Surogate: Surogate 3.7 Flash

Simpleminds EU is both the cheapest and the fastest provider of this model. Surogate Spark costs more for less speed than a provider on the line.

Simpleminds EU serves Surogate: Surogate 3.7 Flash cheapest, at $0.2625 per million tokens blended.
Simpleminds EU serves Surogate: Surogate 3.7 Flash fastest, at 112 tok/s (median over 24 hours).
Simpleminds EU starts answering Surogate: Surogate 3.7 Flash quickest, first token in 0.04 s (median over 24 hours).
Simpleminds EU has the best uptime for Surogate: Surogate 3.7 Flash, 100% over 72 hours.

ModelCompare with

Output speedtok/s, median over 24 h, higher is better

Simpleminds EU112 tok/s

Surogate Spark112 tok/s

First tokenseconds, median over 24 h, lower is better

Simpleminds EU0.04 s

Surogate Spark0.04 s

Blended price$ per 1M tokens, lower is better

Simpleminds EU$0.2625

Surogate Spark$0.3625

2 providers

Providers with their prices and measured figures. Select a column header to sort by it.

Simpleminds EUEU	$0.2625	$0.10	$0.75	112 tok/stest	0.04 stest	100%test
Surogate SparkEU	$0.3625	$0.15	$1.00	112 tok/stest	0.04 stest	100%test

Speed against priceOutput speed in tok/s (median over 24 h), against the blended pricenobody beats these on both price and speed

050100150$0.20$0.25$0.30$0.35$0.40

Simpleminds EU$0.2625 blended, 112 tok/s

Surogate Spark$0.3625 blended, 112 tok/s

Blended price, $ per million tokens (3 input to 1 output)

Customer traffic on this model is still below the publishing floor, so its figures are from llm.buzz's test requests, tagged "test".

The last 24 hours, by hour

Last 24 hours, from llm.buzz's test requests

Output speed, tok/s

Data table

Provider	From (UTC)	p50	p90	p99
Simpleminds EU	Oct 26, 06:00	112 tok/s	112 tok/s	112 tok/s
Simpleminds EU	Oct 26, 11:00	112 tok/s	112 tok/s	112 tok/s
Simpleminds EU	Oct 26, 16:00	112 tok/s	112 tok/s	112 tok/s
Simpleminds EU	Oct 26, 21:00	112 tok/s	112 tok/s	112 tok/s
Simpleminds EU	Oct 27, 01:00	112 tok/s	112 tok/s	112 tok/s
Simpleminds EU	Last 24 hours	112 tok/s	112 tok/s	112 tok/s
Surogate Spark	Oct 26, 08:00	112 tok/s	112 tok/s	112 tok/s
Surogate Spark	Oct 26, 12:00	134 tok/s	134 tok/s	134 tok/s
Surogate Spark	Oct 26, 17:00	112 tok/s	112 tok/s	112 tok/s
Surogate Spark	Oct 26, 21:00	112 tok/s	112 tok/s	112 tok/s
Surogate Spark	Oct 27, 02:00	112 tok/s	112 tok/s	112 tok/s
Surogate Spark	Last 24 hours	112 tok/s	112 tok/s	112 tok/s

Time to first token

Data table

Provider	From (UTC)	p50	p90	p99
Simpleminds EU	Oct 26, 06:00	0.04 s	0.04 s	0.04 s
Simpleminds EU	Oct 26, 11:00	0.04 s	0.04 s	0.04 s
Simpleminds EU	Oct 26, 16:00	0.07 s	0.07 s	0.07 s
Simpleminds EU	Oct 26, 21:00	0.04 s	0.04 s	0.04 s
Simpleminds EU	Oct 27, 01:00	0.04 s	0.04 s	0.04 s
Simpleminds EU	Last 24 hours	0.04 s	0.07 s	0.07 s
Surogate Spark	Oct 26, 08:00	0.04 s	0.04 s	0.04 s
Surogate Spark	Oct 26, 12:00	0.04 s	0.04 s	0.04 s
Surogate Spark	Oct 26, 17:00	0.05 s	0.05 s	0.05 s
Surogate Spark	Oct 26, 21:00	0.04 s	0.04 s	0.04 s
Surogate Spark	Oct 27, 02:00	0.04 s	0.04 s	0.04 s
Surogate Spark	Last 24 hours	0.04 s	0.05 s	0.05 s

Last 72 hours, by hour

Best provider 100%

This model

Simpleminds EU

Surogate Spark

Speed and first tokenOutput speed and time to first token are medians over the last 24 hours, per provider, from text requests.
UptimeThe share of attempts the provider served over the 72 hours before the figures' end, provider failures counted against it.
Two sourcesCustomer traffic once enough organizations count toward a figure; below that, llm.buzz's test requests, short streamed requests sent to every live provider. The tables tag those "test".
PriceEach provider's price per million tokens, with a running discount applied. The blended price weighs input and output 3 to 1, a chat request's usual mix.

Let the router pickName the model; llm.buzz sends each request to a provider and moves to the next when one fails.