How Architect launched Liquid Inference on X

38K views, ranked 1759 of the 1981 launches we track. It was saved at well above the usual rate, which is the signal that matters more than reach for anything with a considered purchase behind it.

Posted 2026-10-07 by @BrettHarrison · engagement read 2026-10-19

Architect launch post on X0:44
Brett Harrison
Brett Harrison
@BrettHarrison · 71K followers
Open on X →

Introducing Liquid Inference by Architect, a new LLM model router where inference providers compete dynamically to offer lowest-cost tokens. Providers onboard in minutes, not weeks. Buyers have full price visibility and receive 20% of referred fees in free inference. More info:

323 likes41 reposts 60 replies20 quotes 125 bookmarks
38K
Views
0x the median launch
#1759
Of the launches we track
out of 1981
1x
Its own following
71K followers
32.6
Saves per 10K views
2.8x the median rate

How it compares

A launch means nothing against no one. These are the launches it is actually comparable to, and where this one sits among them.

Compared withLaunchesMedian viewsThis oneRank
Product release
the same kind of announcement
954692K0.1x852
25K to 100K followers
accounts of a similar size
264963K0.0x245
Every launch
all of them, for scale
1981688K0.1x1759

What this launch shows

Architect posted this from an account with 71K followers and reached about 54.1% of them. Accounts of that size usually reach 20.9 times their following.

This one did not get far past the people who already followed it. It ranks 245 of 264 launches from accounts that size. Against every launch in the directory it is below the median of 688K views, at rank 1759 of 1981.

Replies led. 60 of them, 15.6 per 10,000 views against a median of 2.3.

The post started a conversation, and the ranking model pays for conversation with reach in the hours after. Bookmarks came in at 125, reposts at 41.

The post opens with “Introducing Liquid Inference by Architect, a new LLM model router where inference providers compete dynamically to offer lowest-cost…”, the same first word as 25% of launches in the directory.

It carries a 44-second video against a directory median of 65 seconds. Videos between 30 and 90 seconds have a median of 603K views in the directory.

The copy runs 42 words, about the usual length for a launch post here, where the median is 41. There is a link in the body, which costs a post some reach and buys it a place to send people.

It went out on a Wednesday. Launches posted on a Wednesday have a median of 721K views in the directory, and Friday is the strongest day at 880K.

Attributing signups to a launch covers this: a save rate this high is the number to follow into the product. For the next one, read giving people something to reply to: the conversation is what carried this one.

Why posts from large accounts under-reach is the guide for it: a post seen by fewer people than follow the account was held back by the ranking model.

Questions about this launch

When did Architect launch Liquid Inference?

Architect posted the launch on X on 7 October 2026.

How many views did the Liquid Inference launch post get?

38,400 views at the last read, ranked 1759 of the 1981 AI launches Doomers tracks, 1 times the account's following.

Who posted the Liquid Inference launch?

@BrettHarrison, which has 71K followers.

Planning something like this?

We run launches on X for AI companies, with creators who already hold the audience you want reaching.