LLM inferencev3.14+
Enable the VeriKnox plugin on a Route that proxies OpenAI-compatible LLM inference traffic.
The plugin intercepts requests to the upstream LLM provider, applies VeriKnox Hub policy, and forwards a cryptographically signed receipt to VeriKnox Hub before the request is proxied. A signed response receipt is sent after the upstream responds.
The agent_passphrase must be a Vault reference. Don’t set it as a plain string.
The data plane must be enrolled with VeriKnox Hub before the plugin can sign receipts.
See the installation instructions for enrollment steps.
The http_session_header field is optional. When set, the plugin attaches the value
of that request header to receipts as a session ID, which is useful for grouping
multi-turn conversations in VeriKnox Hub audit logs.
sequenceDiagram
autonumber
participant A as AI Agent / Client
participant K as AI Gateway
(veriknox-plugin)
participant H as VeriKnox Hub
participant U as Upstream LLM
(e.g. OpenAI, Anthropic,
OpenRouter, Google Gemini)
A->>K: Send inference request
Note over K: Parse request body
(prompt, model, messages)
K->>H: POST signed receipt — inference request
(ED25519 + ML-DSA-65 signatures)
H-->>K: 200 OK (receipt accepted)
K->>U: Forward request upstream
U-->>K: Return inference response
Note over K: Parse response body
(completion text, token usages)
K->>H: POST signed receipt — inference response
(ED25519 + ML-DSA-65 signatures)
H-->>K: 200 OK (receipt accepted)
K-->>A: Return response to client
Prerequisites
-
The VeriKnox plugin is installed and the data plane is enrolled with VeriKnox Hub.
-
The identity passphrase is stored in a Kong Vault. Reference it as
{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}or the equivalent path for your vault backend. -
The upstream LLM provider Route exists in Kong Gateway.
Environment variables
-
VERIKNOX_PROVIDER_NAME: A logical name for the upstream provider used in audit receipts. For example:OpenAIorAnthropic. -
{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}: Vault reference to the identity passphrase. Replaceveriknoxwith your vault prefix if different. -
https://hub.veriknox.ai: Base URL of your VeriKnox Hub instance. The default value ishttps://hub.veriknox.ai. -
VERIKNOX_SESSION_HEADER: Name of the HTTP header to extract a session ID from. For example:X-Session-Id. Omit this variable to leave the field unset.
Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: veriknox
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: ${{ env "DECK_VERIKNOX_PROVIDER_NAME" }}
agent_passphrase: ${{ env "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}" }}
veriknox_hub:
base_url: ${{ env "https://hub.veriknox.ai" }}
http_session_header: ${{ env "DECK_VERIKNOX_SESSION_HEADER" }}Make the following request:
curl -i -X POST http://localhost:8001/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'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 $KONNECT_TOKEN" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongClusterPlugin
metadata:
name: veriknox
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
labels:
global: 'true'
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: '$VERIKNOX_PROVIDER_NAME'
agent_passphrase: '{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}'
veriknox_hub:
base_url: https://hub.veriknox.ai
http_session_header: '$VERIKNOX_SESSION_HEADER'
plugin: veriknox
" | kubectl apply -f -Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_veriknox" "my_veriknox" {
enabled = true
config = {
endpoint = {
specification = "Inference:OpenAI/Chat_Completions"
provider = var.veriknox_provider_name
}
agent_passphrase = var.{vault://veriknox/veriknox_identity_passphrase}
veriknox_hub = {
base_url = var.https://hub.veriknox.ai
}
http_session_header = var.veriknox_session_header
}
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 "veriknox_session_header" {
type = string
}Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: veriknox
service: serviceName|Id
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: ${{ env "DECK_VERIKNOX_PROVIDER_NAME" }}
agent_passphrase: ${{ env "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}" }}
veriknox_hub:
base_url: ${{ env "https://hub.veriknox.ai" }}
http_session_header: ${{ env "DECK_VERIKNOX_SESSION_HEADER" }}Make sure to replace the following placeholders with your own values:
-
serviceName|Id: Theidornameof the service the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/services/{serviceName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
serviceName|Id: Theidornameof 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 $KONNECT_TOKEN" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane. -
serviceId: Theidof the service the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: veriknox
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: '$VERIKNOX_PROVIDER_NAME'
agent_passphrase: '{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}'
veriknox_hub:
base_url: https://hub.veriknox.ai
http_session_header: '$VERIKNOX_SESSION_HEADER'
plugin: veriknox
" | kubectl apply -f -Next, apply the KongPlugin resource by annotating the service resource:
kubectl annotate -n kong service SERVICE_NAME konghq.com/plugins=veriknoxPrerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_veriknox" "my_veriknox" {
enabled = true
config = {
endpoint = {
specification = "Inference:OpenAI/Chat_Completions"
provider = var.veriknox_provider_name
}
agent_passphrase = var.{vault://veriknox/veriknox_identity_passphrase}
veriknox_hub = {
base_url = var.https://hub.veriknox.ai
}
http_session_header = var.veriknox_session_header
}
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 "veriknox_session_header" {
type = string
}Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: veriknox
route: routeName|Id
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: ${{ env "DECK_VERIKNOX_PROVIDER_NAME" }}
