Skip to main content
Triton AI Triton AI

Get Started

  1. TritonAI
  2. Developer APIs
  3. Get Started

Build with TritonAI

Get started with the TritonAI Gateway

Request a Gateway key, connect a client, and run a first test. n8n access is a separate request, covered at the end of this page.

Request Gateway access

Submit the access form to receive your approved Gateway key and the models available to it. The approval records the access, limits, and billing treatment for the key.

UC-hosted models carry no recharge for campus administrative work. Cloud models and sponsored research require a departmental or project chartstring. Recharge is the campus term for internal billing to a chartstring.

Request Gateway access (Kuali Build)

Eligibility and recharge details

  • Faculty and staff: Campus and Health Sciences personnel may use UC-hosted models for administrative work under monthly caps.
  • Research projects: Sponsored research charges model usage to an approved grant or project chartstring.
  • Other UC campuses: Intercampus recharge agreements are arranged via tritonai@ucsd.edu.
  • Health System patient care: Clinical operations must use approved Medical Center AI platforms on Pulse.

Choose your client or integration

Connect your approved key to TritonAI Harness, another compatible client, or your own code.

Primary Supported Client

TritonAI Harness

Native desktop app for local coding, file editing, terminal execution, and Microsoft 365 connections. In pilot for Mac (Apple Silicon) and Windows. Anyone with a Gateway key can request it.

Version 0.3.3. Read release notes or view checksums.

CLI Coding Agents

Claude Code, Codex, Hermes, and other clients

Claude Code and Codex are supported alternatives. Hermes, OpenCode, and any client that accepts a base URL and API key connect the same way.

  • Base URL: https://tritonai-api.ucsd.edu/v1
  • Default Model: api-glm-5.3
  • Store your API key in your shell profile.
API & Pipelines

Direct Code Integration

Use the OpenAI Python SDK.

from openai import OpenAI
client = OpenAI(
  base_url="https://tritonai-api.ucsd.edu/v1",
  api_key="YOUR_KEY"
)
resp = client.chat.completions.create(
  model="api-glm-5.3",
  messages=[{"role":"user","content":"Hi"}]
)
See Model Hub for available routes.

Launch and verify

Enter your key and verify your connection with a low-risk test prompt.

  1. 1
    Enter your key

    Paste the approved key into your client settings.

  2. 2
    Choose an approved model

    Select api-glm-5.3 (UC-hosted, 320K context) or an approved cloud route.

  3. 3
    Run a test request

    Confirm the model responds and check results.

Need setup help?

If your key is rejected or models do not appear, remove extra spaces around your key. Keep the key private; support will never ask for your secret key.

Email tritonai@ucsd.edu with your operating system and error details. Never include the secret key in email.

Request n8n access

n8n is the campus-hosted workflow platform. Access is granted separately from a Gateway key, and workflows that call a model use your key through the Gateway.

  1. 1
    Submit a support request

    Ask the ITS-TritonAI team for access to the n8n platform.

  2. 2
    Describe the intended workflow

    Include your AD username, department, intended use case, and whether you need a testing environment.

  3. 3
    Sign in after approval

    Use your UC San Diego SSO credentials at n8n.tritonai.ucsd.edu.

Request n8n access Open n8n

When n8n fits

You know the process and how it should handle exceptions. It runs on a schedule or when a message, file, or request arrives. For work that changes shape every time, start in TritonAI Harness instead.