Anthropic: Claude Sonnet 5.5

Anthropic and llm.buzz tie for the cheapest, and Anthropic is the fastest provider of this model. llm.buzz costs the same as a provider on the line, for less speed.

All benchmarks Model page Try in Playground

Live providers: 2; Same model, one API
Cheapest: $4.00 blended; llm.buzz
Fastest output: 997 tok/s; Anthropic
Quickest first token: 2.98 s; Anthropic
Best uptime: 100%; Anthropic

llm.buzz and Anthropic tie for the cheapest Anthropic: Claude Sonnet 5.5, at $4.00 per million tokens blended.
Anthropic serves Anthropic: Claude Sonnet 5.5 fastest, at 997 tok/s (median over 24 hours).
Anthropic starts answering Anthropic: Claude Sonnet 5.5 quickest, first token in 2.98 s (median over 24 hours).
Anthropic has the best uptime for Anthropic: Claude Sonnet 5.5, 100% over 72 hours.

ModelCompare with

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

Anthropic997 tok/s

llm.buzz134 tok/s

First tokenseconds, median over 24 h, lower is better

Anthropic2.98 s

llm.buzz7.41 s

Blended price$ per 1M tokens, lower is better

llm.buzz$4.00

Anthropic$4.00

2 providers

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

llm.buzz	$4.00	$2.00	$10.00	134 tok/stest	7.41 stest	97.1%test
Anthropic	$4.00	$2.00	$10.00	997 tok/stest	2.98 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

04008001200$2.00$3.00$4.00$5.00$6.00

llm.buzz$4.00 blended, 134 tok/s

Anthropic$4.00 blended, 997 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

llm.buzz134 tok/s
Anthropic997 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 06:00	134 tok/s	134 tok/s	134 tok/s
llm.buzz	Oct 26, 10:00	161 tok/s	161 tok/s	161 tok/s
llm.buzz	Oct 26, 19:00	112 tok/s	112 tok/s	112 tok/s
llm.buzz	Oct 27, 00:00	93 tok/s	93 tok/s	93 tok/s
llm.buzz	Last 24 hours	134 tok/s	93 tok/s	93 tok/s
Anthropic	Oct 26, 05:00	1196 tok/s	1196 tok/s	1196 tok/s
Anthropic	Oct 26, 20:00	997 tok/s	997 tok/s	997 tok/s
Anthropic	Oct 27, 01:00	997 tok/s	997 tok/s	997 tok/s
Anthropic	Last 24 hours	997 tok/s	997 tok/s	997 tok/s

Time to first token

llm.buzz7.41 s
Anthropic2.98 s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 06:00	3.57 s	3.57 s	3.57 s
llm.buzz	Oct 26, 10:00	10.7 s	10.7 s	10.7 s
llm.buzz	Oct 26, 14:00	45.9 s	45.9 s	45.9 s
llm.buzz	Oct 26, 19:00	7.41 s	7.41 s	7.41 s
llm.buzz	Oct 27, 00:00	2.48 s	2.48 s	2.48 s
llm.buzz	Last 24 hours	7.41 s	45.9 s	45.9 s
Anthropic	Oct 26, 05:00	2.98 s	2.98 s	2.98 s
Anthropic	Oct 26, 10:00	2.98 s	2.98 s	2.98 s
Anthropic	Oct 26, 15:00	3.57 s	3.57 s	3.57 s
Anthropic	Oct 26, 20:00	2.98 s	2.98 s	2.98 s
Anthropic	Oct 27, 01:00	6.17 s	6.17 s	6.17 s
Anthropic	Last 24 hours	2.98 s	6.17 s	6.17 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

Anthropic

Up: 95% or more served
Degraded: 85% to 95%
Down: below 85%
No data
From llm.buzz's test requests

How we measure

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.

Get API key