Triton AI Docs

API reference

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

Use these routes to list models, generate responses, create embeddings, and transcribe audio. Your API key determines which models and features you can access.

Connection

SettingValue
OpenAI-compatible base URLhttps://tritonai-api.ucsd.edu/v1
Anthropic-compatible base URLhttps://tritonai-api.ucsd.edu
AuthenticationAuthorization: Bearer <API_KEY>
JSON content typeapplication/json

Use the Anthropic-compatible base URL only for clients that call /v1/messages.

Documented routes

MethodRouteReference
GET/v1/modelsList accessible models
GET/v1/models/{model_id}Retrieve a model
POST/v1/chat/completionsCreate a chat completion
POST/v1/responsesCreate a response
POST/v1/embeddingsCreate embeddings
POST/v1/audio/transcriptionsTranscribe audio
POST/vllm/poolingClassify private text
POST/v1/messagesConnect Claude Code
GET/public/model_hubRead the public catalog

Each endpoint page shows authentication, request fields, and response fields. The OpenAPI specification contains this documented subset.

Use the Models page to compare public models. Use the authenticated model list to find the models your key can access.

Authenticate a request

list_models.py
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TRITONAI_API_KEY"],
    base_url="https://tritonai-api.ucsd.edu/v1",
)

for model in client.models.list().data:
    print(model.id)

Keep keys on the server

Do not call the Developer API directly from browser code. A browser request exposes the API key to the user.

Transcribe an audio file

Use the speech-to-text guide for tested Python and cURL examples, or open the endpoint reference.

Common response headers

The production gateway can return these headers:

HeaderMeaning
x-litellm-call-idThe gateway identifier for one request
x-ratelimit-limit-requestsThe request limit for the current window
x-ratelimit-remaining-requestsThe requests left in the current window
x-ratelimit-limit-tokensThe token limit for the current window
x-ratelimit-remaining-tokensThe tokens left in the current window
x-ratelimit-reset-requestsThe request-limit reset value
x-ratelimit-reset-tokensThe token-limit reset value

Header availability depends on the model provider. Include x-litellm-call-id when you report a failed request.

Compatibility boundary

The API follows common OpenAI and Anthropic request shapes. It does not support every upstream feature on every model.

Before you send an optional field, check that the model lists it in supported_openai_params. Test tool and media features before production use.

The generated gateway OpenAPI schema is useful for inspection. It is not the curated public API contract.

Use the documented routes

The gateway schema also includes LiteLLM administrative and provider routes. Their presence in the schema does not establish Triton AI support.

On this page