Generate an API Token
This guide explains how to generate an API token in the PaletteAI Inference Launchpad console. Clients such as coding assistants use the token to authenticate their requests to the appliance. To understand how tokens, clients, and quotas relate, refer to Clients and Quotas. To create a client and then set its quotas and model access, start with Create a Client.
Prerequisites
- A running PaletteAI Inference Launchpad appliance, with the console reachable.
- An existing client to issue the token to. To create one, refer to Create a Client.
- Console access with permission to create API tokens. Creating a token can require operator access.
Generate an API Token
If an administrator already gave you an API token, you can use it and skip the following steps.
-
From the left main menu, select Access & Policy. The Clients & API tokens page opens.
-
In the client's row, open the three-dot menu and select Manage Client. The client's detail panel opens to the Overview section.
-
Select the API tokens section, and then select Create Token. The Create API token dialog opens.
-
(Optional) In the Label field, enter a name that identifies the token, such as the coding assistant that uses it.
-
(Optional) To set an expiration date, clear Never expires, and then choose an Expires date. By default, the token does not expire.
-
Select Create Token.
-
When the console reveals the token, select Copy. The token begins with
lpai_.
The console shows the token only once and stores only a hash of it. Copy it now. If you lose it, revoke the token and create a new one.
Next Steps
Use the token to connect a coding assistant to the appliance.