AI Inference

Create Chat Completion

post

Creates a model response for the given chat conversation. This endpoint is OpenAI-compatible.

Authorizations
AuthorizationstringRequired

JWT token for authentication

Header parameters
OrgIDstringOptional

organization ID for required if request is made using access token.

ProjectIDstringOptional

project ID required if request is made using access token.

Body
anyOptional
Responses
chevron-right
200

Chat completion response

application/json
Responseany
post
/v1/chat/completions

No content

List Models

get

Lists the currently available models, and provides basic information about each one such as the owner and availability. This endpoint is OpenAI-compatible.

Authorizations
AuthorizationstringRequired

JWT token for authentication

Header parameters
OrgIDstringOptional

organization ID required if request is made using access token.

ProjectIDstringOptional

project ID required if request is made using access token.

Responses
chevron-right
200

List of models

application/json
Responseany
get
/v1/models

No content

Retrieve Model

get

Retrieves a model instance, providing basic information about the model such as the owner and permission. This endpoint is OpenAI-compatible.

Authorizations
AuthorizationstringRequired

JWT token for authentication

Path parameters
model_idstringRequired

The ID of the model to use for this request.

Example: gpt-4
Header parameters
OrgIDstringOptional

organization ID required if request is made using access token.

ProjectIDstringOptional

project ID required if request is made using access token.

Responses
chevron-right
200

Model information

application/json
Responseany
get
/v1/models/{model_id}

No content

Last updated