PERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%27mPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%27mPERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%27mPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%27mPERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%27mPERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%27mPERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%27mPERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%27mPERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%27mPERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%27mPERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%27mPERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%27mPERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%27mPERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%27mPERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%27mPERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%27mPERFORMANCEGLM-4.7 via OpenRouter: TTFT ↓ 78%27mPERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 24%27mPERFORMANCEKimi K3 → Together AI: TTFT ↓ 34%27mPERFORMANCEDeepSeek V4 Flash via OpenRouter: throughput ↓ 17%27mPERFORMANCELlama 3.3 70B via Cortecs: TTFT ↓ 51%27mPERFORMANCEQwen3 235B via OpenRouter: throughput ↑ 37%27mPERFORMANCEQwen3 235B via OpenRouter: TTFT ↓ 29%27mPERFORMANCEDeepSeek V4 Flash → Together AI: throughput ↑ 19%27mPERFORMANCEGLM-5.3 via OpenRouter: throughput ↓ 17%27mPERFORMANCEGPT-OSS 20B via Cortecs: throughput ↑ 28%27mPERFORMANCELlama 3.3 70B → Together AI: TTFT ↓ 33%27mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.2927mPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.3627mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.7527mPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.001127mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.0427mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.003827mPRICEz-ai/glm-5.1 cached_input_per_mtok increased from 0.18 to 0.2627mPRICEz-ai/glm-5.1 output_per_mtok increased from 3.03 to 4.4027mPRICEz-ai/glm-5.1 input_per_mtok increased from 0.96 to 1.4027mPRICEtencent/hy4-preview cached_input_per_mtok increased from 0.038 to 0.04227mPRICEtencent/hy4-preview input_per_mtok increased from 0.75 to 0.8327mPRICEtencent/hy3 cached_input_per_mtok increased from 0.021 to 0.03327mPRICEtencent/hy3 output_per_mtok increased from 0.33 to 0.5327m

European inference providers

Independent benchmarks for European and Europe-hosted inference — performance, pricing and data residency.

What do you need?

European provider ranking

#1 OverallMistral93.2FastestMistral4.45 sBest valueCortecsEurope #1Mistral93.2Best toolsMistral100.0%Best structuredScaleway100.0%
#ProviderΔ30d
01MistralBEST OVERALLEU RESIDENT● MEASUREDFR · Serverless · 2 models · 1 region100.0%100.0%91.7%30710094.4s109P33—
02ScalewayEU RESIDENTEU OWNED● MEASUREDFR · Serverless · 6 models · 1 region100.0%100.0%100.0%17212344.7s93P67↑ 4.8
03CortecsBEST VALUEEU RESIDENT● MEASUREDAT · Routed · 11 models · 1 region99.9%99.6%98.3%42512635.0s125P100↑ 5.0
3 of 18 providers ranked · · Methodology →
01Mistral93.2
Best overallFR · Serverless · 2 models · 1 region
TTFT307 ms
Rel.100.0%
Tok/s109
$ Out$4.50
Tools100.0%
Δ30d—
View dossier
02Scaleway92.4
FR · Serverless · 6 models · 1 region
TTFT172 ms
Rel.100.0%
Tok/s93
$ Out$1.81
Tools100.0%
Δ30d+4.8
View dossier
03Cortecs92.1
Best valueAT · Routed · 11 models · 1 region
TTFT425 ms
Rel.99.9%
Tok/s125
$ Out$1.23
Tools99.6%
Δ30d+5.0
View dossier
3 of 18 providers ranked · · Methodology →
European inference infrastructure3424FalkensteinZaragoza2
Layer
Infrastructure map

Registry-backed provider locations, the Falkenstein measurement runner and its benchmark routes. Hover a node for endpoint details; switch layers for sovereignty and residency.

Providers by country

Models available in Europe

ModelEU providersBest providerFastest endpointLowest price
GLM-5.30———
DeepSeek V4 Pro2Cortecs 79.5Cortecs 480 msCortecs $3.50
DeepSeek V4 Flash5Cortecs 94.4Scaleway 389 msCortecs $0.18
Claude Opus 50———
Kimi K32Cortecs 73.7Cortecs 624 msCortecs $15.43
GPT-5.6 Luna0———
GPT-5.6 Sol0———
Claude Sonnet 50———
GLM-5.26Cortecs 81.4Scaleway 282 msCortecs $3.33
MiniMax M32Cortecs 84.4Cortecs 517 msCortecs $1.23
Mistral Medium 3.53Mistral 80.9Scaleway 164 msMistral $7.50
GLM-4.71———
Mistral Large 32Mistral 82.1Mistral 389 msMistral $1.50
GPT-OSS 120B6Cortecs 92.8Scaleway 179 msCortecs $0.46
GPT-OSS 20B2Cortecs 97.5Cortecs 175 msCortecs $0.17
Qwen3-235B3Scaleway 85.9Scaleway 162 msCortecs $0.47
ALIA Salamandra 40B1———
DeepSeek-V30———
Llama 3.3 70B3Scaleway 89.9Scaleway 144 msCortecs $0.75
Gemma 4 31B0———

European provider directory

Live from registry · 23 providers
AIMLAPIEE · routerDiscovered — awaiting benchmarkAKI.IODE · inference hostDiscovered — awaiting benchmarkAleph AlphaDE · first party model labDiscovered — awaiting benchmarkCortecs#2 EuropeAT · ai gateway · EU residency12 benchmarked modelsEUrouterDE · routerDiscovered — awaiting benchmarkHelmcodeES · inference host · EU residency2 benchmarked modelsInceptronSE · inference hostDiscovered — awaiting benchmarkInfercom.aiLU · inference hostDiscovered — awaiting benchmarkInfomaniak AI ServicesCH · sovereign cloudDiscovered — awaiting benchmarkIONOS AI Model HubDE · sovereign cloud · EU residency1 benchmarked modelsLyceum TechnologyDE · inference hostDiscovered — awaiting benchmarkMeliousDE · inference hostDiscovered — awaiting benchmarkMistral AI#3 EuropeFR · first party model lab · EU residency3 benchmarked modelsNebius Token FactoryNL · inference host · EU residency9 benchmarked modelsNebulNL · sovereign cloudDiscovered — awaiting benchmarkNextBitES · inference host · EU residency2 benchmarked modelsNscaleGB · inference hostDiscovered — awaiting benchmarkOnshoreAIGB · inference hostDiscovered — awaiting benchmarkOVHcloudFR · sovereign cloud · EU residency1 benchmarked modelsRegoloIT · inference host · EU residency2 benchmarked modelsScaleway#1 EuropeFR · sovereign cloud · EU residency6 benchmarked modelsSourcefulSE · inference hostDiscovered — awaiting benchmarkTensorixIE · inference hostDiscovered — awaiting benchmark

By country

FR (3) · ES (2) · DE (6) · GB (2) · NL (2) · AT (1) · CH (1) · IT (1) · SE (2) · EE (1) · IE (1) · LU (1)