export OPENAI_BASE_URL=http://localhost:8000/qwen/chat/completions
qwen --model "my-qwen-openai" --auth-type "openai"And ask a question to confirm that requests reach AI Gateway.
Explain the singleton pattern in Python.Route Qwen Code CLI traffic through AI Gateway and OpenAI
Incompatible with
on-prem
Related Documentation
Related Resources
Minimum Version
AI Gateway - 2.0
TL;DR
Create an AI Model Provider for OpenAI and an AI Model with the generate capability, then point Qwen Code CLI’s OPENAI_BASE_URL at your local AI Gateway endpoint so all requests pass through the gateway for monitoring and control.
Prerequisites
AI Gateway running
This is a Konnect tutorial and requires a Konnect personal access token.
-
Create a new personal access token by opening the Konnect PAT page and selecting Generate Token.
-
Export your token to an environment variable:
export KONNECT_TOKEN='YOUR_KONNECT_PAT' -
Run the AI Gateway quickstart script to automatically provision a control plane and data plane in Kong Konnect, and configure your environment:
curl -Ls https://get.konghq.com/ai | bash -s -- -k $KONNECT_TOKEN
This sets up a AI Gateway control plane named ai-quickstart, provisions a local data plane, and prints out the following environment variables export:
export AI_GATEWAY_ID=your-gateway-id
export KONNECT_TOKEN=$KONNECT_TOKEN
export KONNECT_CONTROL_PLANE_NAME=ai-quickstart
export KONNECT_CONTROL_PLANE_URL=https://us.api.konghq.com
export KONNECT_PROXY_URL='http://localhost:8000'Copy and paste these into your terminal to configure your session.
kongctl v1.13.0+
This tutorial uses kongctl to manage Konnect resources programmatically. We recommend keeping kongctl up to date with the latest version (1.13.0).
- Install kongctl from developer.konghq.com/kongctl.
-
Verify the installation:
kongctl version
OpenAI API key
- Create an OpenAI account.
- Get an API key.
- Export the API key as a variable:
export OPENAI_API_KEY='<YOUR_OPENAI_API_KEY>' export OPENAI_AUTH_HEADER='Bearer $OPENAI_API_KEY'
Qwen Code CLI
Install Node.js 18+ (verify with node --version), then install the Qwen Code CLI:
npm install -g @qwen-code/qwen-codeCreate an AI Model Provider and AI Model
Qwen Code CLI speaks OpenAI’s Chat Completions format natively.
Create an AI Model Provider entity to define your connection and store your authentication credentials.
Create an AI Model entity to declare which upstream models are available, configure how client requests are routed, and specify which AI Model Provider to use.
kongctl apply -f - --auto-approve --pat "$KONNECT_TOKEN" << 'EOF'
ai_gateway_model_providers:
- ref: generic-openai
ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
name: generic-openai
display_name: "generic-openai"
type: openai
config:
auth:
type: basic
headers:
- name: Authorization
value: !secret {source: !env OPENAI_AUTH_HEADER}
ai_gateway_models:
- ref: my-qwen-openai
ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
name: my-qwen-openai
display_name: "my-qwen-openai"
type: model
formats: [{ type: openai }]
config:
route:
paths: [/qwen]
model:
body_param: model
values: [my-qwen-openai]
targets:
- name: gpt-5-mini
provider: generic-openai
config:
type: openai
capabilities: [generate]
EOFThis example uses the following settings:
-
targets: Sends requests togpt-5-minithrough thegeneric-openaiprovider. -
capabilities: [generate]: Exposes the model at a/qwen/chat/completionsendpoint.
Run Qwen Code CLI
Run Qwen Code CLI against the model configured in the AI Model entity’s targets:
Qwen Code CLI returns a response, proxied through AI Gateway to the OpenAI model.
The Qwen Code CLI requires
OPENAI_API_KEYto be set even though the real key lives on the AI Gateway.
Cleanup
Clean up AI Gateway resources
To clean up all AI Gateway resources created in this guide, run:
curl -Ls https://get.konghq.com/ai | bash -s -- -d