PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.6017m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01317m PRICEnvidia/nemotron-3-ultra-550b-a55b cached_input_per_mtok decreased from 0.12 to 0.1017m PRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok decreased from 2.40 to 2.2017m PRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok decreased from 0.60 to 0.5017m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01717m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01717m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.2948m PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.3648m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.0048m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.95 to 1.0448m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.003848m PRICEinclusionai/ling-3.0-flash-fin cached_input_per_mtok decreased from 0.012 to 0.008448m PRICEinclusionai/ling-3.0-flash-fin output_per_mtok decreased from 0.18 to 0.1248m PRICEinclusionai/ling-3.0-flash-fin input_per_mtok decreased from 0.06 to 0.04248m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.0077 to 0.005148m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.0077 to 0.005148m PRICE~z-ai/glm-flash-latest output_per_mtok increased from 0.60 to 0.931h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.20 to 0.951h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00581h PRICEz-ai/glm-5.2 cached_input_per_mtok decreased from 0.32 to 0.261h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00771h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00771h PRICE~moonshotai/kimi-latest input_per_mtok increased from 1.34 to 1.392h PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0038 to 0.00112h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.00862h PRICEgoogle/gemma-4-26b-a4b-it cached_input_per_mtok decreased from 0.05 to 0.0382h PRICEgoogle/gemma-4-26b-a4b-it output_per_mtok decreased from 0.30 to 0.232h PRICEgoogle/gemma-4-26b-a4b-it input_per_mtok decreased from 0.09 to 0.0682h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.0122h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.0122h PRICE~z-ai/glm-flash-latest output_per_mtok decreased from 0.90 to 0.602h PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0058 to 0.00382h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.47 to 1.202h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00382h PRICEz-ai/glm-5.2 cached_input_per_mtok increased from 0.26 to 0.322h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.0172h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.0172h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.803h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.003h

PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.6017m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01317m PRICEnvidia/nemotron-3-ultra-550b-a55b cached_input_per_mtok decreased from 0.12 to 0.1017m PRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok decreased from 2.40 to 2.2017m PRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok decreased from 0.60 to 0.5017m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01717m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01717m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.2948m PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.3648m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.0048m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.95 to 1.0448m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.003848m PRICEinclusionai/ling-3.0-flash-fin cached_input_per_mtok decreased from 0.012 to 0.008448m PRICEinclusionai/ling-3.0-flash-fin output_per_mtok decreased from 0.18 to 0.1248m PRICEinclusionai/ling-3.0-flash-fin input_per_mtok decreased from 0.06 to 0.04248m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.0077 to 0.005148m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.0077 to 0.005148m PRICE~z-ai/glm-flash-latest output_per_mtok increased from 0.60 to 0.931h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.20 to 0.951h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00581h PRICEz-ai/glm-5.2 cached_input_per_mtok decreased from 0.32 to 0.261h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00771h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00771h PRICE~moonshotai/kimi-latest input_per_mtok increased from 1.34 to 1.392h PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0038 to 0.00112h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.00862h PRICEgoogle/gemma-4-26b-a4b-it cached_input_per_mtok decreased from 0.05 to 0.0382h PRICEgoogle/gemma-4-26b-a4b-it output_per_mtok decreased from 0.30 to 0.232h PRICEgoogle/gemma-4-26b-a4b-it input_per_mtok decreased from 0.09 to 0.0682h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.0122h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.0122h PRICE~z-ai/glm-flash-latest output_per_mtok decreased from 0.90 to 0.602h PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0058 to 0.00382h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.47 to 1.202h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00382h PRICEz-ai/glm-5.2 cached_input_per_mtok increased from 0.26 to 0.322h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.0172h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.0172h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.803h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.003h

Cortecs vs OpenRouter

12 shared models · AT vs US · independent benchmarks

Registry facts

Fact	Cortecs	OpenRouter
Type	ai gateway	router
Headquarters	AT	US
Catalogued endpoints	1	1
EU residency	Yes	No

GLM-5.2: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	425 ms	480 ms
TTFT p95	2067 ms	1131 ms
Throughput	142 tok/s	137 tok/s
Reliability	100%	99.1%
Tool calling	100%	100%
Structured output	100%	71.4%
$ output / M tokens	$3.33	$3.99

DeepSeek V4 Pro: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	480 ms	1086 ms
TTFT p95	3019 ms	3466 ms
Throughput	140 tok/s	63 tok/s
Reliability	100%	100%
Tool calling	100%	100%
Structured output	95.2%	97.6%
$ output / M tokens	$3.50	$0.42

DeepSeek V4 Flash: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	411 ms	1059 ms
TTFT p95	1263 ms	8863 ms
Throughput	73 tok/s	89 tok/s
Reliability	100%	100%
Tool calling	100%	100%
Structured output	100%	92.9%
$ output / M tokens	$0.18	$0.056

Kimi K3: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	624 ms	674 ms
TTFT p95	1566 ms	3408 ms
Throughput	171 tok/s	90 tok/s
Reliability	100%	97.2%
Tool calling	100%	100%
Structured output	100%	100%
$ output / M tokens	$15.43	$13.50

MiniMax M3: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	517 ms	929 ms
TTFT p95	5962 ms	3033 ms
Throughput	90 tok/s	75 tok/s
Reliability	100%	99.5%
Tool calling	100%	100%
Structured output	100%	97.6%
$ output / M tokens	$1.23	$1.20

GPT-OSS 120B: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	240 ms	474 ms
TTFT p95	501 ms	1413 ms
Throughput	358 tok/s	68 tok/s
Reliability	100%	99.1%
Tool calling	100%	100%
Structured output	100%	100%
$ output / M tokens	$0.46	$0.17

GPT-OSS 20B: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	175 ms	656 ms
TTFT p95	588 ms	1946 ms
Throughput	67 tok/s	77 tok/s
Reliability	99.5%	100%
Tool calling	100%	100%
Structured output	100%	95.2%
$ output / M tokens	$0.17	$0.09

Qwen3-235B: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	937 ms	766 ms
TTFT p95	5613 ms	3027 ms
Throughput	52 tok/s	59 tok/s
Reliability	99.5%	100%
Tool calling	98%	100%
Structured output	100%	100%
$ output / M tokens	$0.47	$0.35

Llama 3.3 70B: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	441 ms	576 ms
TTFT p95	1051 ms	4604 ms
Throughput	51 tok/s	38 tok/s
Reliability	100%	100%
Tool calling	98%	100%
Structured output	100%	100%
$ output / M tokens	$0.75	$0.32

Mistral Large 3: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	413 ms	406 ms
TTFT p95	739 ms	—
Throughput	80 tok/s	81 tok/s
Reliability	100%	100%
Tool calling	100%	—
Structured output	85.7%	—
$ output / M tokens	$1.89	$1.50

Mistral Medium 3.5: Cortecs vs OpenRouter

● MEASURED Cortecs detail → · ● MEASURED OpenRouter detail →

Metric	Cortecs	OpenRouter
TTFT p50	261 ms	261 ms
TTFT p95	441 ms	498 ms
Throughput	153 tok/s	153 tok/s
Reliability	99.5%	100%
Tool calling	100%	100%
Structured output	100%	100%
$ output / M tokens	$8.07	$7.50

Every figure above is an independent measurement from the canonical vantage; unmeasured fields show — until measured. How we benchmark →