PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.6018m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01318m PRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.0021 to 0.002118m PRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.0021 to 0.00618m PRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.68 to 1.2018m PRICEdeepseek/deepseek-v4.1-flash input_per_mtok increased from 0.015 to 0.3018m PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.001149m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.0449m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.003849m PRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.02 to 0.002149m PRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.60 to 0.6849m PRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.02 to 0.01549m PRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok decreased from 0.02 to 0.002149m PRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.60 to 0.6849m PRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.02 to 0.01549m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.01749m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.01749m PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.012 to 0.00771h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.012 to 0.00771h 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 PRICEdeepseek/deepseek-v3.1-terminus input_per_mtok decreased from 0.30 to 0.271h PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0011 to 0.0122h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.60 to 1.282h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.0122h 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 NEW MODELnvidia/switchyard appeared in the catalogue2h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.602h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.0132h PRICEnvidia/nemotron-3-ultra-550b-a55b cached_input_per_mtok decreased from 0.12 to 0.102h PRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok decreased from 2.40 to 2.202h PRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok decreased from 0.60 to 0.502h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.0172h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.0172h PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.293h PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.363h PRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.003h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.95 to 1.043h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00383h

PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.6018m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01318m PRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.0021 to 0.002118m PRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.0021 to 0.00618m PRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.68 to 1.2018m PRICEdeepseek/deepseek-v4.1-flash input_per_mtok increased from 0.015 to 0.3018m PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.001149m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.0449m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.003849m PRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.02 to 0.002149m PRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.60 to 0.6849m PRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.02 to 0.01549m PRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok decreased from 0.02 to 0.002149m PRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.60 to 0.6849m PRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.02 to 0.01549m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.01749m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.01749m PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.012 to 0.00771h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.012 to 0.00771h 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 PRICEdeepseek/deepseek-v3.1-terminus input_per_mtok decreased from 0.30 to 0.271h PRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0011 to 0.0122h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.60 to 1.282h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.0122h 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 NEW MODELnvidia/switchyard appeared in the catalogue2h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.602h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.0132h PRICEnvidia/nemotron-3-ultra-550b-a55b cached_input_per_mtok decreased from 0.12 to 0.102h PRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok decreased from 2.40 to 2.202h PRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok decreased from 0.60 to 0.502h PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.0172h PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.0172h PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.293h PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.363h PRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.39 to 1.003h PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.95 to 1.043h PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0058 to 0.00383h

Cookie Policy

The technologies InferenceBench actually uses in your browser.

Version 1.0Effective August 15, 2026Last updated August 15, 2026

What cookies are

Cookies and similar technologies (such as localStorage) are small pieces of data a website stores in your browser to remember state between requests or visits.

How InferenceBench uses them

InferenceBench currently uses only technologies necessary to operate the service. As of the effective date of this policy, the site sets no cookies, uses no localStorage-based tracking, and loads no third-party analytics, advertising or social scripts. Because no technology requiring consent is in use, no cookie consent banner is shown.

Necessary technologies

No cookies are currently set in this category. Strictly technical, non-identifying operations (such as serving pages) do not store data in your browser.

Preferences

Currently not used.

Analytics

Currently not used.

Marketing

Currently not used.

Policy changes

Material changes — including the introduction of any cookie — will be reflected by a new version, an updated table above and, where required, a consent mechanism before activation.

Contact

Contact: support@inferencebench.dev