PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.803mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.003mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.00 to 0.993mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.00773mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.00773mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.00773mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.60 to 1.283mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0011 to 0.00773mPRICEdeepseek/deepseek-v4.1-flash input_per_mtok increased from 0.015 to 0.3034mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.68 to 1.2034mPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok increased from 0.0021 to 0.00634mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.0021 to 0.002134mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.01334mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.6034mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0077 to 0.0171hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0077 to 0.0171hPRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.02 to 0.0151hPRICEdeepseek/deepseek-v4.1-flash output_per_mtok increased from 0.60 to 0.681hPRICEdeepseek/deepseek-v4.1-flash cached_input_per_mtok decreased from 0.02 to 0.00211hPRICE~deepseek/deepseek-flash-latest input_per_mtok decreased from 0.02 to 0.0151hPRICE~deepseek/deepseek-flash-latest output_per_mtok increased from 0.60 to 0.681hPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok decreased from 0.02 to 0.00211hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.00381hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.041hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.00111hPRICEdeepseek/deepseek-v3.1-terminus input_per_mtok decreased from 0.30 to 0.272hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00772hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00772hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.012 to 0.00772hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.012 to 0.00772hNEW MODELnvidia/switchyard appeared in the catalogue2hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.0122hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.0122hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.0122hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 0.60 to 1.282hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0011 to 0.0122hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.0173hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.0173hPRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok decreased from 0.60 to 0.503hPRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok decreased from 2.40 to 2.203h

MiniMax M3 on Cortecs

#2 of 3 providers for MiniMax M3 · #5 of 11 models on Cortecs · EU
Compare with other providers
Score93.0Rel.100.0%Tools100.0%JSON100.0%TTFT517 msP955962 msTok/s90Price$0.31 / $1.23Ctx1M217 results · last 682m ago

MiniMax M3 on other providers

ProviderScoreTTFTTok/s$ Out
Together93.8542 ms132$1.20
CortecsTHIS PAGE93.0517 ms90$1.23
OpenRouter88.0929 ms75$1.20

Other models on Cortecs

ModelScoreTTFT$ Out
GPT-OSS 20B97.5175 ms$0.17
DeepSeek V4 Flash94.4411 ms$0.18
GPT-OSS 120B92.8240 ms$0.46
Llama 3.3 70B87.7441 ms$0.75
MiniMax M3THIS PAGE84.4517 ms$1.23
Qwen3-235B82.2937 ms$0.47
GLM-5.281.4425 ms$3.33
Mistral Large 381.2413 ms$1.89
Mistral Medium 3.579.9261 ms$8.07
DeepSeek V4 Pro79.5480 ms$3.50
Kimi K373.7624 ms$15.43

1 more model declared in Cortecs's catalogue — not yet measured from the canonical vantage.