Configure the AI Proxy Advanced plugin with multiple targets, each with a unique model_alias. When a request arrives, Kong matches the model field in the body to the alias and routes to the corresponding target.
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 quickstart script to automatically provision a Control Plane and Data Plane, and configure your environment:
curl -Ls https://get.konghq.com/quickstart | bash -s -- -k $KONNECT_TOKEN --deck-output
This sets up a Konnect Control Plane named quickstart, provisions a local Data Plane, and prints out the following environment variable exports:
export DECK_KONNECT_TOKEN=$KONNECT_TOKEN
export DECK_KONNECT_CONTROL_PLANE_NAME=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.
This tutorial requires Kong Gateway Enterprise. If you don’t have Kong Gateway set up yet, you can use the quickstart script with an enterprise license to get an instance of Kong Gateway running almost instantly.
Export your license to an environment variable:
export KONG_LICENSE_DATA='LICENSE-CONTENTS-GO-HERE'
Run the quickstart script:
curl -Ls https://get.konghq.com/quickstart | bash -s -- -e KONG_LICENSE_DATA
Once Kong Gateway is ready, you will see the following message:
Kong Gateway Ready
decK is a CLI tool for managing Kong Gateway declaratively with state files. To complete this tutorial, install decK version 1.43 or later.
This guide uses deck gateway apply, which directly applies entity configuration to your Gateway instance.
We recommend upgrading your decK installation to take advantage of this tool.
You can check your current decK version with deck version.
For this tutorial, you’ll need Kong Gateway entities, like Gateway Services and Routes, pre-configured. These entities are essential for Kong Gateway to function but installing them isn’t the focus of this guide. Follow these steps to pre-configure them:
Run the following command:
echo '
_format_version: "3.0"
services:
- name: example-service
url: http://httpbin.konghq.com/anything
routes:
- name: example-route
paths:
- "/anything"
service:
name: example-service
protocols:
- http
- https
' | deck gateway apply -
To learn more about entities, you can read our entities documentation.
This tutorial uses OpenAI:
Create a decK variable with the API key:
export DECK_OPENAI_API_KEY='YOUR OPENAI API KEY'
The model_alias field on each target lets you decouple the model name clients send from the actual provider model. Clients request a logical name like powerful or fast, and Kong Gateway routes to the matching upstream model.
Configure the AI Proxy Advanced plugin with two targets, each mapped to a different OpenAI model through a model_alias:
echo '
_format_version: "3.0"
plugins:
- name: ai-proxy-advanced
config:
targets:
- route_type: llm/v1/chat
auth:
header_name: Authorization
header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
model:
provider: openai
name: gpt-4o
model_alias: powerful
- route_type: llm/v1/chat
auth:
header_name: Authorization
header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
model:
provider: openai
name: gpt-4o-mini
model_alias: fast
' | deck gateway apply -
When a client sends "model": "powerful" in the request body, Kong Gateway matches it to the first target and routes the request to gpt-4o. A request with "model": "fast" routes to gpt-4o-mini.
Send a request with "model": "powerful" to verify that Kong Gateway routes it to gpt-4o:
curl -X POST "$KONNECT_PROXY_URL/anything" \
--no-progress-meter --fail-with-body \
-H "Accept: application/json"\
-H "Content-Type: application/json" \
--json '{
"model": "powerful",
"messages": [
{
"role": "user",
"content": "What is 1+1?"
}
]
}'
curl -X POST "http://localhost:8000/anything" \
--no-progress-meter --fail-with-body \
-H "Accept: application/json"\
-H "Content-Type: application/json" \
--json '{
"model": "powerful",
"messages": [
{
"role": "user",
"content": "What is 1+1?"
}
]
}'
Send a second request with "model": "fast" to confirm routing to gpt-4o-mini:
curl -X POST "$KONNECT_PROXY_URL/anything" \
--no-progress-meter --fail-with-body \
-H "Accept: application/json"\
-H "Content-Type: application/json" \
--json '{
"model": "fast",
"messages": [
{
"role": "user",
"content": "What is 1+1?"
}
]
}'
curl -X POST "http://localhost:8000/anything" \
--no-progress-meter --fail-with-body \
-H "Accept: application/json"\
-H "Content-Type: application/json" \
--json '{
"model": "fast",
"messages": [
{
"role": "user",
"content": "What is 1+1?"
}
]
}'
Both requests use the same Route. Check the model field in the JSON response object to confirm which upstream model handled each request. The provider sets this field, so it reflects the actual model used (gpt-4o or gpt-4o-mini), regardless of the alias the client sent.
If you created a new control plane and want to conserve your free trial credits or avoid unnecessary charges, delete the new control plane used in this tutorial.
curl -Ls https://get.konghq.com/quickstart | bash -s -- -d