Triton AI Developer API

Get started

Quickstart Models Authentication

Guides

Chat completions Responses Tool calling Image input Embeddings Speech to text Privacy Filter Safety and security

API reference

List accessible models GET Retrieve a model GET Create a chat completion POST Create a response POST Create embeddings POST Transcribe audio POST Classify private text POST Read the public catalog GET

Response headers

Production

Errors and retries Production checklist Check API usage

Endpoints

List accessible models

List the models that your API key can use.

For the workflow and examples, read the guide.

GET/v1/models

Authorization

bearerAuth

AuthorizationBearer <token>

Your Triton AI Developer API key.

In: header

Response Body

`application/json`

API reference

Find endpoints, request fields, code examples, and response schemas.

Retrieve a model GET

Retrieve one model that your API key can access.