OutputFusionServerToolItem - TypeScript SDK

OutputFusionServerToolItem type definition

The TypeScript SDK and docs are currently in beta. Report issues on GitHub.

An openrouter:fusion server tool output item

Example Usage

1import { OutputFusionServerToolItem } from "@openrouter/sdk/models";
2
3let value: OutputFusionServerToolItem = {
4 status: "completed",
5 type: "openrouter:fusion",
6};

Fields

FieldTypeRequiredDescriptionExample
analysismodels.FusionAnalysisResultStructured analysis produced by the fusion judge model.{"blind_spots": ["No model considered the impact on existing API consumers."],"consensus": ["All panel models agree the request is asking for a concise summary."],"contradictions": [{"stances": [{"model": "openai/gpt-5","stance": "Favors an incremental rollout."},
{"model": "anthropic/claude-sonnet-4.5","stance": "Favors a single coordinated migration."}
],
“topic”: “Recommended approach”
}
],
“partial_coverage”: [
{"models": ["openai/gpt-5"],"point": "Only one model addressed the rollback strategy."}
],
“unique_insights”: [
{"insight": "Highlighted a backwards-compatibility risk the other models missed.","model": "anthropic/claude-sonnet-4.5"}
]
}
errorstringError message when the fusion run did not produce an analysis result.
failedModelsmodels.FailedModel[]Models that were requested as part of the analysis panel but did not produce a response. Present when at least one requested analysis model failed. The fusion result is still usable but was produced from a degraded panel.
failureReasonstringTyped failure reason when the fusion run failed. Possible values include: all_panels_failed, insufficient_credits, rate_limited, judge_not_valid_json, judge_schema_mismatch, judge_upstream_error, judge_empty_completion.
idstringN/A
responsesmodels.ResponseT[]Analysis models that produced a response in this fusion run, with each model’s full panel content.
statusmodels.ToolCallStatus✔️N/Acompleted
type”openrouter:fusion”✔️N/A