Use PaletteAI Inference Launchpad with Claude Code

This guide explains how to connect Claude Code to a PaletteAI Inference Launchpad appliance so that a model running on the appliance serves every request instead of Anthropic's hosted API. Claude Code reaches the appliance over the Anthropic API, so you trust the appliance certificate, set a group of environment variables, and confirm the connection.

The console assembles these values for you. In the Connect a coding agent panel, the Claude Code CLI tab lists the steps and generates an environment block for bash, zsh, or PowerShell. For what each value does, refer to Claude Code Configuration.

Prerequisites

• Claude Code installed and already working against Anthropic's hosted API. For installation, refer to the Claude Code documentation.
• A running PaletteAI Inference Launchpad appliance with at least one model deployed and serving. To deploy a model, refer to Deploy a Model.
• An API token for the appliance. To create one, refer to Generate an API Token, or use a token an administrator generated for you.

Download the Platform CA Certificate

When the appliance serves HTTPS with a certificate issued by its own platform Certificate Authority (CA), the connect panel offers that CA certificate as a download. Your machine does not trust the platform CA yet, so download the certificate before you configure the agent.

1. In the console, open the Connect a coding agent panel. Select Connect Coding Agent on the homepage, select Connect a Coding Agent in the Create API token dialog that reveals a new token, or select Connect Agent in the dialog that finishes the Add client wizard.

2. Select the tab for your agent, and then select CA certificate. The browser saves palette-ai-inference-launchpad-ca.crt to your Downloads folder.

If the panel shows no CA certificate step, the appliance does not need one. Skip this section and every later step that points at the downloaded file.

Configure Claude Code

1. On the machine where you run Claude Code, set the following environment variables. Replace <appliance-host> with your appliance address.

   export NODE_EXTRA_CA_CERTS=$HOME/Downloads/palette-ai-inference-launchpad-ca.crt
   export ANTHROPIC_BASE_URL=https://<appliance-host>
   export ANTHROPIC_MODEL=claude-opus-4-8
   export ANTHROPIC_DEFAULT_OPUS_MODEL=claude-opus-4-8
   export ANTHROPIC_DEFAULT_SONNET_MODEL=claude-sonnet-4-5
   export ANTHROPIC_DEFAULT_HAIKU_MODEL=claude-haiku-4-5
   export ANTHROPIC_DEFAULT_FABLE_MODEL=claude-fable-5
   export CLAUDE_CODE_EFFORT_LEVEL=auto
   export CLAUDE_CODE_MAX_OUTPUT_TOKENS=64000

   Include the NODE_EXTRA_CA_CERTS line only when the panel shows the CA certificate step. Claude Code runs on Node.js, and this variable adds the platform CA to the certificates Node.js trusts, so certificate verification stays on. Set it in the shell before you start Claude Code. On PowerShell, the panel writes the same path as $env:USERPROFILE\Downloads\palette-ai-inference-launchpad-ca.crt.

2. Export your API token. The panel keeps the token out of the copied block, so you do not paste it alongside the shared values. Replace <lpai-token> with your token.

   export ANTHROPIC_AUTH_TOKEN=<lpai-token>

3. (Optional) To keep the endpoint and token across sessions, add them to the ~/.claude/settings.json file instead of exporting them each time. Persisting the token there writes the secret to disk.

   {
     "env": {
       "ANTHROPIC_BASE_URL": "https://<appliance-host>",
       "ANTHROPIC_AUTH_TOKEN": "<lpai-token>"
     }
   }

Verify the Connection

1. Run a single prompt to confirm the appliance answers.

   claude --print "reply with exactly CC_OK and nothing else"
   Expected output

   CC_OK

   A reply confirms that the certificate, base URL, token, and model routing all work.

2. Start an interactive session.

   claude

3. To confirm which endpoint and credential the session uses, run the /status command in Claude Code and review the Anthropic base URL and Auth token lines.

Request Routing and Quotas

Requests you send through the appliance are subject to the routing rule and quota configured for your client. If an operator configured a routing rule for your token, the appliance can redirect a request to a frontier model instead of a local one. Quotas apply to the client, so every API token that belongs to the client draws on the same limits. When the client exhausts a quota, the appliance returns an HTTP 429 response.

To understand what a client is and how API keys and quotas govern usage, refer to Clients and Quotas. To understand how the Tier map and the semantic router combine to pick a model for each request, refer to Routing Behavior.

Next Steps

To look up any configuration value, refer to Claude Code Configuration. To deploy another model to the appliance, refer to Deploy a Model. To let the appliance answer questions about pasted screenshots, refer to Enable Vision Preprocessing. To understand how the Tier map and the semantic router pick a model for each request, refer to Routing Behavior.