openrouter model_reasoning_effort config not work

Resolved 💬 2 comments Opened Oct 10, 2025 by anthod0 Closed Nov 15, 2025
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

codex-cli 0.46.0

Which model were you using?

openai/gpt-5-codex

What platform is your computer?

Linux 6.8.0-65-generic x86_64 x86_64

What steps can reproduce the bug?

When using the following configuration, the reasoning field sent to the openrouter endpoint is null

model= "openai/gpt-5-codex"
model_provider="openrouter-responses"
# not work
model_reasoning_effort = "high"

[model_providers.openrouter-responses]
name="openrouter responses API"
base_url="https://openrouter.ai/api/alpha"
wire_api = "responses"
env_key="OPENROUTER_API_KEY"

RUST_LOG=codex_core=trace,codex_tui=trace codex

What is the expected behavior?

_No response_

What do you see instead?

_No response_

Additional information

_No response_

View original on GitHub ↗

2 Comments

github-actions[bot] contributor · 10 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #5002

Powered by Codex Action

etraut-openai contributor · 9 months ago

Closing in favor of #2387