Create an AI Gateway Model
Changed onPre-release Endpoint This endpoint is currently in beta and is subject to change.
Registers a new model with routing, capabilities, and target backends.
Request
- Base URL: https://global.api.konghq.com
- URL: https://global.api.konghq.com/v1/ai-gateways/{gatewayId}/models
- Auth: one of:
- HTTP bearer
- HTTP bearer
- HTTP bearer
- HTTP bearer
Request body
Example request
{
"display_name": "My GPT 5 model",
"name": "my-entity-name",
"enabled": true,
"access": {
"identity_providers": [
"okta-ai-se"
],
"auth_strategies": [
"okta-ai-se"
]
},
"formats": [
{
"type": "openai"
}
],
"targets": [
{
"name": "gpt-5-model",
"weight": 100,
"provider": "azure-ai-se"
}
],
"labels": {
"category": "finance"
},
"managed_by": {
"owner": "terraform"
},
"config": {
"route": {
"headers": {
"version": [
"v1",
"v2"
]
},
"hosts": [
"foo.example.com"
],
"model": {
"body_param": "model",
"header_param": "x-model",
"path_param": "model_name"
}
},
"balancer": {
"embeddings": {
"provider": "azure-ai-se"
}
}
}
}Response
Model created successfully.
Example response
{
"id": "5f9fd312-a987-4628-b4c5-bb4f4fddd5f7",
"created_at": "2022-11-04T20:10:06.927Z",
"updated_at": "2022-11-04T20:10:06.927Z",
"display_name": "My GPT 5 model",
"name": "my-entity-name",
"enabled": true,
"access": {
"identity_providers": [
"okta-ai-se"
],
"auth_strategies": [
"okta-ai-se"
]
},
"formats": [
{
"type": "openai"
}
],
"targets": [
{
"name": "gpt-5-model",
"weight": 100,
"provider": "azure-ai-se"
}
],
"labels": {
"category": "finance"
},
"managed_by": {
"owner": "terraform"
},
"config": {
"route": {
"headers": {
"version": [
"v1",
"v2"
]
},
"hosts": [
"foo.example.com"
],
"model": {
"body_param": "model",
"header_param": "x-model",
"path_param": "model_name"
}
},
"balancer": {
"embeddings": {
"provider": "azure-ai-se"
}
}
}
}Changes
- breaking
removed the enum value
vertexof the request property////// - breaking
removed the enum value
vertexof the request property////// - breaking
removed from the
//////request propertyoneOflist - breaking
removed from the
//////request propertyoneOflist - breaking
removed from the
///////////request propertyoneOflist - breaking
removed from the
///////////request propertyoneOflist - warning
the
///////////////request property's max was set to65535.00 - warning
the
////////////////request property's max was set to2147483646.00 - warning
the
///////////////request property's max was set to2147483646.00 - warning
the
/////request property's max was set to2147483646.00 - warning
the
//////request property's max was set to599.00 - warning
the
//////request property's max was set to2147483647.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////////request property's max was set to65535.00 - warning
the
////////////////request property's max was set to2147483646.00 - warning
the
///////////////request property's max was set to2147483646.00 - warning
the
/////request property's max was set to2147483646.00 - warning
the
//////request property's max was set to599.00 - warning
the
//////request property's max was set to2147483647.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////request property's max was set to2147483646.00 - warning
the
///////////////request property's min was set to0.00 - warning
the
////////////////request property's min was set to0.00 - warning
the
///////////////request property's min was set to0.00 - warning
the
/////request property's min was set to0.00 - warning
the
//////request property's min was set to100.00 - warning
the
//////request property's min was set to-2147483648.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////////request property's min was set to0.00 - warning
the
////////////////request property's min was set to0.00 - warning
the
///////////////request property's min was set to0.00 - warning
the
/////request property's min was set to0.00 - warning
the
//////request property's min was set to100.00 - warning
the
//////request property's min was set to-2147483648.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - warning
the
///////////request property's min was set to0.00 - info
added the new optional request property
///// - info
added the new optional request property
///// - info
request property
/////deprecated - info
request property
//////deprecated - info
request property
/////deprecated - info
request property
//////deprecated - info
removed
vertexdiscriminator mapping keys from the///////////request property - info
removed
vertexdiscriminator mapping keys from the//////request property - info
removed
vertexdiscriminator mapping keys from the///////////request property - info
removed
vertexdiscriminator mapping keys from the//////request property - info
added the optional property
/////to the response with the status - info
added the optional property
/////to the response with the status - info
response property
oneOf[AIGatewayModelAPI]/access/identity_providersdeprecated - info
response property
oneOf[AIGatewayModelAPI]/access/identity_providers/items/deprecated - info
response property
oneOf[AIGatewayModelModel]/access/identity_providersdeprecated - info
response property
oneOf[AIGatewayModelModel]/access/identity_providers/items/deprecated - info
removed
vertexdiscriminator mapping keys from the///////////response property for the response status - info
removed
vertexdiscriminator mapping keys from the//////response property for the response status - info
removed
vertexdiscriminator mapping keys from the///////////response property for the response status - info
removed
vertexdiscriminator mapping keys from the//////response property for the response status - info
removed the
vertexenum value from the//////response property for the response status - info
removed the
vertexenum value from the//////response property for the response status - info
removed from the
//////response propertyoneOflist for the response status - info
removed from the
//////response propertyoneOflist for the response status - info
removed from the
///////////response propertyoneOflist for the response status - info
removed from the
///////////response propertyoneOflist for the response status
- breaking
- info
endpoint added
- info