Which AI models does DekaLLM serve?

Of the models we benchmark, DekaLLM serves 8 through OpenRouter: DeepSeek V4 Pro 0813, GLM 5.3, Qwen3.8 27B, gpt-oss-120b, gpt-oss-20b, Qwen3.6 35B A3B, Gemma 4 31B, Gemma 4 26B A4B.

What is the most accurate model on DekaLLM?

DeepSeek V4 Pro 0813 by DeepSeek, with a verification score of 71.2% (57 of 80 questions correct) in our tests.

Is DekaLLM the cheapest host?

DekaLLM has the lowest list price for 0 of the 8 models it serves that other hosts also serve. Its median markup over the cheapest host is +55%.

How reliable is DekaLLM?

Averaged over the models it serves, DekaLLM reported 99.6% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.

API host · catalogue checked 27 Oct 2026

DekaLLM: models, prices and uptime

DekaLLM 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 for0of 8 shared models

Median premium+55%over the cheapest host

Uptime99.6%last 30 min, average

Most accurate models on DekaLLM

Verification score of each model this host serves

1DeepSeek V4 Pro 0813DeepSeek71.2%
2GLM 5.3Z.ai67.5%
3Qwen3.8 27BQwen63.8%
4gpt-oss-120bOpenAI58.8%
5gpt-oss-20bOpenAI51.2%
6Qwen3.6 35B A3BQwen37.5%
7Gemma 4 31BGoogle30.0%
8Gemma 4 26B A4BGoogle15.0%

Models on DekaLLM

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 Pro 0813	71.2%	$1.08	$3.8	+739%	23	1M	944k	—	100%
GLM 5.3	67.5%	$0.25	$2.95	+130%	37	1M	944k	—	100%
Qwen3.8 27B	63.8%	$0.04	$2.5	+285%	21	262k	236k	—	100%
gpt-oss-120b	58.8%	$0.03	$0.18	+13%	23	131k	118k	bf16	100%
gpt-oss-20b	51.2%	$0.029	$0.14	+58%	10	131k	118k	bf16	100%
Qwen3.6 35B A3B	37.5%	$0.1	$1	+53%	10	262k	236k	—	100%
Gemma 4 31B	30.0%	$0.14	$0.4	+28%	13	262k	236k	—	96.7%
Gemma 4 26B A4B	15.0%	$0.06	$0.33	+47%	15	262k	236k	bf16	100%

All API hosts →

DekaLLM: frequently asked questions

Which AI models does DekaLLM serve?: Of the models we benchmark, DekaLLM serves 8 through OpenRouter: DeepSeek V4 Pro 0813, GLM 5.3, Qwen3.8 27B, gpt-oss-120b, gpt-oss-20b, Qwen3.6 35B A3B, Gemma 4 31B, Gemma 4 26B A4B.
What is the most accurate model on DekaLLM?: DeepSeek V4 Pro 0813 by DeepSeek, with a verification score of 71.2% (57 of 80 questions correct) in our tests.
Is DekaLLM the cheapest host?: DekaLLM has the lowest list price for 0 of the 8 models it serves that other hosts also serve. Its median markup over the cheapest host is +55%.
How reliable is DekaLLM?: Averaged over the models it serves, DekaLLM reported 99.6% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.