404 Not Found: model 'gpt-5.5' not found after connecting to Ollama

Open 💬 1 comment Opened Jun 30, 2026 by baek-seunghwan

What version of the Codex App are you using (From “About Codex” dialog)?

26.519.81530

What subscription do you have?

Plus

What platform is your computer?

macOS

What issue are you seeing?

I am getting a 404 Not Found: model 'gpt-5.5' not found error pointing to the local Ollama URL (http://127.0.0.1:11434/v1/responses) right after connecting to Ollama.

What steps can reproduce the bug?

  1. Connect the app to Ollama.
  2. Attempt to initialize or use the model.
  3. The connection fails with the 404 error looking for 'gpt-5.5' on the local server.

What is the expected behavior?

It should correctly route requests or map to the locally available Ollama models instead of searching for a non-existent 'gpt-5.5' model on the local host.

Additional information

_No response_

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