Running Codex on top of OpenRouter

codex-openrouter-gist.md

Running Codex on top of OpenRouter

Codex CLI supports custom model providers, so you can point it at OpenRouter instead of the default OpenAI endpoint.

Wrapper script

#!/bin/bash
set -euo pipefail

export OPENROUTER_API_KEY=`keyring get codex openrouter-key`

exec npx @openai/codex \
  -c 'model_provider="openrouter"' \
  -c 'model="openai/gpt-5-codex"' \
  -c 'model_providers.openrouter.name="OpenRouter"' \
  -c 'model_providers.openrouter.base_url="https://openrouter.ai/api/v1"' \
  -c 'model_providers.openrouter.env_key="OPENROUTER_API_KEY"' \
  -c 'model_providers.openrouter.wire_api="responses"' \
  "$@"

Save that as ~/bin/codex, then make it executable:

chmod +x ~/bin/codex

Notes

• model_provider="openrouter" tells Codex to use the custom provider.
• base_url="https://openrouter.ai/api/v1" points Codex to OpenRouter's OpenAI-compatible API.
• env_key="OPENROUTER_API_KEY" tells Codex which environment variable contains the bearer token.
• model="openai/gpt-5-codex" is just a default; swap it for any OpenRouter model that supports the Responses API.

Then run:

codex