AIGatewayModelConfig

object

Routing, logging, and load balancing configuration for the model.

* Additional properties are NOT allowed.
routeobjectrequired

Configuration for an AI Gateway route.

* Additional properties are NOT allowed.
Show Child Parameters
loggingobjectrequired

Configuration for AI Gateway logging.

* Additional properties are NOT allowed.
Show Child Parameters
response_streamingstringrequired

Allowed values:allowalwaysdeny

Default:allow

max_request_body_sizeintegerrequired

Default:1048576

modelobjectrequired
* Additional properties are NOT allowed.
Show Child Parameters
balancerobject

Load balancing strategy when multiple target models are configured.

* Additional properties are NOT allowed.
Show Child Parameters
Example

AIGatewayEmbeddingsModelConfig

Configuration for an embeddings model.

One Of
namestringrequired

The name of the embeddings model.

upstream_urlstringrequired

The URL of the embeddings model.

typestringrequired

Allowed values:azure

deployment_idstring

The Azure deployment ID for the model.

api_versionstring

The Azure OpenAI API version to use.

Default:2023-05-15

Example

AIGatewayAzureEmbeddingsModelConfig

object

Azure-specific configuration for a model.

* Additional properties are NOT allowed.
namestringrequired

The name of the embeddings model.

upstream_urlstringrequired

The URL of the embeddings model.

typestringrequired

Allowed values:azure

deployment_idstring

The Azure deployment ID for the model.

api_versionstring

The Azure OpenAI API version to use.

Default:2023-05-15

Example

AIGatewayBedrockEmbeddingsModelConfig

object

AWS Bedrock-specific configuration for a model.

* Additional properties are NOT allowed.
namestringrequired

The name of the embeddings model.

upstream_urlstringrequired

The URL of the embeddings model.

typestringrequired

Allowed values:bedrock

batch_bucket_prefixstring

S3 bucket prefix for batch inference jobs.

embeddings_normalizeboolean

Whether to normalize embedding vectors in the response.

Default:false

performance_config_latencystring

Latency performance configuration for the model invocation.

video_output_s3_uristring

S3 URI for storing video generation outputs.

Example

AIGatewayGeminiEmbeddingsModelConfig

object

Google Gemini-specific configuration for a model.

* Additional properties are NOT allowed.
namestringrequired

The name of the embeddings model.

upstream_urlstringrequired

The URL of the embeddings model.

typestringrequired

Allowed values:gemini

location_idstring

The Google Cloud location ID for the model endpoint.

api_endpointstring

The custom API endpoint for the Gemini model.

Example