bug: hangs for groq provider

Resolved 💬 4 comments Opened Apr 24, 2025 by codewithdark-git Closed Aug 7, 2025

What version of Codex is running?

0.1.2504221401

Which model were you using?

_No response_

What platform is your computer?

win32 | x64 | 10.0.22621

What steps can reproduce the bug?

I want to set up the Groq Provider to use the Groq Model. This is the command for the Groq provider with the model:

codex -m llama-4-scout-17b-16e-instruct --provide groq

Model setup

│ ↳ model: llama-4-scout-17b-16e-instruct                      │
│ ↳ provider: Groq                                             │
│ ↳ approval: suggest                                          |

Nothing is responding from the LLM. I also set up the API key.

What is the expected behavior?

_No response_

What do you see instead?

_No response_

Additional information

_No response_

View original on GitHub ↗

4 Comments

shosseini811 · 1 year ago

It shows that llama-4 is not in the list of models from groq.

!Image

codewithdark-git · 1 year ago

On my side, they don't show the model list when I use the /model command. Instead, they show me the provider list, and they don't respond to the system for errors.

!Image

shosseini811 · 1 year ago

not sure. try this:

DEBUG=1 npx codex -m llama-4-scout-17b-16e-instruct -p groq "Hello, world"

codex-maintainers · 1 year ago

Thanks for the feedback! Please try again on the latest version of Codex CLI. If the issue persists, feel free to open a new issue or contribute to the codex-rs/ implementation. More details on our project update can be found here.