OpenAI: gpt-oss-120b

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

All benchmarks Model page Try in Playground

Live providers: 3; Same model, one API
Cheapest: $0.10 blended; llm.buzz
Fastest output: 481 tok/s; llm.buzz
Quickest first token: 0.23 s; Scaleway
Best uptime: 100%; Scaleway

llm.buzz and Novita tie for the cheapest OpenAI: gpt-oss-120b, at $0.10 per million tokens blended.
llm.buzz serves OpenAI: gpt-oss-120b fastest, at 481 tok/s (median over 24 hours).
Scaleway starts answering OpenAI: gpt-oss-120b quickest, first token in 0.23 s (median over 24 hours).
Scaleway has the best uptime for OpenAI: gpt-oss-120b, 100% over 72 hours.

ModelCompare with

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

llm.buzz481 tok/s

Novita278 tok/s

Scaleway134 tok/s

First tokenseconds, median over 24 h, lower is better

Scaleway0.23 s

Novita0.58 s

llm.buzz5.14 s

Blended price$ per 1M tokens, lower is better

llm.buzz$0.10

Novita$0.10

Scaleway$0.3025

3 providers

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

llm.buzz	$0.10	$0.05	$0.25	481 tok/stest	5.14 stest	98.6%test
Novita	$0.10	$0.05	$0.25	278 tok/stest	0.58 stest	94.4%test
ScalewayEU	$0.3025	$0.1729	$0.6915	134 tok/stest	0.23 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

0200400600$0.00$0.10$0.20$0.30$0.40

llm.buzz$0.10 blended, 481 tok/s

Novita$0.10 blended, 278 tok/s

Scaleway$0.3025 blended, 134 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.buzz481 tok/s
Novita278 tok/s
Scaleway134 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 07:00	481 tok/s	481 tok/s	481 tok/s
llm.buzz	Oct 26, 12:00	54 tok/s	54 tok/s	54 tok/s
llm.buzz	Oct 26, 21:00	334 tok/s	334 tok/s	334 tok/s
llm.buzz	Oct 27, 01:00	481 tok/s	481 tok/s	481 tok/s
llm.buzz	Last 24 hours	481 tok/s	54 tok/s	54 tok/s
Novita	Oct 26, 07:00	278 tok/s	278 tok/s	278 tok/s
Novita	Oct 26, 11:00	278 tok/s	278 tok/s	278 tok/s
Novita	Oct 26, 15:00	278 tok/s	278 tok/s	278 tok/s
Novita	Oct 26, 20:00	278 tok/s	278 tok/s	278 tok/s
Novita	Oct 27, 01:00	232 tok/s	232 tok/s	232 tok/s
Novita	Last 24 hours	278 tok/s	232 tok/s	232 tok/s
Scaleway	Oct 26, 07:00	112 tok/s	112 tok/s	112 tok/s
Scaleway	Oct 26, 11:00	54 tok/s	54 tok/s	54 tok/s
Scaleway	Oct 26, 15:00	78 tok/s	78 tok/s	78 tok/s
Scaleway	Oct 26, 19:00	134 tok/s	134 tok/s	134 tok/s
Scaleway	Oct 27, 00:00	161 tok/s	161 tok/s	161 tok/s
Scaleway	Oct 27, 04:00	193 tok/s	193 tok/s	193 tok/s
Scaleway	Last 24 hours	134 tok/s	54 tok/s	54 tok/s

Time to first token

llm.buzz5.14 s
Novita0.58 s
Scaleway0.23 s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 07:00	2.07 s	2.07 s	2.07 s
llm.buzz	Oct 26, 12:00	31.8 s	31.8 s	31.8 s
llm.buzz	Oct 26, 16:00	55.0 s	55.0 s	55.0 s
llm.buzz	Oct 26, 21:00	5.14 s	5.14 s	5.14 s
llm.buzz	Oct 27, 01:00	2.98 s	2.98 s	2.98 s
llm.buzz	Last 24 hours	5.14 s	55.0 s	55.0 s
Novita	Oct 26, 07:00	0.58 s	0.58 s	0.58 s
Novita	Oct 26, 11:00	0.58 s	0.58 s	0.58 s
Novita	Oct 26, 15:00	0.58 s	0.58 s	0.58 s
Novita	Oct 26, 20:00	0.58 s	0.58 s	0.58 s
Novita	Oct 27, 01:00	0.48 s	0.48 s	0.48 s
Novita	Last 24 hours	0.58 s	0.58 s	0.58 s
Scaleway	Oct 26, 07:00	0.23 s	0.23 s	0.23 s
Scaleway	Oct 26, 11:00	1.72 s	1.72 s	1.72 s
Scaleway	Oct 26, 15:00	1.20 s	1.20 s	1.20 s
Scaleway	Oct 26, 19:00	0.19 s	0.19 s	0.19 s
Scaleway	Oct 27, 00:00	0.23 s	0.23 s	0.23 s
Scaleway	Oct 27, 04:00	0.19 s	0.19 s	0.19 s
Scaleway	Last 24 hours	0.23 s	1.72 s	1.72 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

Novita

Scaleway

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