Which AI models does ModelRun serve?

Of the models we benchmark, ModelRun serves 5 through OpenRouter: GLM 5.3, MiniMax M3.1 Flash, Qwen3.8 27B, MiniMax M3, Gemma 4 31B.

What is the most accurate model on ModelRun?

GLM 5.3 by Z.ai, with a verification score of 67.5% (54 of 80 questions correct) in our tests.

Is ModelRun the cheapest host?

ModelRun has the lowest list price for 0 of the 5 models it serves that other hosts also serve. Its median markup over the cheapest host is +356%.

How reliable is ModelRun?

Averaged over the models it serves, ModelRun reported 75.0% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.

API host · catalogue checked 27 Oct 2026

ModelRun: models, prices and uptime

ModelRun 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 for0of 5 shared models

Median premium+356%over the cheapest host

Uptime75.0%last 30 min, average

Most accurate models on ModelRun

Verification score of each model this host serves

1GLM 5.3Z.ai67.5%
2MiniMax M3.1 FlashMiniMax66.2%
3Qwen3.8 27BQwen63.8%
4MiniMax M3MiniMax57.5%
5Gemma 4 31BGoogle30.0%

Models on ModelRun

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
GLM 5.3	67.5%	$2.1	$6.6	+701%	37	1M	524k	fp4	—
MiniMax M3.1 Flash	66.2%	$0.15	$0.6	+5%	11	1M	944k	fp4	100%
Qwen3.8 27B	63.8%	$0.2	$2.5	+356%	21	262k	236k	fp4	100%
MiniMax M3	57.5%	$0.3	$1.3	+42%	12	1M	944k	fp8	0.0%
Gemma 4 31B	30.0%	$0.75	$1	+408%	13	262k	236k	fp4	100%

All API hosts →

ModelRun: frequently asked questions

Which AI models does ModelRun serve?: Of the models we benchmark, ModelRun serves 5 through OpenRouter: GLM 5.3, MiniMax M3.1 Flash, Qwen3.8 27B, MiniMax M3, Gemma 4 31B.
What is the most accurate model on ModelRun?: GLM 5.3 by Z.ai, with a verification score of 67.5% (54 of 80 questions correct) in our tests.
Is ModelRun the cheapest host?: ModelRun has the lowest list price for 0 of the 5 models it serves that other hosts also serve. Its median markup over the cheapest host is +356%.
How reliable is ModelRun?: Averaged over the models it serves, ModelRun reported 75.0% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.