API host · catalogue checked 27 Oct 2026

BaseTen: models, prices and uptime

BaseTen serves 8 of the 78 models we benchmark through OpenRouter. Prices are OpenRouter's list prices per million tokens. We did not measure speed per host.

Models served8of 78 we test

Cheapest host for1of 8 shared models

Median premium+298%over the cheapest host

Uptime100%last 30 min, average

Most accurate models on BaseTen

Verification score of each model this host serves

1Muse Spark OpenMeta77.5%
2DeepSeek V4.1 Flash 1017DeepSeek73.8%
3DeepSeek V4 Pro 0813DeepSeek71.2%
4GLM 5.3 FlashZ.ai67.5%
5GLM 5.3Z.ai67.5%
6Nemotron 3 UltraNVIDIA60.0%
7gpt-oss-120bOpenAI58.8%
8Nemotron 3.5 Super VLNVIDIA40.0%

Models on BaseTen

Premium: this host's blended price (3 input : 1 output) against the cheapest host for the same model

Model	Score	Input / 1M	Output / 1M	vs cheapest host	Hosts	Context	Max output	Quantization	Uptime
Muse Spark Open	77.5%	$1.25	$4.25	Cheapest	6	1M	944k	fp4	—
DeepSeek V4.1 Flash 1017	73.8%	$0.3	$1.2	+364%	30	1M	262k	—	100%
DeepSeek V4 Pro 0813	71.2%	$1.32	$3.96	+843%	23	1M	262k	fp4	100%
GLM 5.3 Flash	67.5%	$0.15	$0.5	+406%	34	1M	131k	fp8	—
GLM 5.3	67.5%	$1.4	$4.4	+434%	37	1M	262k	fp4	100%
Nemotron 3 Ultra	60.0%	$0.6	$2.4	+42%	3	203k	183k	fp4	100%
gpt-oss-120b	58.8%	$0.1	$0.5	+233%	23	128k	115k	fp4	100%
Nemotron 3.5 Super VL	40.0%	$0.2	$0.5	+108%	9	1M	944k	fp4	100%

All API hosts →

BaseTen: frequently asked questions

Which AI models does BaseTen serve?: Of the models we benchmark, BaseTen serves 8 through OpenRouter: Muse Spark Open, DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, Nemotron 3 Ultra, gpt-oss-120b, Nemotron 3.5 Super VL.
What is the most accurate model on BaseTen?: Muse Spark Open by Meta, with a verification score of 77.5% (62 of 80 questions correct) in our tests.
Is BaseTen the cheapest host?: BaseTen has the lowest list price for 1 of the 8 models it serves that other hosts also serve (Muse Spark Open). Its median markup over the cheapest host is +298%.
How reliable is BaseTen?: Averaged over the models it serves, BaseTen reported 100% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.

Model

Score

Input / 1M

Output / 1M

vs cheapest host

Hosts

Context

Max output

Quantization

Uptime

Muse Spark Open

77.5%

$1.25

$4.25

Cheapest

944k

fp4

—

DeepSeek V4.1 Flash 1017

73.8%

$0.3

$1.2

+364%

262k

—

100%

DeepSeek V4 Pro 0813

71.2%

$1.32

$3.96

+843%

262k

fp4

100%

GLM 5.3 Flash

67.5%

$0.15

$0.5

+406%

131k

fp8

—

GLM 5.3

67.5%

$1.4

$4.4

+434%

262k

fp4

100%

Nemotron 3 Ultra

60.0%

$0.6

$2.4

+42%

203k

183k

fp4

100%

gpt-oss-120b

58.8%

$0.1

$0.5

+233%

128k

115k

fp4

100%

Nemotron 3.5 Super VL

40.0%

$0.2

$0.5

+108%

944k

fp4

100%

BaseTen: frequently asked questions

Which AI models does BaseTen serve?

Of the models we benchmark, BaseTen serves 8 through OpenRouter: Muse Spark Open, DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, Nemotron 3 Ultra, gpt-oss-120b, Nemotron 3.5 Super VL.

What is the most accurate model on BaseTen?

Muse Spark Open by Meta, with a verification score of 77.5% (62 of 80 questions correct) in our tests.

Is BaseTen the cheapest host?

BaseTen has the lowest list price for 1 of the 8 models it serves that other hosts also serve (Muse Spark Open). Its median markup over the cheapest host is +298%.

How reliable is BaseTen?

Averaged over the models it serves, BaseTen reported 100% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.