European Union / documented coverage
AI APIs with documented data residency in European Union
This page answers: Which providers document processing or storage within this geography?
| Provider | Documented claim | Scope | Source |
|---|---|---|---|
| AKI.IO | Regional inference endpoint | AKI.IO states that its open-weight models are hosted on EU infrastructure and that inference runs in European data centres. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Apertus 70B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists DeepSeek Flash v4 0731 in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists GPT-OSS 120B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Gemma 4 26B A4B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Kimi K2.7-Code 1110B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Llama 3.1 8B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Llama 3.3 70B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Minimax M2.5 230B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Mistral 4 119B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Qwen 3.6 35B A3B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| AKI.IO | Regional inference endpoint | AKI.IO lists Qwen 3.8 27B in its official token-pricing catalogue for its EU-hosted model service. | Official source |
| Alibaba Cloud Model Studio | Selected models process inference within this jurisdiction | Model Studio Frankfurt EU deployment scope restricts inference to the EU; model availability remains region-specific. | Official source |
| Amazon Bedrock | Selected models process inference within this jurisdiction | AWS geographic inference profiles can keep supported model inference within the EU; model-specific destination regions vary. | Official source |
| Google Vertex AI | Selected models process inference within this jurisdiction | Google documents EU multi-region endpoints for supported Google and partner models. | Official source |
| GreenPT | Regional inference endpoint | GreenPT states that user data and content are stored and processed exclusively in the European Union, with AI model inference and compute documented in France and Finland. | Official source |
| Inceptron | Data residency documented | Inceptron states that customer content processed through its services remains exclusively within the EU or EEA. | Official source |
| Infercom | Regional inference endpoint | Infercom states that its managed inference platform is EU-hosted and that its EU-hosted models run in German infrastructure. | Official source |
| Infercom | Regional inference endpoint | Infercom lists MiniMax M2.7 in its official EU-hosted model catalogue. | Official source |
| Infercom | Regional inference endpoint | Infercom lists gpt-oss-120b in its official EU-hosted model catalogue. | Official source |
| Infercom | Regional inference endpoint | Infercom lists Gemma 4 31B in its official EU-hosted model catalogue. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS states that AI Model Hub data processing is confined within Germany and that its managed OpenAI-compatible model service is hosted in IONOS Cloud data centres. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS lists Qwen3.5-397B-A17B Neu in its official AI Model Hub token-pricing table. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS lists Mistral Nemo Instruct in its official AI Model Hub token-pricing table. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS lists Mistral Small 24B Instruct New in its official AI Model Hub token-pricing table. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS lists gpt-oss-120b in its official AI Model Hub token-pricing table. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS lists Llama 3.3 70B Instruct in its official AI Model Hub token-pricing table. | Official source |
| IONOS AI Model Hub | Regional inference endpoint | IONOS lists Qwen3-Coder-Next (80B) New in its official AI Model Hub code-model pricing table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum states that its serverless inference and GPU infrastructure use EU data centres and provide EU data residency. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists GLM-5.2 in its official serverless inference price table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists Kimi K2.7 Code in its official serverless inference price table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists MiniMax M3 in its official serverless inference price table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists DeepSeek V4 Pro in its official serverless inference price table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists DeepSeek V4 Flash in its official serverless inference price table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists Qwen3.5 9B in its official serverless inference price table. | Official source |
| Lyceum Technology | Regional inference endpoint | Lyceum lists Qwen3 Coder 30B A3B in its official serverless inference price table. | Official source |
| Mistral API | Regional inference endpoint | Mistral EU regional endpoint processes supported model inference in EU and EFTA data centers; control-plane data is separate. | Official source |
| Nebius Token Factory | Regional inference endpoint | Nebius states that public Token Factory endpoints are Global with no fixed-region guarantee; dedicated endpoints process requests in their selected deployment region. An EU locality claim therefore requires a dedicated endpoint deployed in an EU region. | Official source |
| Nebul | Regional inference endpoint | Nebul states that its OpenAI-compatible inference API uses dedicated GPU clusters and optimized inference on multi-GPU nodes across EU data centres. The documentation does not provide a model-by-model EU matrix. | Official source |
| Regolo | Regional inference endpoint | Regolo states that its managed AI API is EU-hosted and that its core models run in European data centres. | Official source |
| Regolo | Regional inference endpoint | Regolo lists apertus-70b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists brick-complexity-pro in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists brick-v1-beta in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists gemma4-31b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists glm5.2 in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists gpt-oss-120b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists gpt-oss-20b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists Llama-3.3-70B-Instruct in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists mistral-small-4-119b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists qwen3-coder-next in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists qwen3.5-122b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists qwen3.5-9b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists qwen3.6-27b in its official model library pricing table. | Official source |
| Regolo | Regional inference endpoint | Regolo lists qwen3.8-27b in its official model library pricing table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway states that Generative APIs are hosted in secure European data centres and identifies Paris as the selected pricing region. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists glm-5.2 in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists deepseek-v4-flash-0731 in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists qwen3.5-397b-a17b in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists qwen3.6-35b-a3b in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists gemma-4-26b-a4b-it in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists mistral-medium-3.5-128b in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists whisper-large-v3 in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists llama-3.3-70b-instruct in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists qwen3-235b-a22b-instruct-2507 in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists qwen3-coder-30b-a3b-instruct in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists qwen3-embedding-8b in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists pixtral-12b-2409 in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists mistral-small-3.2-24b-instruct-2506 in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists gpt-oss-120b in the Paris Generative APIs model-price table. | Official source |
| Scaleway | Regional inference endpoint | Scaleway lists bge-multilingual-gemma2 in the Paris Generative APIs model-price table. | Official source |
| TensorX | Regional inference endpoint | TensorX states that its model inference runs on EU-sovereign infrastructure with dedicated EU compute and EU data residency. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists moonshotai/kimi-k3 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists qwen/qwen3.8-2.4t-a95b on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists deepseek/deepseek-v4-pro on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists z-ai/glm-5.2 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists qwen/qwen3.8-27b on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists deepseek/deepseek-v4-flash-0731 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists minimax/minimax-m3 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists moonshotai/kimi-k2.6 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists moonshotai/kimi-k2.7-code on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists z-ai/glm-5.1 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists z-ai/glm-5 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists z-ai/glm-5-turbo on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists moonshotai/kimi-k2.5 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists z-ai/glm-5v-turbo on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists minimax/minimax-m2.5 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists qwen/qwen3.5-122b-a10b on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists deepseek/deepseek-v3.2 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists qwen/qwen3.5-9b on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists deepseek/deepseek-r1-0528 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists qwen/qwen3-235b-a22b-2507 on EU-sovereign infrastructure. | Official source |
| TensorX | Regional inference endpoint | TensorX's official model library lists qwen/qwen3-embedding-8b on EU-sovereign infrastructure. | Official source |
Results are generated from 20 sources checked Aug 27, 2026. Read the linked source before making a procurement or residency decision.