OpenRouter adds Fusion, a multi-model deliberation API

Category: AI
Status: developing
Sources: OpenRouter Fusion, HN discussion
Summary: OpenRouter published Fusion, a routing model that runs a prompt through a panel of expert models in parallel with web search and web fetch enabled, then has a judge model synthesize their outputs into a structured response covering consensus, contradictions, partial coverage, unique insights, and blind spots. It is accessed by model slug through OpenRouter's existing OpenAI-compatible API, with preset panels (Quality, Budget, General-High) or a custom panel set via the fusion plugin's analysis_models and model fields. Requests are billed as the sum of the underlying model completions rather than a single model price. The feature is described on OpenRouter's own product page with no usage data shown yet and no independent evaluation.
Why it matters: It packages an ensemble or mixture-of-agents pattern (parallel model calls plus a synthesizing judge) behind one API slug, so teams can trade higher per-request cost for cross-model deliberation without building the orchestration themselves.
Follow-up: Watch for a launch post with model list and pricing detail, and independent quality or cost comparisons against single-model calls.