Skip to main content
The TypeScript SDK and docs are currently in beta. Report issues on GitHub.
Configuration for the openrouter:fusion server tool.

Example Usage

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

let value: FusionServerToolConfig = {};

Fields

FieldTypeRequiredDescriptionExample
analysisModelsstring[]:heavy_minus_sign:Slugs of models to run in parallel as the analysis panel. Each model receives the user prompt with openrouter:web_search and openrouter:web_fetch enabled, then a judge model summarizes the collective output into structured analysis JSON. Capped at 8 models to bound cost amplification. Defaults to the Quality preset from /labs/fusion.[
“~anthropic/claude-opus-latest”,
“~openai/gpt-latest”,
“~google/gemini-pro-latest”
]
maxCompletionTokensnumber:heavy_minus_sign:Maximum number of output tokens (including reasoning tokens) each panelist and the judge model may produce per inner call. Controls the total output budget so reasoning-heavy models like GPT-5.5 do not exhaust their token allowance before producing visible text. When omitted, the provider’s default applies.16384
maxToolCallsnumber:heavy_minus_sign:Maximum number of tool-calling steps each panelist (analysis model) and the judge model may take during their agentic web-research loop. Models with web_search/web_fetch enabled iterate until they produce a text response or hit this ceiling. Defaults to 8. Capped at 16.12
modelstring:heavy_minus_sign:Slug of the judge model that produces the structured analysis JSON. Defaults to the model used in the outer API request.~anthropic/claude-opus-latest
reasoningmodels.FusionServerToolConfigReasoning:heavy_minus_sign:Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking.
temperaturenumber:heavy_minus_sign:Sampling temperature forwarded to panelist and judge inner calls. When omitted, the provider’s default applies.0.7