AI Proxy: OpenAI SDK: Multi-provider chat routing - Plugin

OpenAI SDK: Multi-provider chat routingv3.6+

Use a single OpenAI SDK client to route chat requests to different LLM providers by defining separate Routes per provider.

Configure multiple chat Routes in Kong Gateway, each targeting a different LLM provider such as Cohere or Mistral, while using the same OpenAI-compatible SDK client. The AI Proxy plugin extracts the model name from the request path, and injects provider-specific credentials automatically. This lets you arbitrate between providers without changing client logic, using only the base URL to select a provider.

Using this configuration, you can select your desired provider using the SDK:

client = OpenAI(
base_url="http://127.0.0.1:8000/cohere"
)

Or:

client = OpenAI(
base_url="http://127.0.0.1:8000/mistral"
)

For this configuration to work properly, you need two Routes with the following configuration:

routes:
 - name: cohere-chat
   paths:
     - "~/cohere/(?<model>[^#?/]+)/chat/completions$"
   methods:
     - POST

and:

routes:
 - name: mistral-chat
   paths:
     - "~/mistral(?<model>[^#?/]+)/chat/completions$"
   methods:
     - POST

Prerequisites

Cohere account
Mistral account

Environment variables

COHERE_API_KEY: The API key to authenticate requests to Cohere.
MISTRAL_API_KEY: The API key to authenticate requests to Mistral.

Set up the plugin

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    config:
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_COHERE_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: "$(uri_captures.model)"
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_MISTRAL_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: mistral
        name: "$(uri_captures.model)"

Make the following request:

curl -i -X POST http://localhost:8001/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make the following request:

curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.

See the Konnect API reference to learn about region-specific URLs and personal access tokens.

echo "
apiVersion: configuration.konghq.com/v1
kind: KongClusterPlugin
metadata:
  name: ai-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
  labels:
    global: 'true'
config:
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$COHERE_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: '$(uri_captures.model)'
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$MISTRAL_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: mistral
    name: '$(uri_captures.model)'
plugin: ai-proxy
" | kubectl apply -f -

Prerequisite: Configure your Personal Access Token

terraform {
  required_providers {
    konnect = {
      source  = "kong/konnect"
    }
  }
}

provider "konnect" {
  personal_access_token = "$KONNECT_TOKEN"
  server_url            = "https://us.api.konghq.com/"
}

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_proxy" "my_ai_proxy" {
  enabled = true

  config = [
    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.cohere_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "openai"
        name = "$(uri_captures.model)"
      }
    }, 

    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.mistral_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "mistral"
        name = "$(uri_captures.model)"
      }
    }  ]

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}

This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.

variable "mistral_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    service: serviceName|Id
    config:
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_COHERE_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: "$(uri_captures.model)"
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_MISTRAL_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: mistral
        name: "$(uri_captures.model)"

Make sure to replace the following placeholders with your own values:

serviceName|Id: The id or name of the service the plugin configuration will target.

Make the following request:

curl -i -X POST http://localhost:8001/services/{serviceName|Id}/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

serviceName|Id: The id or name of the service the plugin configuration will target.

Make the following request:

curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/services/{serviceId}/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
serviceId: The id of the service the plugin configuration will target.

See the Konnect API reference to learn about region-specific URLs and personal access tokens.

echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: ai-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$COHERE_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: '$(uri_captures.model)'
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$MISTRAL_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: mistral
    name: '$(uri_captures.model)'
plugin: ai-proxy
" | kubectl apply -f -

Next, apply the KongPlugin resource by annotating the service resource:

kubectl annotate -n kong service SERVICE_NAME konghq.com/plugins=ai-proxy

Prerequisite: Configure your Personal Access Token

terraform {
  required_providers {
    konnect = {
      source  = "kong/konnect"
    }
  }
}

provider "konnect" {
  personal_access_token = "$KONNECT_TOKEN"
  server_url            = "https://us.api.konghq.com/"
}

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_proxy" "my_ai_proxy" {
  enabled = true

  config = [
    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.cohere_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "openai"
        name = "$(uri_captures.model)"
      }
    }, 

    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.mistral_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "mistral"
        name = "$(uri_captures.model)"
      }
    }  ]

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  service = {
    id = konnect_gateway_service.my_service.id
  }
}

This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.

variable "mistral_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    route: routeName|Id
    config:
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_COHERE_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: "$(uri_captures.model)"
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_MISTRAL_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: mistral
        name: "$(uri_captures.model)"

Make sure to replace the following placeholders with your own values:

routeName|Id: The id or name of the route the plugin configuration will target.

Make the following request:

curl -i -X POST http://localhost:8001/routes/{routeName|Id}/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

routeName|Id: The id or name of the route the plugin configuration will target.

Make the following request:

curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/routes/{routeId}/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
routeId: The id of the route the plugin configuration will target.

