Inference

Query the models available through the inference gateway.

List chat model ids

GET

/v1/inference/list-chat-models

Returns the verified chat models this deployment can route. EchoMode's reranking slot uses the same list as chat, so use this route for that picker too. Embedding models are served by GET /inference/list-embedding-models.

Authorizations

HTTPBearer

Type

HTTP (bearer)

Responses

Successful Response

Content-Type

application/json

{

  

"models": [

  

  

{

  

  

  

"id": "string",

  

  

  

"label": "string",

  

  

  

"provider": "string",

  

  

  

"reasoning_efforts": [

  

  

  

  

"string"

  

  

  

],

  

  

  

"supports_reasoning": false,

  

  

  

"thinking_toggleable": false

  

  

}

  

]

}

Samples

List embedding model ids

GET

/v1/inference/list-embedding-models

Returns the embedding models this deployment can route, for the Dataroom RAG picker. Chat models are served by GET /inference/list-chat-models.

Authorizations

HTTPBearer

Type

HTTP (bearer)

Responses

Successful Response

Content-Type

application/json

{

  

"models": [

  

  

{

  

  

  

"id": "string",

  

  

  

"label": "string",

  

  

  

"provider": "string",

  

  

  

"reasoning_efforts": [

  

  

  

  

"string"

  

  

  

],

  

  

  

"supports_reasoning": false,

  

  

  

"thinking_toggleable": false

  

  

}

  

]

}

Samples