask you for it if you don’t.
Detailed steps to reproduce the problem
- Set AI model to gpt-4o
- use the AI assistant
What happened
Get error:
There was a problem with the AI query: Error from OpenAI: max_tokens is too large: 127819. This model supports at most 4096 completion tokens, whereas you provided 127819.
What should have happened
gpt-4o has as token size of 128k. It should have be fine. It's probably using the wrong model underneath the hood.
It works fine with gpt-4-turbo
Thanks for the AMAZING work! Love this.