Skip to main content
The TypeScript SDK and docs are currently in beta. Report issues on GitHub.
Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking.

​
Example Usage

import { FusionServerToolConfigReasoning } from "@openrouter/sdk/models";

let value: FusionServerToolConfigReasoning = {};

​
Fields

FieldTypeRequiredDescription
effortmodels.FusionServerToolConfigEffort:heavy_minus_sign:Reasoning effort level for panelist and judge inner calls.
maxTokensnumber:heavy_minus_sign:Maximum number of reasoning tokens each panelist and judge model may use. Helps bound cost when models allocate too much budget to chain-of-thought.