EU-owned, EU-operated
Company and infrastructure both under EU law and EU ownership.
endpoints: 6
LLM hosting in the EU
What hosting on LLM EU means in practice, which regions the endpoint rows record, what retention each row states, and which models nothing serves yet.
What hosting means here
A request is served only by an endpoint whose row matches the policy it was sent with. The row is the whole claim: region, runtime, hosting class and the retention it records. When no row matches, the router answers 409 no_endpoint_for_policy instead of sending the request somewhere else. Residency here is a filter, never a preference — Routing and policy.
These four labels replace the bare word sovereign, which we do not use on its own. A model is called sovereign only with its class and region beside it, because ownership, operation and jurisdiction are three different facts.
Hosting classes
EU region of a non-EU parent
Data stays in an EU region, but the parent company is outside the EU and may be subject to non-EU law.
endpoints: 0
On premises at the customer
Runs in infrastructure the customer controls.
endpoints: 0
Catalogue entry, hosting not documented
No inference is offered on LLM EU. Treat residency claims as unverified.
endpoints: 0
Regions the endpoint rows record
Retention comes from the endpoint row fields zero_retention and notes, not from a policy this page holds. Zero means the prompt and completion bodies are never written to the database — Verified.
This page is documentation, not a certification. It records what each endpoint states about its region, its retention and its hosting class, and names the source. It is not a legal opinion, not a conformity assessment, and not a guarantee about any provider.
Not hosted on LLM EU yet
No model is hosted on LLM EU yet
No model is served by a first-party runtime on this deployment. The catalogue below is complete, every card states where its facts come from, and each one records the endpoint that serves it. Remove the hosting filter to see it.
| Models | Inference region | Runtime | Retention |
|---|---|---|---|
| Mistral Small 4 (119B-A6B) | dev-mock | mock | zero |
| Devstral Small 2 (24B) | dev-mock | mock | zero |
| EuroLLM-22B-Instruct (2512) | dev-mock | mock | zero |
| EuroLLM-9B-Instruct (2512) | dev-mock | mock | zero |
| EuroLLM-1.7B-Instruct | dev-mock | mock | zero |
| Whisper large-v3 | dev-mock | mock | zero |
This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.
Catalogue only — no endpoint yet
These models are documented in the catalogue but have no endpoint that can answer a request, so there is no region and no retention to report for them. Asking for one returns an error rather than routing somewhere else.
- Aya 23 8B — Cohere
- Aya Expanse 8B — Cohere
- Blip2 Flan T5 Xl — Salesforce
- Blip2 Opt 2.7B — Salesforce
- Bloom — BigScience (BLOOM)
