PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.298mPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.368mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 1.34 to 0.508mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.00388mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 1.28 to 1.608mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.00388mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.0077 to 0.00518mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.0077 to 0.00518mPRICEdeepseek/deepseek-v3.1-terminus input_per_mtok decreased from 0.30 to 0.278mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.013 to 0.007739mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.60 to 1.2839mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.013 to 0.007739mPRICE~deepseek/deepseek-flash-latest cached_input_per_mtok increased from 0.0021 to 0.00639mPRICE~deepseek/deepseek-flash-latest output_per_mtok decreased from 1.20 to 0.4239mPRICE~deepseek/deepseek-flash-latest input_per_mtok increased from 0.015 to 0.0239mPRICEdeepseek/deepseek-v4.1-flash output_per_mtok decreased from 1.20 to 0.4239mPRICEdeepseek/deepseek-v4.1-flash input_per_mtok decreased from 0.30 to 0.0239mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.017 to 0.007739mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.017 to 0.007739mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok increased from 0.0051 to 0.0131hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.0171hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.0171hPRICEnvidia/nemotron-3-ultra-550b-a55b input_per_mtok increased from 0.50 to 0.601hPRICEnvidia/nemotron-3-ultra-550b-a55b output_per_mtok increased from 2.20 to 2.401hPRICEnvidia/nemotron-3-ultra-550b-a55b cached_input_per_mtok increased from 0.10 to 0.121hPRICEtencent/hy3 input_per_mtok decreased from 0.13 to 0.0831hPRICEtencent/hy3 output_per_mtok decreased from 0.53 to 0.331hPRICEtencent/hy3 cached_input_per_mtok decreased from 0.033 to 0.0211hPRICEtencent/hy4-preview input_per_mtok decreased from 0.83 to 0.751hPRICEtencent/hy4-preview output_per_mtok decreased from 2.50 to 2.251hPRICEtencent/hy4-preview cached_input_per_mtok decreased from 0.042 to 0.0381hPRICEz-ai/glm-5.3-flash input_per_mtok decreased from 0.15 to 0.0261hPRICEz-ai/glm-5.3-flash output_per_mtok increased from 0.50 to 0.901hPRICEz-ai/glm-5.3-flash cached_input_per_mtok decreased from 0.03 to 0.0111hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0051 to 0.0131hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok increased from 1.28 to 1.601hPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok decreased from 0.012 to 0.00512hPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok decreased from 0.012 to 0.00512hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0086 to 0.00512hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.60 to 1.282h

AI inference providers in Germany

Live from the registry: providers headquartered in Germany, their endpoints and their place in the European inference market. All of Europe →

6 providers · 1 catalogued endpoint · 1 endpoint hosted in-country
ProviderTypeEndpointsRegistry state
AKI.IOinference host0discovered
Aleph Alphafirst party model lab0discovered
EUrouterrouter0discovered
IONOS AI Model Hubsovereign cloud1discovered
Lyceum Technologyinference host0discovered
Meliousinference host0discovered

Registry data is live and continuously discovered; benchmark coverage is measured independently from our EU vantage. Methodology →