AIGatewayModelVectorDBConfigPgVector

object
* Additional properties are NOT allowed.
strategystringrequired

Allowed values:pgvector

dimensionsintegerrequired

the desired dimensionality for the vectors

distance_metricstringrequired

the distance metric to use for vector searches

Allowed values:cosineeuclidean

thresholdnumber

the default similarity threshold for accepting semantic search results (float). Higher threshold means more results are considered similar.

databasestring

the database of the pgvector database

Default:kong-pgvector

hoststring

the host of the pgvector database

Default:127.0.0.1

passwordstring

the password of the pgvector database
This field is referenceable.
This field is encrypted.

portinteger

the port of the pgvector database

Default:5432

sslobject
* Additional properties are NOT allowed.
Show Child Parameters
timeoutnumber

the timeout of the pgvector database

Default:5000

userstring

the user of the pgvector database
This field is referenceable.

Default:postgres

Example

AIGatewayModelFormat

object

Request and response format supported by this model.

* Additional properties are NOT allowed.
typestring

The format type.

Example:openai

Example

AIGatewayTargetModel

object

A target model instance that this model entry routes requests to.

* Additional properties are NOT allowed.
namestringrequired

The name of the model defined in the upstream provider that will be executed.

Example:gpt-5-model

providerobjectrequired

Lightweight object used to reference a provider instance, identified by its ref.

* Additional properties are NOT allowed.
Show Child Parameters
configOne Of

Configuration for a target model.

AIGatewayTargetModelAnthropicConfigobject

Anthropic-specific configuration for a model.

* Additional properties are NOT allowed.
Show Child Parameters
Example

AIGatewayTargetModelConfig

Configuration for a target model.

One Of
embeddings_dimensionsinteger

The number of dimensions for embedding outputs.

max_tokensinteger

The maximum number of tokens to generate in the response.

input_costnumber

Cost per input token for billing and cost tracking.

output_costnumber

Cost per output token for billing and cost tracking.

temperaturenumber

Controls randomness in the model output. Higher values produce more varied responses.

top_kinteger

Limits the number of highest-probability tokens considered during generation.

top_pnumber

Nucleus sampling probability mass. Tokens with cumulative probability up to top_p are considered.

upstream_urlstring(uri)

The upstream URL for the model endpoint.

typestringrequired

Allowed values:anthropic

versionstring

The Anthropic API version to use.

Example

AIGatewayTargetModelAnthropicConfig

object

Anthropic-specific configuration for a model.

* Additional properties are NOT allowed.
embeddings_dimensionsinteger

The number of dimensions for embedding outputs.

max_tokensinteger

The maximum number of tokens to generate in the response.

input_costnumber

Cost per input token for billing and cost tracking.

output_costnumber

Cost per output token for billing and cost tracking.

temperaturenumber

Controls randomness in the model output. Higher values produce more varied responses.

top_kinteger

Limits the number of highest-probability tokens considered during generation.

top_pnumber

Nucleus sampling probability mass. Tokens with cumulative probability up to top_p are considered.

upstream_urlstring(uri)

The upstream URL for the model endpoint.

typestringrequired

Allowed values:anthropic

versionstring

The Anthropic API version to use.

Example