Custom / Local Model Setup

Use Custom / Local when you run an OpenAI-compatible server such as a local model host or an internal gateway.

Configure it

1. Open Settings > Models.
2. Set the provider to Custom / Local.
3. Enter the exact model ID exposed by the server.
4. Enter the OpenAI-compatible base endpoint, typically ending in /v1.
5. Enter a token if the server requires one.
6. Run Test Connection.
7. Save Settings and send a simple Genie request.

Genie uses one provider route with one endpoint.

Common failures

Test Connection fails

• Confirm the server is running and reachable from the Mac running FileMaker.
• Check the base URL, port, /v1 path, token, and model ID.
• Confirm the server implements the OpenAI-compatible endpoint Genie calls.

Basic chat works but Genie tools fail

The selected model or server may not support tool calling, required tool choice, or compatible structured responses. Choose a tool-capable model or gateway.

Genie answers but script and layout actions are unavailable

Your AI provider and your Genie plan are separate. The free plan answers questions and gives complete script steps to build by hand. Writing scripts and layouts, executable data changes, and external MCP coding and execution require a paid plan.

Related pages

• AI Providers
• Settings Guide
• Licensing and Activation

For the custom server’s Low / Medium / High compatibility option, see Agent reasoning.