Skip to main content
The orq:advisor tool lets the primary model ask another model for advice during a response. The advisor receives the conversation transcript, the model’s question, and optional context. Its answer goes back to the primary model, which writes the final response. Advisor is useful at a decision point or before the primary model commits to a high-cost action. It is not a separate user-facing answer.

Quick start

The examples use the client configuration from the Server tools overview.

Configuration

Transcript size is estimated from the serialized conversation. When a limit is set, the AI Gateway keeps the newest complete user turns that fit.

Cost and usage

Advisor tokens are billed at the selected model’s standard rate. Each Advisor call appears at usage.server_tool_use.advisor_requests.