DeepSeek: DeepSeek V4 Pro 0813

llm.buzz and DeepInfra tie for the cheapest, and llm.buzz is the fastest provider of this model. DeepInfra 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: $1.63 blended; llm.buzz
Fastest output: 65 tok/s; llm.buzz
Quickest first token: 1.20 s; DeepInfra
Best uptime: 100%; DeepInfra

llm.buzz and DeepInfra tie for the cheapest DeepSeek: DeepSeek V4 Pro 0813, at $1.63 per million tokens blended.
llm.buzz serves DeepSeek: DeepSeek V4 Pro 0813 fastest, at 65 tok/s (median over 24 hours).
DeepInfra starts answering DeepSeek: DeepSeek V4 Pro 0813 quickest, first token in 1.20 s (median over 24 hours).
DeepInfra has the best uptime for DeepSeek: DeepSeek V4 Pro 0813, 100% over 72 hours.

ModelCompare with

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

llm.buzz65 tok/s

DeepInfra54 tok/s

First tokenseconds, median over 24 h, lower is better

DeepInfra1.20 s

llm.buzz6.17 s

Blended price$ per 1M tokens, lower is better

llm.buzz$1.63

DeepInfra$1.63

2 providers

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

llm.buzz	$1.63	$1.30	$2.60	65 tok/stest	6.17 stest	98.6%test
DeepInfra	$1.63	$1.30	$2.60	54 tok/stest	1.20 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

0255075$1.00$1.25$1.50$1.75$2.00$2.25

llm.buzz$1.63 blended, 65 tok/s

DeepInfra$1.63 blended, 54 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.buzz65 tok/s
DeepInfra54 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 08:00	31 tok/s	31 tok/s	31 tok/s
llm.buzz	Oct 26, 13:00	78 tok/s	78 tok/s	78 tok/s
llm.buzz	Oct 26, 17:00	93 tok/s	93 tok/s	93 tok/s
llm.buzz	Oct 26, 21:00	65 tok/s	65 tok/s	65 tok/s
llm.buzz	Oct 27, 01:00	65 tok/s	65 tok/s	65 tok/s
llm.buzz	Last 24 hours	65 tok/s	31 tok/s	31 tok/s
DeepInfra	Oct 26, 05:00	45 tok/s	45 tok/s	45 tok/s
DeepInfra	Oct 26, 09:00	45 tok/s	45 tok/s	45 tok/s
DeepInfra	Oct 26, 14:00	78 tok/s	78 tok/s	78 tok/s
DeepInfra	Oct 26, 18:00	54 tok/s	54 tok/s	54 tok/s
DeepInfra	Oct 26, 22:00	31 tok/s	31 tok/s	31 tok/s
DeepInfra	Oct 27, 03:00	78 tok/s	78 tok/s	78 tok/s
DeepInfra	Last 24 hours	54 tok/s	31 tok/s	31 tok/s

Time to first token

llm.buzz6.17 s
DeepInfra1.20 s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 08:00	4.29 s	4.29 s	4.29 s
llm.buzz	Oct 26, 13:00	31.8 s	31.8 s	31.8 s
llm.buzz	Oct 26, 17:00	15.4 s	15.4 s	15.4 s
llm.buzz	Oct 26, 21:00	6.17 s	6.17 s	6.17 s
llm.buzz	Oct 27, 01:00	2.48 s	2.48 s	2.48 s
llm.buzz	Last 24 hours	6.17 s	31.8 s	31.8 s
DeepInfra	Oct 26, 05:00	1.44 s	1.44 s	1.44 s
DeepInfra	Oct 26, 09:00	1.20 s	1.20 s	1.20 s
DeepInfra	Oct 26, 14:00	0.83 s	0.83 s	0.83 s
DeepInfra	Oct 26, 18:00	5.14 s	5.14 s	5.14 s
DeepInfra	Oct 26, 22:00	5.14 s	5.14 s	5.14 s
DeepInfra	Oct 27, 03:00	1.00 s	1.00 s	1.00 s
DeepInfra	Last 24 hours	1.20 s	5.14 s	5.14 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

DeepInfra

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