Model

The deployment's model configuration: the OpenAI-compatible endpoint every saddle assignment is sent to, and the advisor's optional overrides. Stored in the database — environment variables no longer configure it (a pre-page deployment's SADDLE_LLM_* environment is imported once, on first read).

paused No base URL is configured — task assignment is paused and the advisor is disabled until one is saved.

ready Updated when.

Main endpoint

Used by every saddle assignment (the harness's LLM).

Base URL

Model

API key A key is stored (hint) Clear the stored key

Advisor endpoint (optional)

Overrides for the AI Chat advisor. Leave the base URL empty to use the main endpoint's fields.

Base URL

Model

API key A key is stored (hint) Clear the stored key