Triton AI Docs
Developer API

Chat completions

Send text messages and stream responses with Python or cURL.

Use the chat completions API for text conversations. Choose a public model with mode: chat that your key can access.

Send a conversation

chat.py
import os

from openai import OpenAI

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

completion = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {
            "role": "system",
            "content": "Answer with short, direct sentences.",
        },
        {
            "role": "user",
            "content": "What is a model context window?",
        },
    ],
)

print(completion.choices[0].message.content)

Stream a response

stream_chat.py
stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {
            "role": "user",
            "content": "Give me three ways to evaluate a summarization system.",
        }
    ],
    stream=True,
)

for chunk in stream:
    text = chunk.choices[0].delta.content
    if text:
        print(text, end="", flush=True)

Main request fields

Prop

Type

The Models page shows each route's supported_openai_params values. Do not send an unsupported field.

On this page