OmegaRouter: figures & benchmarks

Evidence for OmegaRouter: 1. Evidence pack · 2. Answers to buyer questions · 3. Figures & benchmarks · 4. Selling tools · IHVRK kit · Learn it · why these pages exist

Every number on this page is read from the signed transcript inside the IHVRK kit; none is typed in by hand.

4/4

claims matched when recorded

attack cases: this kit records normal requests only

1 ms

median round trip (min 0, max 193), incl. network

#	Kind	Claim	Recorded value	HTTP	ms
C01	control	Which provider was chosen? -> The mid model meets the 0.8 bar and is far cheaper.	`"lab-b"`	200	193
C02	control	Quality of the chosen model -> Above the 0.8 minimum: the bar is respected.	`0.85`	200	1
C03	control	Estimated cost of this request -> About 2 cents, versus about 10.5 cents on the top model.	`0.021`	200	0
C04	control	What it was asked to optimise -> The rule you set is the rule it follows.	`"cost"`	200	0

Copy the table (paste into a spreadsheet)

id	kind	claim	recorded_value	expected	http	ms	recorded_at
C01	control	Which provider was chosen? -> The mid model meets the 0.8 bar and is far cheaper.	"lab-b"	["lab-b"]	200	193	2026-11-03T22:54:20+00:00
C02	control	Quality of the chosen model -> Above the 0.8 minimum: the bar is respected.	0.85	[0.85]	200	1	2026-11-03T22:54:21+00:00
C03	control	Estimated cost of this request -> About 2 cents, versus about 10.5 cents on the top model.	0.021	[0.021]	200	0	2026-11-03T22:54:21+00:00
C04	control	What it was asked to optimise -> The rule you set is the rule it follows.	"cost"	["cost"]	200	0	2026-11-03T22:54:22+00:00

Download: figures.tsv · transcript.json (full answers) · whole kit

How to read these numbers

Recorded 2026-11-03T22:54:22+00:00 against cainstudio.online from our build host; times include the internet round trip.
They show these inputs, not every possible input. Known misses are on the limits page.
This is not a load test, an SLA or a third-party benchmark. Re-run it yourself: python3 verify.py --live.