- Bloom 1b1 — BigScience (BLOOM)
- Bloom 3B — BigScience (BLOOM)
- Bloom 560M — BigScience (BLOOM)
- Bloomz 560M — BigScience (BLOOM)
- Codestral 25.08 — Mistral AI
- Command A+ (05-2026) — Cohere
- Command R (08-2024) — Cohere
- DeepSeek Coder V2 Lite Instruct — DeepSeek
- DeepSeek OCR — DeepSeek
- DeepSeek OCR 2 — DeepSeek
- DeepSeek R1 0528 — DeepSeek
- DeepSeek R1 0528 Qwen3 8B — DeepSeek
- DeepSeek R1 Distill Llama 8B — DeepSeek
- DeepSeek R1 Distill Qwen 1.5B — DeepSeek
- DeepSeek R1 Distill Qwen 14B — DeepSeek
- DeepSeek R1 Distill Qwen 7B — DeepSeek
- DeepSeek V2 Lite — DeepSeek
- DeepSeek V3 — DeepSeek
- DeepSeek V3 0324 — DeepSeek
- DeepSeek V3.1 — DeepSeek
- DeepSeek V4 Flash — DeepSeek
- DeepSeek V4 Pro — DeepSeek
- DeepSeek V4.1 Flash — DeepSeek
- DeepSeek-R1 — DeepSeek
- DeepSeek-R1-Distill-Qwen-32B — DeepSeek
- DeepSeek-V3.2 — DeepSeek
- DeepSeek-V4-Flash (0731) — DeepSeek
- Deepseek Coder 7B Instruct V1.5 — DeepSeek
- Devstral Small 2 (24B) — Mistral AI
- Diffusiongemma 26B A4B It — Google DeepMind
- ERNIE 4.5 0.3B — Baidu
- ERNIE 4.5 21B-A3B Thinking — Baidu
- ERNIE 4.5 VL 28B-A3B — Baidu
- EmbeddingGemma 300M — Google DeepMind
- EuroLLM-1.7B-Instruct — EuroLLM (utter-project)
- EuroLLM-22B-Instruct (2512) — EuroLLM (utter-project)
- EuroLLM-9B-Instruct (2512) — EuroLLM (utter-project)
- Falcon 7B — Technology Innovation Institute (TII)
- Falcon 7B Instruct — Technology Innovation Institute (TII)
- Falcon H1 0.5B Base — Technology Innovation Institute (TII)
- Falcon H1 1.5B Deep Instruct — Technology Innovation Institute (TII)
- Falcon H1 1.5B Instruct — Technology Innovation Institute (TII)
- Falcon H1 3B Instruct — Technology Innovation Institute (TII)
- Falcon H1 7B Instruct — Technology Innovation Institute (TII)
- Falcon Mamba 7B Instruct — Technology Innovation Institute (TII)
- Falcon3 10B Instruct — Technology Innovation Institute (TII)
- Falcon3 7B Instruct — Technology Innovation Institute (TII)
- Flan T5 Base — Google DeepMind
- Flan T5 Small — Google DeepMind
- Florence 2 Base Ft — Microsoft
- Florence 2 Large Ft — Microsoft
- GLM 4.1V 9B Thinking — Z.ai (Zhipu AI)
- GLM 4.5 — Z.ai (Zhipu AI)
- GLM 4.5 Air — Z.ai (Zhipu AI)
- GLM 4.5V — Z.ai (Zhipu AI)
- GLM 4.6 — Z.ai (Zhipu AI)
- GLM 4.6V Flash — Z.ai (Zhipu AI)
- GLM 5 — Z.ai (Zhipu AI)
- GLM 5.1 — Z.ai (Zhipu AI)
- GLM 5.2 — Z.ai (Zhipu AI)
- GLM 5.3 Flash — Z.ai (Zhipu AI)
- GLM Z1 32B 0414 — Z.ai (Zhipu AI)
- GLM-4 9B Chat 1M — Z.ai (Zhipu AI)
- GLM-4.7-Flash — Z.ai (Zhipu AI)
- GLM-5.3 — Z.ai (Zhipu AI)
- GLM-OCR — Z.ai (Zhipu AI)
- Gemma 2 2B It — Google DeepMind
- Gemma 2 9B It — Google DeepMind
- Gemma 3 12B It — Google DeepMind
- Gemma 3 1B It — Google DeepMind
- Gemma 3 27B It — Google DeepMind
- Gemma 3 4B It — Google DeepMind
- Gemma 4 12B It — Google DeepMind
- Gemma 4 26B A4B IT — Google DeepMind
