Everyone is building LLM routers, we deprecated ours

Product

LLM Gateway

Auto-fix<br>New

Observability

Solutions

For AI builders

For teams

For platforms

PricingBlogDocs

Star

7,344

Login

Get started

Logo SVG copied to clipboard

Offer<br>🎁 Talk to us and get $25 of Gemini credit<br>Read more

Before you go

Talk to us and get $25 credit for .

We're doing user discovery to understand your expectations and pain points around agent reliability.

15 minutes through a video call.

Quick access to $25 of Gemini tokens through Manifest.

You talk and we listen. Just questions and nothing to sell.

Book my slot to get $25<br>Offer terms

{this.querySelector('.blog-post__share-check').style.display='none';this.querySelector('.blog-post__share-copy').style.display='block'},2000)">

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.

Like most LLM routers, ours was made for cost reduction. Why call a powerful, and therefore expensive, model for a simple task? Routing to the most cost-effective model seems like a natural solution, right? Not that simple. After four months of usage across 7000 cloud users, we saw mixed results and a lot of GitHub issues and discussions about it. Let’s dive into the main problems.

Complexity cannot be deduced from the prompt alone

The prompt alone does not contain the whole task; it is just the trigger. A lot of the context that determines complexity is only discovered later through tool calls, web searches, and so on.

Let’s take an example: “evaluate the tests for the repo $GIT_REPO and improve them” can be a very simple task if you mention a personal website written in plain HTML5; or an incredibly complex task if you target the Linux kernel repo.

Cache is more effective than routing for reducing costs

Cache reads are between 75% and 90% cheaper than uncached inputs. System prompts and conversation history often represent a lot of tokens. Prefix cache works extremely well for those because they sit at the beginning of the prompt.

A cache-aware model router will take that into account by adding stickiness to the initially chosen model and keeps querying it. In other words, the router will do its job by, ironically, not doing it.

LLM routers break behavior consistency

Some say that “engineers should not be concerned about choosing the best LLM for their task”. Well, we strongly disagree .

Just as a painter knows exactly what brush they need to use, and the craftsman carefully chooses their tools, engineers should understand trade-offs and subtleties of the different models. At Manifest, every engineer selects models and effort parameters based on their intent.

Jumping from a model to another during working sessions results in lower quality of the overall work, and detaches the people from mastering their tools.

Unpredictability has a cost

No one likes unpredictability, especially software engineers.

In automated agentic workflows or autonomous agents, managing that extra layer of uncertainty can cost more than it saves . Think of evals, system prompts, observability and so on. Everything suddenly becomes harder to maintain.

Isolating different requests and setting up the right models, params and prompts for it seems naturally superior in most cases.

Conclusion

There are probably many use cases where LLM routing can be useful, and the companies that launched those have probably good reasons.

However, based on our experience, we’ve concluded that in most of the use cases we saw, it was not worth it. The amount saved is paid somewhere else , and that cost is harder to estimate.

Keep reading

Jul 30, 2026<br>Request logs are back

Jul 28, 2026<br>The Biggest Reliability Problem in AI Isn't Hallucinations Anymore

Jul 2, 2026<br>The reliability stack for LLM agents: tools and methods

Start for free. Scale with your team.

Get started

Talk to sales

&copy; 2026 Manifest, 250 Shattuck Avenue, Berkeley, CA 94704. All rights reserved.

Claim my spot

Request access<br>Request

We'll only use this to contact you about early access.