OpenRouter launches Fusion: a compound model that debates across models before synthesizing a final answer
OpenRouter 发布 Fusion 复合模型,让多个模型辩论后合成最终答案
OpenRouter Fusion is a compound inference pipeline, not a new model. It fans out one prompt to up to 8 panelist models in parallel, has a judge compare their answers for consensus and blind spots, then lets the calling model write a final synthesis. A default three-model panel costs roughly 4–5× a single completion and takes 2–3× longer. On the DRACO deep-research benchmark, a budget panel of Gemini 3 Flash, Kimi K2.6, and DeepSeek V4 Pro scored ~64.7%, close to Claude Fable 5’s solo 65.3%. OpenRouter’s own test paired two Claude Opus 4.8 runs and saw a 6.7-point gain over a single run. The team positions Fusion as an escalation path for complex research and high-stakes decisions, not for simple chat. The post does not disclose per-token pricing, only the cost multiplier.
Why it matters: OpenRouter's Fusion fans one prompt out to several models, has a judge weigh agreement against disagreement, then merges an answer at roughly four to five times the cost of a single completion.