PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8020mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0020mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.50 to 1.3420mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.005820mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.60 to 1.4720mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.005820mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok increased from 0.006 to 0.0220mPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.50 to 0.6020mPRICEz-ai/glm-5.3-flash cached_input_per_mtok increased from 0.011 to 0.0320mPRICEz-ai/glm-5.3-flash output_per_mtok decreased from 0.90 to 0.5020mPRICEz-ai/glm-5.3-flash input_per_mtok increased from 0.026 to 0.1520mPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.006 to 0.0220mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.50 to 0.6020mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.007720mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.007720mPRICEdeepseek/deepseek-v3.1-terminus input_per_mtok increased from 0.27 to 0.3020mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0038 to 0.01351mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01351mPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.42 to 0.5051mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.42 to 0.5051mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01751mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01751mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291hPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.34 to 0.501hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.00381hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 1.28 to 1.601hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.00381hPRICEdeepseek/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 0.00511hPRICEdeepseek/deepseek-v3.1-terminus input_per_mtok decreased from 0.30 to 0.271hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.00772hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.60 to 1.282hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.00772hPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok increased from 0.0021 to 0.0062hPRICE~deepseek/deepseek-flash-latest output_per_mtok decreased from 1.20 to 0.422hPRICE~deepseek/deepseek-flash-latest input_per_mtok increased from 0.015 to 0.022hPRICEdeepseek/deepseek-v4.1-flash output_per_mtok decreased from 1.20 to 0.422hPRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.30 to 0.022hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.00772h
Not yet benchmarked

Upstage is in the registry, awaiting benchmark coverage. View the live ranking →

Upstage in the registry

  • HeadquartersKR
  • API protocolsopenai chat completions
  • Catalogued endpoints0
  • Websitewww.upstage.ai

All providers · How we benchmark