Which AI models does InferenceNet serve?

Of the models we benchmark, InferenceNet serves 5 through OpenRouter: DeepSeek V4.1 Flash 1017, GLM 5.3 Flash, GLM 5.3, MiniMax M3.1 Flash, Step 5 Preview.

What is the most accurate model on InferenceNet?

DeepSeek V4.1 Flash 1017 by DeepSeek, with a verification score of 73.8% (59 of 80 questions correct) in our tests.

Is InferenceNet the cheapest host?

InferenceNet has the lowest list price for 1 of the 5 models it serves that other hosts also serve (Step 5 Preview). Its median markup over the cheapest host is +74%.

How reliable is InferenceNet?

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

API host · catalogue checked 27 Oct 2026

InferenceNet: models, prices and uptime

InferenceNet serves 5 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 served5of 78 we test

Cheapest host for1of 5 shared models

Median premium+74%over the cheapest host

Uptime100%last 30 min, average

Most accurate models on InferenceNet

Verification score of each model this host serves

1DeepSeek V4.1 Flash 1017DeepSeek73.8%
2GLM 5.3 FlashZ.ai67.5%
3GLM 5.3Z.ai67.5%
4MiniMax M3.1 FlashMiniMax66.2%
5Step 5 PreviewStepFun63.8%

Models on InferenceNet

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
DeepSeek V4.1 Flash 1017	73.8%	$0.08	$0.55	+74%	30	1M	393k	fp8	100%
GLM 5.3 Flash	67.5%	$0.12	$0.388	+299%	34	1M	262k	fp4	100%
GLM 5.3	67.5%	$0.08	$3.6	+139%	37	1M	944k	fp4	100%
MiniMax M3.1 Flash	66.2%	$0.15	$0.6	+5%	11	1M	524k	fp4	100%
Step 5 Preview	63.8%	$1	$2.7	Cheapest	4	1M	131k	fp4	100%

All API hosts →

InferenceNet: frequently asked questions

Which AI models does InferenceNet serve?: Of the models we benchmark, InferenceNet serves 5 through OpenRouter: DeepSeek V4.1 Flash 1017, GLM 5.3 Flash, GLM 5.3, MiniMax M3.1 Flash, Step 5 Preview.
What is the most accurate model on InferenceNet?: DeepSeek V4.1 Flash 1017 by DeepSeek, with a verification score of 73.8% (59 of 80 questions correct) in our tests.
Is InferenceNet the cheapest host?: InferenceNet has the lowest list price for 1 of the 5 models it serves that other hosts also serve (Step 5 Preview). Its median markup over the cheapest host is +74%.
How reliable is InferenceNet?: Averaged over the models it serves, InferenceNet reported 100% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.