Skip to main content
The Galileo decision model integration enables you to create and use decision model metrics in Log streams, experiments, playgrounds, and at every step type.

Prerequisites

To set up a decision model integration, you must meet the following requirements:
  • You have an existing API key for your decision model provider.
  • (TypeSafe users only) Your Galileo deployment has outbound HTTPs to api.typesafe.ai.

Set up a decision model integration

  1. In the Galileo UI, select your user profile in the upper-right corner and then select Integrations.
  2. Open the card for your decision model provider. Follow the on-screen instructions to set up an integration.

How the decision model integration works

This integration is for decision model metrics only. Decision models don’t appear in LLM model pickers. Integration sharing and permissions work the same way as for LLM integrations. Galileo uses the API key of the user who created the run. If that user doesn’t have a decision model integration, the decision model metric toggle is disabled.

TypeSafe billing and rate limits

TypeSafe bills you directly for model usage. Galileo shows the estimated cost on each result. For billing details, see Models in the TypeSafe documentation. When multiple metrics share a call, Galileo splits the estimated call cost across the metrics. TypeSafe sets rate limits per model. If the rate limit is reached, Galileo retries with backoff and shows the standard rate-limit error.

Next steps

Custom decision model metrics

Learn how to create and use decision model metrics.