PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.008616mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.008616mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.01216mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.01216mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0038 to 0.01347mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01347mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok increased from 0.002 to 0.002147mPRICE~deepseek/deepseek-flash-latest input_per_mtok increased from 0.002 to 0.01547mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01747mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01747mPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.801hPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.001hPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.35 to 1.391hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0058 to 0.00381hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00381hPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.004 to 0.0021hPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.60 to 1.201hPRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.004 to 0.0021hPRICEqwen/qwen3-30b-a3b-instruct-2507 output_per_mtok decreased from 0.30 to 0.191hPRICEqwen/qwen3-30b-a3b-instruct-2507 input_per_mtok decreased from 0.10 to 0.0481hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.0077 to 0.00511hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.0077 to 0.00511hPRICE~z-ai/glm-latest cached_input_per_mtok decreased from 0.18 to 0.082hPRICE~z-ai/glm-latest output_per_mtok increased from 2.99 to 4.002hPRICE~z-ai/glm-latest input_per_mtok increased from 0.083 to 0.122hPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.292hPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.362hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 0.352hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0086 to 0.00582hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00582hPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.0061 to 0.0042hPRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.0061 to 0.0042hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00772hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00772hPRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.06 to 0.182hPRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.992hPRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.0832hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.00862hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.00862hPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.0091 to 0.00612h

Mistral vs OpenRouter

3 shared models · FR vs US · independent benchmarks

Registry facts

FactMistralOpenRouter
Typefirst party model labrouter
HeadquartersFRUS
Catalogued endpoints11
EU residencyYesNo

Mistral Large 3: Mistral vs OpenRouter

● MEASURED Mistral detail → · ● MEASURED OpenRouter detail →

MetricMistralOpenRouter
TTFT p50383 ms406 ms
TTFT p951739 ms—
Throughput73 tok/s81 tok/s
Reliability100%100%
Tool calling100%—
Structured output83.3%—
$ output / M tokens$1.50$1.50

Mistral Medium 3.5: Mistral vs OpenRouter

● MEASURED Mistral detail → · ● MEASURED OpenRouter detail →

MetricMistralOpenRouter
TTFT p50223 ms261 ms
TTFT p95411 ms498 ms
Throughput145 tok/s153 tok/s
Reliability100%100%
Tool calling100%100%
Structured output100%100%
$ output / M tokens$7.50$7.50

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