Set up AI Proxy to route requests to Cohere, use a custom Lua function to count tokens via the x-prompt-count header, and enforce usage limits with Redis-based rate limiting.
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
' | deck gateway apply -
To learn more about entities, you can read our entities documentation.
For this task, you need an Anthropic API key.
export DECK_COHERE_API_KEY='COHERE API KEY'
To complete this tutorial, make sure you have the following:
6379, or your custom Redis port is open and reachable from Kong.Redis host set as an environment variable so the plugin can connect:
export DECK_REDIS_HOST='YOUR-REDIS-HOST'
If you’re testing locally with Docker, use
host.docker.internalas the host value.
Enable the AI Proxy plugin with your Cohere API key and the model details to proxy requests to Cohere. In this example, we’ll use the command-a-03-2025 model.
echo '
_format_version: "3.0"
plugins:
- name: ai-proxy
config:
route_type: llm/v1/chat
auth:
header_name: Authorization
header_value: Bearer ${{ env "DECK_COHERE_API_KEY" }}
model:
provider: cohere
name: command-a-03-2025
options:
max_tokens: 512
temperature: 1.0
' | deck gateway apply -
Now, configure the AI Rate Limiting Advanced plugin. This configuration enforces usage limits on AI model requests by tracking token consumption through a custom Lua function. Rate limit counters are stored in Redis, and the x-prompt-count HTTP header is used to count tokens per request. This setup helps prevent quota overruns and protects your AI infrastructure from excessive usage.
echo '
_format_version: "3.0"
plugins:
- name: ai-rate-limiting-advanced
config:
strategy: redis
redis:
host: "${{ env "DECK_REDIS_HOST" }}"
port: 16379
sync_rate: 0
llm_providers:
- name: cohere
limit:
- 100
- 1000
window_size:
- 60
- 3600
request_prompt_count_function: |
local header_count = tonumber(kong.request.get_header("x-prompt-count"))
if header_count then
return header_count
end
return 0
' | deck gateway apply -
Now, you can test the rate limiting configuration.
x-prompt-count of 100000, which is within the configured token limits and should receive a 200 OK response.x-prompt-count of 950000, exceeds the allowed token quota and is expected to return a 429 response.curl -i -X POST "$KONNECT_PROXY_URL/anything" \
--no-progress-meter --fail-with-body \
-H "Content-Type: application/json"\
-H "x-prompt-count: 100000" \
--json '{
"messages": [
{
"role": "system",
"content": "You are an IT specialist."
},
{
"role": "user",
"content": "Tell me about Google?"
}
]
}'
You should see the following response:
HTTP/1.1 200 OK
curl -i -X POST "http://localhost:8000/anything" \
--no-progress-meter --fail-with-body \
-H "Content-Type: application/json"\
-H "x-prompt-count: 100000" \
--json '{
"messages": [
{
"role": "system",
"content": "You are an IT specialist."
},
{
"role": "user",
"content": "Tell me about Google?"
}
]
}'
You should see the following response:
HTTP/1.1 200 OK
Now, you can test the rate limiting function by sending the following request:
curl -i -X POST "$KONNECT_PROXY_URL/anything" \
--no-progress-meter --fail-with-body \
-H "Content-Type: application/json"\
-H "x-prompt-count: 950000" \
--json '{
"messages": [
{
"role": "system",
"content": "You are an IT specialist."
},
{
"role": "user",
"content": "Tell me about Google?"
}
]
}'
You should see the following response:
HTTP/1.1 429 AI token rate limit exceeded for provider(s): cohere
curl -i -X POST "http://localhost:8000/anything" \
--no-progress-meter --fail-with-body \
-H "Content-Type: application/json"\
-H "x-prompt-count: 950000" \
--json '{
"messages": [
{
"role": "system",
"content": "You are an IT specialist."
},
{
"role": "user",
"content": "Tell me about Google?"
}
]
}'
You should see the following response:
HTTP/1.1 429 AI token rate limit exceeded for provider(s): cohere
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