Z.ai: GLM 5.3 Flash

llm.buzz, Prime Intellect, DeepInfra and Novita tie for the cheapest, and llm.buzz is the fastest provider of this model. Prime Intellect, DeepInfra and Novita cost the same as a provider on the line, for less speed.

All benchmarks Model page Try in Playground

Live providers: 4; Same model, one API
Cheapest: $0.2375 blended; llm.buzz
Fastest output: 193 tok/s; llm.buzz
Quickest first token: 0.69 s; Prime Intellect
Best uptime: 100%; Prime Intellect

llm.buzz, Prime Intellect, DeepInfra and Novita tie for the cheapest Z.ai: GLM 5.3 Flash, at $0.2375 per million tokens blended.
llm.buzz serves Z.ai: GLM 5.3 Flash fastest, at 193 tok/s (median over 24 hours).
Prime Intellect starts answering Z.ai: GLM 5.3 Flash quickest, first token in 0.69 s (median over 24 hours).
Prime Intellect has the best uptime for Z.ai: GLM 5.3 Flash, 100% over 72 hours.

ModelCompare with

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

llm.buzz193 tok/s

Novita93 tok/s

Prime Intellect65 tok/s

DeepInfra31 tok/s

First tokenseconds, median over 24 h, lower is better

Prime Intellect0.69 s

DeepInfra0.83 s

llm.buzz2.48 s

Novita2.48 s

Blended price$ per 1M tokens, lower is better

llm.buzz$0.2375

Prime Intellect$0.2375

DeepInfra$0.2375

Novita$0.2375

4 providers

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

llm.buzz	$0.2375	$0.15	$0.50	193 tok/stest	2.48 stest	98.6%test
Prime Intellect	$0.2375	$0.15	$0.50	65 tok/stest	0.69 stest	100%test
DeepInfra	$0.2375	$0.15	$0.50	31 tok/stest	0.83 stest	93%test
Novita	$0.2375	$0.15	$0.50	93 tok/stest	2.48 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

080160240$0.15$0.20$0.25$0.30$0.35

llm.buzz$0.2375 blended, 193 tok/s

Prime Intellect$0.2375 blended, 65 tok/s

DeepInfra$0.2375 blended, 31 tok/s

Novita$0.2375 blended, 93 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.buzz193 tok/s
Prime Intellect65 tok/s
DeepInfra31 tok/s
Novita93 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 05:00	334 tok/s	334 tok/s	334 tok/s
llm.buzz	Oct 26, 09:00	193 tok/s	193 tok/s	193 tok/s
llm.buzz	Oct 26, 14:00	65 tok/s	65 tok/s	65 tok/s
llm.buzz	Oct 26, 19:00	93 tok/s	93 tok/s	93 tok/s
llm.buzz	Oct 26, 23:00	65 tok/s	65 tok/s	65 tok/s
llm.buzz	Oct 27, 04:00	193 tok/s	193 tok/s	193 tok/s
llm.buzz	Last 24 hours	193 tok/s	65 tok/s	65 tok/s
Prime Intellect	Oct 26, 06:00	37 tok/s	37 tok/s	37 tok/s
Prime Intellect	Oct 26, 11:00	65 tok/s	65 tok/s	65 tok/s
Prime Intellect	Oct 26, 15:00	65 tok/s	65 tok/s	65 tok/s
Prime Intellect	Oct 26, 20:00	54 tok/s	54 tok/s	54 tok/s
Prime Intellect	Oct 27, 01:00	278 tok/s	278 tok/s	278 tok/s
Prime Intellect	Last 24 hours	65 tok/s	37 tok/s	37 tok/s
DeepInfra	Oct 26, 07:00	31 tok/s	31 tok/s	31 tok/s
DeepInfra	Oct 26, 15:00	18 tok/s	18 tok/s	18 tok/s
DeepInfra	Oct 26, 19:00	8.7 tok/s	8.7 tok/s	8.7 tok/s
DeepInfra	Oct 26, 23:00	65 tok/s	65 tok/s	65 tok/s
DeepInfra	Oct 27, 03:00	78 tok/s	78 tok/s	78 tok/s
DeepInfra	Last 24 hours	31 tok/s	8.7 tok/s	8.7 tok/s
Novita	Oct 26, 06:00	134 tok/s	134 tok/s	134 tok/s
Novita	Oct 26, 11:00	78 tok/s	78 tok/s	78 tok/s
Novita	Oct 26, 15:00	112 tok/s	112 tok/s	112 tok/s
Novita	Oct 26, 20:00	54 tok/s	54 tok/s	54 tok/s
Novita	Oct 27, 00:00	37 tok/s	37 tok/s	37 tok/s
Novita	Oct 27, 04:00	93 tok/s	93 tok/s	93 tok/s
Novita	Last 24 hours	93 tok/s	37 tok/s	37 tok/s

Time to first token

llm.buzz2.48 s
Prime Intellect0.69 s
DeepInfra0.83 s
Novita2.48 s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 05:00	2.07 s	2.07 s	2.07 s
llm.buzz	Oct 26, 09:00	3.57 s	3.57 s	3.57 s
llm.buzz	Oct 26, 14:00	38.2 s	38.2 s	38.2 s
llm.buzz	Oct 26, 19:00	2.48 s	2.48 s	2.48 s
llm.buzz	Oct 26, 23:00	5.14 s	5.14 s	5.14 s
llm.buzz	Oct 27, 04:00	1.72 s	1.72 s	1.72 s
llm.buzz	Last 24 hours	2.48 s	38.2 s	38.2 s
Prime Intellect	Oct 26, 06:00	0.83 s	0.83 s	0.83 s
Prime Intellect	Oct 26, 11:00	0.69 s	0.69 s	0.69 s
Prime Intellect	Oct 26, 15:00	0.58 s	0.58 s	0.58 s
Prime Intellect	Oct 26, 20:00	0.83 s	0.83 s	0.83 s
Prime Intellect	Oct 27, 01:00	0.40 s	0.40 s	0.40 s
Prime Intellect	Last 24 hours	0.69 s	0.83 s	0.83 s
DeepInfra	Oct 26, 07:00	0.69 s	0.69 s	0.69 s
DeepInfra	Oct 26, 15:00	1.00 s	1.00 s	1.00 s
DeepInfra	Oct 26, 19:00	1.44 s	1.44 s	1.44 s
DeepInfra	Oct 26, 23:00	0.83 s	0.83 s	0.83 s
DeepInfra	Oct 27, 03:00	0.83 s	0.83 s	0.83 s
DeepInfra	Last 24 hours	0.83 s	1.44 s	1.44 s
Novita	Oct 26, 06:00	2.98 s	2.98 s	2.98 s
Novita	Oct 26, 11:00	1.72 s	1.72 s	1.72 s
Novita	Oct 26, 15:00	2.98 s	2.98 s	2.98 s
Novita	Oct 26, 20:00	4.29 s	4.29 s	4.29 s
Novita	Oct 27, 00:00	2.48 s	2.48 s	2.48 s
Novita	Oct 27, 04:00	1.72 s	1.72 s	1.72 s
Novita	Last 24 hours	2.48 s	4.29 s	4.29 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

Prime Intellect

DeepInfra

Novita

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