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
| Setting | Value |
|---|---|
| OpenAI-compatible base URL | https://tritonai-api.ucsd.edu/v1 |
| Anthropic-compatible base URL | https://tritonai-api.ucsd.edu |
| Authentication | Authorization: Bearer <API_KEY> |
| JSON content type | application/json |
Use the Anthropic-compatible base URL only for clients that call /v1/messages.
Documented routes
| Method | Route | Reference |
|---|---|---|
GET | /v1/models | List accessible models |
GET | /v1/models/{model_id} | Retrieve a model |
POST | /v1/chat/completions | Create a chat completion |
POST | /v1/responses | Create a response |
POST | /v1/embeddings | Create embeddings |
POST | /v1/audio/transcriptions | Transcribe audio |
POST | /vllm/pooling | Classify private text |
POST | /v1/messages | Connect Claude Code |
GET | /public/model_hub | Read 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
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:
| Header | Meaning |
|---|---|
x-litellm-call-id | The gateway identifier for one request |
x-ratelimit-limit-requests | The request limit for the current window |
x-ratelimit-remaining-requests | The requests left in the current window |
x-ratelimit-limit-tokens | The token limit for the current window |
x-ratelimit-remaining-tokens | The tokens left in the current window |
x-ratelimit-reset-requests | The request-limit reset value |
x-ratelimit-reset-tokens | The 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.