Skip to main content
Last updated on

Connect your coding agent

This page shows how to configure coding agents to use model services in Unity Gateway by hand.

Follow the instructions for:

Cursor IDE​

To configure Cursor to use model services in Unity Gateway:

Step 1: Configure base URL and API key

  1. Open Cursor and navigate to Settings > Cursor Settings > Models > API Keys.

  2. Enable Override OpenAI Base URL and enter the URL:

    https://<workspace-url>/ai-gateway/cursor/v1

    Replace <workspace-url> with your Databricks workspace URL.

  3. Paste your Databricks personal access token into the OpenAI API Key field.

Step 2: Add custom models

  1. Click + Add Custom Model in Cursor Settings.
  2. Add your model service name (for example, system.ai.claude-opus-4-6) and enable the toggle.
note

Currently, only Databricks-provided model services are supported.

Step 3: Test the integration

  1. Open Ask mode with Cmd+L (macOS) or Ctrl+L (Windows/Linux) and select your model.
  2. Send a message. All requests now route through Databricks.

Codex CLI​

Step 1: Install or update Codex CLI

Install or update to Codex CLI version 0.118 or later:

Bash
npm install -g @openai/codex@latest

Step 2: Create or update the Codex config file

Create or edit the Codex configuration file at ~/.codex/config.toml:

Toml
profile = "default"

[profiles.default]
model_provider = "Databricks"

[model_providers.Databricks]
name = "Databricks :re[ai-gateway]"
base_url = "<workspace-url>/ai-gateway/codex/v1"
wire_api = "responses"

[model_providers.Databricks.auth]
command = "sh"
args = ["-c", "databricks auth token --host <workspace-url> --output json | jq -r '.access_token'"]
timeout_ms = 5000
refresh_interval_ms = 1800000

Replace <workspace-url> with your Databricks workspace URL.

Step 3: Authenticate to your workspace

note

This only needs to be done once. You do not need to re-authenticate every time you start Codex.

First, make sure you have the Databricks CLI installed. See Install or update the Databricks CLI for instructions.

Then authenticate:

Bash
databricks auth login --host <workspace-url>

Replace <workspace-url> with your Databricks workspace URL.

Step 4: Start Codex

Bash
codex

To change the model, use /model.

Gemini CLI​

Step 1: Install the latest version of Gemini CLI

Bash
npm install -g @google/gemini-cli@nightly

Step 2: Configure environment variables

Create a file ~/.gemini/.env and add the following configuration. See the Gemini CLI authentication docs for more details.

GEMINI_MODEL=databricks-gemini-2-5-flash
GOOGLE_GEMINI_BASE_URL=https://<workspace-url>/ai-gateway/gemini
GEMINI_API_KEY_AUTH_MECHANISM="bearer"
GEMINI_API_KEY=<databricks_pat_token>

Replace <workspace-url> with your Databricks workspace URL and <databricks_pat_token> with your personal access token.

Use Open Source models with coding agents​

Databricks supports integrating open source (OSS) models, such as glm-5-2, with coding agents.

Your workspace must have access to the target OSS model.

OpenCode​

Install the Unity Gateway CLI with uv tool install git+https://github.com/databricks/unity-gateway, then select system.ai.glm-5-2 as your model.

Manual setup

Alternatively, you can install OpenCode as described in the OpenCode docs, then create or edit ~/.config/opencode/opencode.json:

JSON
{
  "$schema": "https://opencode.ai/config.json",
  "model": "databricks-oss/<open source model service name>",
  "provider": {
    "databricks-oss": {
      "npm": "@ai-sdk/openai",
      "options": {
        "baseURL": "<workspace-url>/ai-gateway/mlflow/v1",
        "apiKey": "<databricks_pat_token>"
      },
      "models": {
        "<open source model service name>": {}
      }
    }
  }
}

Replace the following:

  • <workspace-url> with your Databricks workspace URL.
  • <databricks_pat_token> with your personal access token.
  • <open source model service name> with the target OSS model service, for example system.ai.glm-5-2.

Then start OpenCode:

Bash
opencode

Codex​

Codex connects to Open Source models through the Open Responses API that Codex supports.

Install the Unity Gateway CLI with uv tool install git+https://github.com/databricks/unity-gateway, then run:

Bash
ug codex --model <open source model service name>

For example, to use GLM 5.2 with Codex, run:

Bash
ug codex --model system.ai.glm-5-2

Manual setup

Alternatively, you can install the Codex CLI as described in Codex CLI, then create or edit ~/.codex/config.toml:

Toml
model = "<open source model service name>"
model_provider = "Databricks"

[model_providers.Databricks]
name = "Databricks :re[ai-gateway]"
base_url = "<workspace-url>/ai-gateway/codex/v1"
wire_api = "responses"

[model_providers.Databricks.auth]
command = "sh"
args = ["-c", "databricks auth token --host <workspace-url> --output json | jq -r '.access_token'"]
# Re-run the token command periodically so long sessions don't fail when the
# short-lived Databricks token expires.
timeout_ms = 5000
refresh_interval_ms = 1800000

Replace <workspace-url> with your Databricks workspace URL and <open source model service name> with the target OSS model service, for example system.ai.glm-5-2.

Then start Codex:

Bash
codex

Next steps​

On this page