Triton AI Docs
Developer API

Quickstart

Send a chat request through the Triton AI Developer API.

Request access

Submit the Developer API access request. Your approval defines model routes, limits, and billing.

Set the environment variable

export TRITONAI_API_KEY="your-key"

Do not save the key in a source file or commit it to a repository.

Send a request

quickstart.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": "user",
            "content": "Explain retrieval-augmented generation in two sentences.",
        }
    ],
)

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

The Python example uses the OpenAI Python client. The cURL example has no language-specific package requirement.

Client configuration

Prop

Type

Access can differ

The public Model Hub lists public routes. Your key can have a smaller approved model set.

Next steps

On this page