agent_passphrase: ${{ env "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}" }}
veriknox_hub:
base_url: ${{ env "https://hub.veriknox.ai" }}
http_session_header: ${{ env "DECK_VERIKNOX_SESSION_HEADER" }}Make sure to replace the following placeholders with your own values:
-
routeName|Id: Theidornameof the route the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/routes/{routeName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
routeName|Id: Theidornameof 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 $KONNECT_TOKEN" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane. -
routeId: Theidof the route the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: veriknox
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: '$VERIKNOX_PROVIDER_NAME'
agent_passphrase: '{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}'
veriknox_hub:
base_url: https://hub.veriknox.ai
http_session_header: '$VERIKNOX_SESSION_HEADER'
plugin: veriknox
" | kubectl apply -f -Next, apply the KongPlugin resource by annotating the httproute or ingress resource:
kubectl annotate -n kong httproute konghq.com/plugins=veriknoxkubectl annotate -n kong ingress konghq.com/plugins=veriknoxPrerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_veriknox" "my_veriknox" {
enabled = true
config = {
endpoint = {
specification = "Inference:OpenAI/Chat_Completions"
provider = var.veriknox_provider_name
}
agent_passphrase = var.{vault://veriknox/veriknox_identity_passphrase}
veriknox_hub = {
base_url = var.https://hub.veriknox.ai
}
http_session_header = var.veriknox_session_header
}
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 "veriknox_session_header" {
type = string
}Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: veriknox
consumer: consumerName|Id
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: ${{ env "DECK_VERIKNOX_PROVIDER_NAME" }}
agent_passphrase: ${{ env "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}" }}
veriknox_hub:
base_url: ${{ env "https://hub.veriknox.ai" }}
http_session_header: ${{ env "DECK_VERIKNOX_SESSION_HEADER" }}Make sure to replace the following placeholders with your own values:
-
consumerName|Id: Theidornameof the consumer the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/consumers/{consumerName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
consumerName|Id: Theidornameof 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 $KONNECT_TOKEN" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane. -
consumerId: Theidof the consumer the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: veriknox
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: '$VERIKNOX_PROVIDER_NAME'
agent_passphrase: '{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}'
veriknox_hub:
base_url: https://hub.veriknox.ai
http_session_header: '$VERIKNOX_SESSION_HEADER'
plugin: veriknox
" | kubectl apply -f -Next, apply the KongPlugin resource by annotating the KongConsumer resource:
kubectl annotate -n kong kongconsumer CONSUMER_NAME konghq.com/plugins=veriknoxPrerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_veriknox" "my_veriknox" {
enabled = true
config = {
endpoint = {
specification = "Inference:OpenAI/Chat_Completions"
provider = var.veriknox_provider_name
}
agent_passphrase = var.{vault://veriknox/veriknox_identity_passphrase}
veriknox_hub = {
base_url = var.https://hub.veriknox.ai
}
http_session_header = var.veriknox_session_header
}
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 "veriknox_session_header" {
type = string
}Add this section to your kong.yaml configuration file:
_format_version: "3.0"
plugins:
- name: veriknox
consumer_group: consumerGroupName|Id
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: ${{ env "DECK_VERIKNOX_PROVIDER_NAME" }}
agent_passphrase: ${{ env "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}" }}
veriknox_hub:
base_url: ${{ env "https://hub.veriknox.ai" }}
http_session_header: ${{ env "DECK_VERIKNOX_SESSION_HEADER" }}Make sure to replace the following placeholders with your own values:
-
consumerGroupName|Id: Theidornameof the consumer group the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/consumer_groups/{consumerGroupName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
consumerGroupName|Id: Theidornameof 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 $KONNECT_TOKEN" \
--data '
{
"name": "veriknox",
"config": {
"endpoint": {
"specification": "Inference:OpenAI/Chat_Completions",
"provider": "'$VERIKNOX_PROVIDER_NAME'"
},
"agent_passphrase": "{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}",
"veriknox_hub": {
"base_url": "https://hub.veriknox.ai"
},
"http_session_header": "'$VERIKNOX_SESSION_HEADER'"
}
}
'Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
controlPlaneId: Theidof the control plane. -
consumerGroupId: Theidof the consumer group the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: veriknox
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
endpoint:
specification: Inference:OpenAI/Chat_Completions
provider: '$VERIKNOX_PROVIDER_NAME'
agent_passphrase: '{vault://veriknox/VERIKNOX_IDENTITY_PASSPHRASE}'
veriknox_hub:
base_url: https://hub.veriknox.ai
http_session_header: '$VERIKNOX_SESSION_HEADER'
plugin: veriknox
" | kubectl apply -f -Next, apply the KongPlugin resource by annotating the KongConsumerGroup resource:
kubectl annotate -n kong kongconsumergroup CONSUMERGROUP_NAME konghq.com/plugins=veriknoxPrerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_veriknox" "my_veriknox" {
enabled = true
config = {
endpoint = {
specification = "Inference:OpenAI/Chat_Completions"
provider = var.veriknox_provider_name
}
agent_passphrase = var.{vault://veriknox/veriknox_identity_passphrase}
veriknox_hub = {
base_url = var.https://hub.veriknox.ai
}
http_session_header = var.veriknox_session_header
}
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 "veriknox_session_header" {
type = string
}