# Factory AI — Factory Router cuts inference costs by 63%

- Company: Factory AI (factory.com)
- Announced: 2026-09-23
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://factory.com/news/factory-router-inference-savings
- Record: https://forck.live/items/17847-factory-router-cuts-inference-costs-by-63
- Subject: Droid

When we introduced Factory Router in June, benchmarks showed 20–25% lower inference costs while maintaining near-frontier task completion. Production results are now even stronger. Sessions using Factory Router cost 63% less in aggregate than the same workload would have cost at published frontier-model rates. " Factory Router saved us thousands of dollars in inference costs in one week. For the router users, they saved a median of 72%. This has greatly extended our runway for AI investments while reducing the mental load of choosing the optimal model for every task. " Lower costs do not require assigning every task to a smaller model. Factory Router selects an efficient model when it can complete the workload reliably and moves to a stronger model when needed. In our published task-completion benchmarks , routed runs achieved 99% of Claude Opus 4.7’s pass rate on Terminal-Bench 2 and 96% on Legacy-Bench . Factory Router is also now available in Factory Private (in private preview), making it the first and only on-premises model router built for software development agents. Teams can run routing and inference in their own VPC, on-premises infrastructure, or air-gapped network. …

---

Record: https://forck.live/items/17847-factory-router-cuts-inference-costs-by-63
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md