Everyone is building LLM routers, we deprecated ours
The developers of the Manifest LLM gateway have deprecated their model router, arguing that routing requests to different models based on complexity is often ineffective. They suggest that using a single, high-performance model is more reliable and cost-effective than complex routing logic.
Why it matters
Challenges the prevailing industry trend of building AI routers to optimize inference costs, suggesting a shift toward model consolidation.
{this.querySelector('.blog-post__share-check').style.display='none';this.querySelector('.blog-post__share-copy').style.display='block'},2000)"> Everyone is building LLM routers, we deprecated ours Bruno Perez Jul 31, 2026 3 min read We don’t believe in model routing anymore. For most use cases, sticking to a single battle-tested model is the best thing you can do.
Recently, there’s been huge hype around AI model routers that select the model that will respond to your request on the fly. There have been many launches in recent weeks with similar promises of reducing inference costs. We had our LLM router too, and decided to remove it.
Some context first: we launched the Manifest LLM router in March as a key feature in our LLM gateway , and we deprecated it in June , shutting it down for good on September 1st. Our router was classifying each request into one of four different tiers of complexity: simple, standard, complex and reasoning.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in