See the Konnect API reference to learn about region-specific URLs and personal access tokens.

echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: ai-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$COHERE_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: '$(uri_captures.model)'
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$MISTRAL_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: mistral
    name: '$(uri_captures.model)'
plugin: ai-proxy
" | kubectl apply -f -

Next, apply the KongPlugin resource by annotating the httproute or ingress resource:

kubectl annotate -n kong httproute  konghq.com/plugins=ai-proxy

kubectl annotate -n kong ingress  konghq.com/plugins=ai-proxy

Prerequisite: Configure your Personal Access Token

terraform {
  required_providers {
    konnect = {
      source  = "kong/konnect"
    }
  }
}

provider "konnect" {
  personal_access_token = "$KONNECT_TOKEN"
  server_url            = "https://us.api.konghq.com/"
}

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_proxy" "my_ai_proxy" {
  enabled = true

  config = [
    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.cohere_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "openai"
        name = "$(uri_captures.model)"
      }
    }, 

    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.mistral_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "mistral"
        name = "$(uri_captures.model)"
      }
    }  ]

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  route = {
    id = konnect_gateway_route.my_route.id
  }
}

This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.

variable "mistral_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    consumer: consumerName|Id
    config:
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_COHERE_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: "$(uri_captures.model)"
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_MISTRAL_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: mistral
        name: "$(uri_captures.model)"

Make sure to replace the following placeholders with your own values:

consumerName|Id: The id or name of the consumer the plugin configuration will target.

Make the following request:

curl -i -X POST http://localhost:8001/consumers/{consumerName|Id}/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

consumerName|Id: The id or name of the consumer the plugin configuration will target.

Make the following request:

curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/consumers/{consumerId}/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
consumerId: The id of the consumer the plugin configuration will target.

See the Konnect API reference to learn about region-specific URLs and personal access tokens.

echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: ai-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$COHERE_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: '$(uri_captures.model)'
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$MISTRAL_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: mistral
    name: '$(uri_captures.model)'
plugin: ai-proxy
" | kubectl apply -f -

Next, apply the KongPlugin resource by annotating the KongConsumer resource:

kubectl annotate -n kong  CONSUMER_NAME konghq.com/plugins=ai-proxy

Prerequisite: Configure your Personal Access Token

terraform {
  required_providers {
    konnect = {
      source  = "kong/konnect"
    }
  }
}

provider "konnect" {
  personal_access_token = "$KONNECT_TOKEN"
  server_url            = "https://us.api.konghq.com/"
}

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_proxy" "my_ai_proxy" {
  enabled = true

  config = [
    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.cohere_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "openai"
        name = "$(uri_captures.model)"
      }
    }, 

    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.mistral_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "mistral"
        name = "$(uri_captures.model)"
      }
    }  ]

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  consumer = {
    id = konnect_gateway_consumer.my_consumer.id
  }
}

This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.

variable "mistral_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    consumer_group: consumerGroupName|Id
    config:
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_COHERE_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: "$(uri_captures.model)"
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${{ env "DECK_MISTRAL_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: mistral
        name: "$(uri_captures.model)"

Make sure to replace the following placeholders with your own values:

consumerGroupName|Id: The id or name of the consumer group the plugin configuration will target.

Make the following request:

curl -i -X POST http://localhost:8001/consumer_groups/{consumerGroupName|Id}/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

consumerGroupName|Id: The id or name of the consumer group the plugin configuration will target.

Make the following request:

curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/consumer_groups/{consumerGroupId}/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": [
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$COHERE_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "openai",
            "name": "$(uri_captures.model)"
          }
        },
        {
          "route_type": "llm/v1/chat",
          "auth": {
            "header_name": "Authorization",
            "header_value": "'$MISTRAL_API_KEY'"
          },
          "logging": {
            "log_statistics": true,
            "log_payloads": false
          },
          "model": {
            "provider": "mistral",
            "name": "$(uri_captures.model)"
          }
        }
      ]
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
consumerGroupId: The id of the consumer group the plugin configuration will target.

See the Konnect API reference to learn about region-specific URLs and personal access tokens.

echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: ai-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$COHERE_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: '$(uri_captures.model)'
- route_type: llm/v1/chat
  auth:
    header_name: Authorization
    header_value: '$MISTRAL_API_KEY'
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: mistral
    name: '$(uri_captures.model)'
plugin: ai-proxy
" | kubectl apply -f -

Next, apply the KongPlugin resource by annotating the KongConsumerGroup resource:

kubectl annotate -n kong  CONSUMERGROUP_NAME konghq.com/plugins=ai-proxy

Prerequisite: Configure your Personal Access Token

terraform {
  required_providers {
    konnect = {
      source  = "kong/konnect"
    }
  }
}

provider "konnect" {
  personal_access_token = "$KONNECT_TOKEN"
  server_url            = "https://us.api.konghq.com/"
}

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_proxy" "my_ai_proxy" {
  enabled = true

  config = [
    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.cohere_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "openai"
        name = "$(uri_captures.model)"
      }
    }, 

    {
      route_type = "llm/v1/chat"

      auth = {
        header_name = "Authorization"
        header_value = var.mistral_api_key
      }

      logging = {
        log_statistics = true
        log_payloads = false
      }

      model = {
        provider = "mistral"
        name = "$(uri_captures.model)"
      }
    }  ]

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  consumer_group = {
    id = konnect_gateway_consumer_group.my_consumer_group.id
  }
}

This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.

variable "mistral_api_key" {
  type = string
}

AI Proxy

OpenAI SDK: Multi-provider chat routingv3.6+

Prerequisites

Environment variables

Set up the plugin

Help us make these docs great!

Still need help