What are "smart" model routers you know of? Services or vendors that take queries and route the most efficient model they deem, saving cost.
I sense there is a massive demand for these, and will be even more...
4:58 AM · Jun 11, 2026 · 8K Views
Sentiment
Users criticized smart model routers for cost-efficient AI queries as ineffective or untrustworthy, citing Copilot picking expensive models, outdated options, and dishonest claims from firms like Cognit.
Pos
37.5%
Neg
62.5%
10 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS2.9KBOOKMARKS14LIKES17REPLIES6
Gergely Orosz@GergelyOrosz
Solutions I collected so far (no affiliation with either):
- Factory Router - Not Diamond - Prism by Augment Code
AI gateways with routing:
- OpenRouter (auto router) - Kilo Gateway - Requestly - LiteLLM (auto routing)
More pointers welcome!
Gergely Orosz@GergelyOrosz
What are "smart" model routers you know of? Services or vendors that take queries and route the most efficient model they deem, saving cost.
I sense there is a massive demand for these, and will be even more...
1hViews 2.9KLikes 17Bookmarks 14
Gergely Orosz@GergelyOrosz
@dabit3 @cognition yes but I have trust issues with Devin, given the company lied about Devin's capabilities on launch, never addressed it, apologized or corrected it
just ignoring Cognition till it happens. 2 years and counting I think
1hViews 498Likes 7Bookmarks 1
nader dabit@dabit3
@GergelyOrosz @cognition Devin
1hViews 414Likes 3
Marc-André Moreau@awakecoding
@GergelyOrosz OpenRouter has one: https://openrouter.ai/openrouter/auto
2hViews 115Likes 2
Matthew Lam@mattlam_
@GergelyOrosz Cognition has adaptive routing right @dabit3
1hViews 114Likes 2
Fer@harderthanfire
@GergelyOrosz Morph also have one: https://docs.morphllm.com/sdk/components/router
1hViews 144Likes 1
VLAD ARBATOV@vladzima
@GergelyOrosz routellm from lmsys is the open source take, martian and notdiamond sell it as a product. NB: router has to judge difficulty with a cheap model, and it misjudges where routing matters
1hViews 107Likes 1
Gergely Orosz@GergelyOrosz
@harderthanfire unclear to me if this works only with their models tho. reads like it?
1hViews 96
Gergely Orosz@GergelyOrosz
@vladzima routellm has not been updated in 2 years tho?
1hViews 91
Fer@harderthanfire
@GergelyOrosz This is their example model selection and you can specify what provider and/or specific models:
1hViews 17Likes 1
yenkel@yenkel
@GergelyOrosz not diamond
@tomas_hk is a beast
1hViews 138Likes 3
Gergely Orosz@GergelyOrosz
@dabit3 @cognition this was the lie in the launch post
integrity matters at startups, and I do not see Cognition having much, never having owed up to this even
http://youtube.com/watch?v=tNmgmwEtoWE
1hViews 418Likes 1
VLAD ARBATOV@vladzima
@GergelyOrosz oh sht you're right I didn't even notice
1hViews 7
Yury Molodtsov ⚡️@y_molodtsov
@awakecoding @GergelyOrosz I though it was about optimizing for quality and not cost?
2hViews 5
nader dabit@dabit3
@mattlam_ @GergelyOrosz Yes! Thanks for tagging
1hViews 32Likes 2
Alex Kates@thealexkates
@GergelyOrosz Copilot auto mode worked well for a minute but feels like it’s picking expensive models on purpose the past few days
2hViews 67Likes 1
Kovács István@kovacsperez
@GergelyOrosz It is not necessarily about cost optimization, but there are routing options in AnythingLLM as well.
1hViews 116
random_user@RandomU94836
@GergelyOrosz There's no such thing as a good router for an agent.
Because: - 1st message is not indicative of "complexity" of a task - if switch in every message => dead cache => high cost
Just use the best open source provider. Don't try to trick yourself with routing.
1hViews 14Likes 1
Harish@code_typist
@GergelyOrosz I've always wondered how effective those would be since the context cache wouldn't be effective. In almost all cases, it would only make sense to switch to a cheaper model and never to a more expensive model.
1hViews 35
Raimon Lapuente 🦞@wolffan
@GergelyOrosz cursor does that
1hViews 30
Load more posts