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

Cortecs vs Together

10 shared models · AT vs US · independent benchmarks

Registry facts

FactCortecsTogether
Typeai gatewayinference host
HeadquartersATUS
Catalogued endpoints11
EU residencyYesNo

GLM-5.2: Cortecs vs Together

● MEASURED Cortecs detail → · ● MEASURED Together detail →

MetricCortecsTogether
TTFT p50425 ms271 ms
TTFT p952067 ms589 ms
Throughput142 tok/s283 tok/s
Reliability100%100%
Tool calling100%100%
Structured output100%100%
$ output / M tokens$3.33$4.40

DeepSeek V4 Flash: Cortecs vs Together

● MEASURED Cortecs detail → · ● MEASURED Together detail →

MetricCortecsTogether
TTFT p50411 ms714 ms
TTFT p951263 ms1866 ms
Throughput73 tok/s61 tok/s
Reliability100%98.6%
Tool calling100%100%
Structured output100%100%
$ output / M tokens$0.18$0.28

Kimi K3: Cortecs vs Together

● MEASURED Cortecs detail → · ● MEASURED Together detail →

MetricCortecsTogether
TTFT p50624 ms602 ms
TTFT p951566 ms1514 ms
Throughput171 tok/s104 tok/s
Reliability100%99.5%
Tool calling100%100%
Structured output100%97.6%
$ output / M tokens$15.43$13.50

MiniMax M3: Cortecs vs Together

● MEASURED Cortecs detail → · ● MEASURED Together detail →

MetricCortecsTogether
TTFT p50517 ms542 ms
TTFT p955962 ms1736 ms
Throughput90 tok/s132 tok/s
Reliability100%100%
Tool calling100%100%
Structured output100%97.6%
$ output / M tokens$1.23$1.20

GPT-OSS 120B: Cortecs vs Together

● MEASURED Cortecs detail → · ● MEASURED Together detail →

MetricCortecsTogether
TTFT p50240 ms182 ms
TTFT p95501 ms467 ms
Throughput358 tok/s138 tok/s
Reliability100%93.5%
Tool calling100%100%
Structured output100%85.7%
$ output / M tokens$0.46$0.60

Llama 3.3 70B: Cortecs vs Together

● MEASURED Cortecs detail → · ● MEASURED Together detail →

MetricCortecsTogether
TTFT p50441 ms618 ms
TTFT p951051 ms1761 ms
Throughput51 tok/s61 tok/s
Reliability100%100%
Tool calling98%98%
Structured output100%100%
$ output / M tokens$0.75$1.04

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