code 400
Resolved 💬 2 comments Opened Dec 17, 2025 by aliaxy Closed Mar 29, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
codex-cli 0.73.0
What subscription do you have?
3rd party, my company built
Which model were you using?
_No response_
What platform is your computer?
Darwin 25.2.0 arm64 arm
What issue are you seeing?
{"error":{"message":"Input required: specify \"prompt\" or
\"messages\"","code":400},"user_id":"user_2mgbKxUuNB4ks4PEmPZ2kbBiwq5"}
What steps can reproduce the bug?
config.toml
model_provider = "xxxx"
model = "gpt-5.2"
preferred_auth_method = "apikey"
[model_providers.xxxx]
name = "xxxx"
base_url = "https://api.xxxxxx.cn/v1"
env_key = "xxxxxx_API_KEY"
wire_api = "responses"What is the expected behavior?
_No response_
Additional information
_No response_
2 Comments
This indicates that the
responsesendpoint that you're accessing is returning a 400 error. I can't tell from your config which endpoint that is because you've redacted it. Are you pointing at an internal LLM proxy server? The problem is likely in the implementation of that endpoint.Incidentally, the
preferred_auth_methodconfig key is no longer supported. It was removed about two months ago.This bug report hasn't received any upvotes or additional posts in three months. Closing.