The European AI inference provider directory

Every hosting partner on the Opper gateway, with the per-route privacy and residency detail most directories skip: zero data retention, training posture, GDPR DPA, and EU or US hosting. Filter to the providers that match your requirements.

Looking for the models themselves? Browse the full catalogue →

29 providers14 EU-resident5 with ZDR by default653 models →

All hosting providers

Google CloudVertex AI — Gemini, Claude on Vertex, and Llama under one Google contract.
3 routes50 models
EU + USGDPR DPA
NebiusGPU cloud and managed inference — strong on EU residency for open-weight models.
2 routes32 models
EU + USGDPR DPA
AzureMicrosoft Foundry — frontier OpenAI and Anthropic models on a single Azure contract.
3 routes29 models
EU, MultiGDPR DPA
MistralMistral's first-party API — Paris-based, EU-hosted, GDPR-native.
1 route27 models
EUGDPR DPA
AWS BedrockAmazon's managed inference platform — the broadest hyperscaler catalogue, EU + US.
3 routes24 models
EU + USZDR by defaultGDPR DPA
xAIxAI's first-party API — direct route to the Grok family across EU and US.
2 routes20 models
EU + USGDPR DPA
BergetSwedish AI cloud — EU-only, full GDPR posture by default.
1 route16 models
EUZDR by defaultGDPR DPA
GeoddProduction AI inference infrastructure across US and European routes.
2 routes16 models
EU/EEA + USZDR by defaultGDPR DPA
Alibaba CloudModel Studio — Qwen lineage hosted in Frankfurt (eu-central-1).
1 route15 models
EUGDPR DPA
EvrocEuropean AI cloud — EU residency, open-weight focus.
1 route13 models
EUZDR by defaultGDPR DPA
InfercomEU-based open-weight inference.
3 routes7 models
EU + USZDR by defaultGDPR DPA
InceptronEU-based inference for open-weight models.
1 route4 models
EUGDPR DPA
DoclingIBM's document-understanding API.
1 route2 models
EUGDPR DPA
OpperModels that Opper hosts directly — small specialised models we ship as part of the gateway.
1 route1 model
EU
DeepInfraLarge open-weight catalogue at scale — US-hosted.
1 route124 models
US
NovitaBroad open-weight catalogue at competitive prices.
1 route119 models
USGDPR DPA
OpenAIOpenAI's first-party API — direct route to GPT and o-series, US-hosted.
1 route58 models
USGDPR DPA
GeminiGoogle's direct AI Studio API — fastest access to new Gemini features.
1 route34 models
USGDPR DPA
FireworksFast, cost-efficient hosting for open-weight models.
1 route15 models
USGDPR DPA
GroqLPU-based inference — sub-100ms first-token latencies on open-weight models.
1 route11 models
USGDPR DPA
AnthropicAnthropic's first-party API — direct route to Claude, US-hosted.
1 route8 models
USGDPR DPA
MorphSpeed-optimised inference for coding agents — US-hosted.
1 route7 models
USGDPR DPA
PrunaEuropean image and video model lab — compression-optimised inference.
1 route5 models
USGDPR DPA
CerebrasWafer-scale chip inference — among the fastest tokens-per-second in the industry.
1 route4 models
USGDPR DPA
ElevenLabsProduction-grade voice, speech, and conversational-AI models.
1 route4 models
USGDPR DPA
PerplexitySonar — language models with live web search built in.
1 route4 models
USGDPR DPA
ArceeArcee's first-party API — direct route to the Trinity model family.
1 route3 models
USGDPR DPA
MiniMaxMiniMax's first-party API — direct route to the MiniMax M-series.
1 route1 model
Multi
NVIDIANemotron and realtime audio models on NVIDIA infrastructure.
1 route0 models
USGDPR DPA

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation