!
Production integration docs · examples use router-api.mengbi-ai.net and a personal API key placeholder.
01 /
Prepare
Prepare Codex CLI with a personal Mengbi Router key and a current model ID.
Prepare 1
Use the Codex CLI configuration supported by your current installation.
npm install -g @openai/codex
codex --version02 /
Configure
Connect Codex CLI to the endpoint that matches its supported protocol.
Configure 1
Use the Codex CLI configuration supported by your current installation.
model_provider = "mengbi"
model = "gpt-5.6-sol"
model_reasoning_effort = "high"
[model_providers.mengbi]
name = "Mengbi Router"
base_url = "https://router-api.mengbi-ai.net/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"Configure 2
Use the Codex CLI configuration supported by your current installation.
export OPENAI_API_KEY="sk-mengbi-xxxxxx"
codex