- Gemma 4 31B — Google DeepMind
- Gemma 4 31B IT — Google DeepMind
- Gemma 4 E2B It — Google DeepMind
- Gemma 4 E4B IT — Google DeepMind
- Glm 4 9B Chat — Z.ai (Zhipu AI)
- Gpt Neo 1.3B — EleutherAI
- Gpt Neo 125M — EleutherAI
- Gpt Neo 2.7B — EleutherAI
- Gpt Neox 20B — EleutherAI
- Gpt Oss Safeguard 20B — OpenAI
- Granite 3.0 1B A400M Instruct — IBM
- Granite 3.1 8B Instruct — IBM
- Granite 3.2 8B Instruct — IBM
- Granite 3.3 2B Instruct — IBM
- Granite 3.3 8B Instruct — IBM
- Granite 4.0 3B Vision — IBM
- Granite 4.0 H Tiny — IBM
- Granite 4.0 Micro — IBM
- Granite 4.1 30B — IBM
- Granite 4.1 3B — IBM
- Granite 4.1 8B — IBM
- Granite 4.2 30B — IBM
- Granite 4.2 3B — IBM
- Granite 4.2 8B — IBM
- Granite Docling 258M — IBM
- Granite Guardian 4.1 8B — IBM
- Granite Vision 4.1 4B — IBM
- Hunyuan A13B Instruct — Tencent
- Hunyuan Hy3 — Tencent
- Hunyuan Hy4 Preview — Tencent
- Hunyuan MT2 1.8B — Tencent
- Hunyuan MT2 7B — Tencent
- HunyuanOCR — Tencent
- Instructblip Flan T5 Xl — Salesforce
- Instructblip Vicuna 7B — Salesforce
- Intern-S1 — Shanghai AI Laboratory
- Intern-S1 Mini — Shanghai AI Laboratory
- InternLM 2 20B Chat — Shanghai AI Laboratory
- InternLM 2 7B Chat — Shanghai AI Laboratory
- InternLM 2.5 7B Chat — Shanghai AI Laboratory
- InternLM 3 8B Instruct — Shanghai AI Laboratory
- Kimi K2 Instruct — Moonshot AI
- Kimi K2 Instruct 0905 — Moonshot AI
- Kimi K2 Thinking — Moonshot AI
- Kimi K2.5 — Moonshot AI
- Kimi K2.6 — Moonshot AI
- Kimi K2.7 Code — Moonshot AI
- Kimi K3 — Moonshot AI
- Kimi Linear 48B A3B Instruct — Moonshot AI
- Kimi VL A3B Instruct — Moonshot AI
- LLMEU V2 (announced) — LLM EU
- Llama 2 13B Chat Hf — Meta
- Llama 2 7B Chat Hf — Meta
- Llama 3.1 405B — Meta
- Llama 3.1 70B Instruct — Meta
- Llama 3.1 8B Instruct — Meta
- Llama 3.2 11B Vision Instruct — Meta
- Llama 3.2 1B Instruct — Meta
- Llama 3.2 3B Instruct — Meta
- Llama 3.3 70B Instruct — Meta
- Llama 4 Maverick 17B-128E Instruct — Meta
- Llama 4 Scout 17B-16E Instruct — Meta
- Llama Embed Nemotron 8B — NVIDIA
- Llama Guard 3 8B — Meta
- Llama Guard 4 12B — Meta
- Llama Nemotron Embed 1B V2 — NVIDIA
- Llama Nemotron Rerank 1B v2 — NVIDIA
- Llama Nemotron Rerank Vl 1B V2 — NVIDIA
- Magistral Small 1.2 — Mistral AI
- Medgemma 4B It — Google DeepMind
- Meta Llama 3 70B Instruct — Meta
- Meta Llama 3 8B Instruct — Meta
- MiniMax M1 40k — MiniMax
- MiniMax M2 — MiniMax
- MiniMax M2.1 — MiniMax
- MiniMax M2.5 — MiniMax
- MiniMax M3 — MiniMax
- MiniMax Text 01 — MiniMax
- Ministral 3 8B — Mistral AI
- Mistral 7B Instruct v0.3 — Mistral AI
- Mistral Large 3 (675B) — Mistral AI
- Mistral NeMo 12B Instruct — Mistral AI
- Mistral Small 4 (119B-A6B) — Mistral AI
- Molmo 7B D 0924 — Allen Institute for AI (Ai2)
- Molmo2 4B — Allen Institute for AI (Ai2)
- Molmo2 8B — Allen Institute for AI (Ai2)
- Moonlight 16B A3B Instruct — Moonshot AI
- NVIDIA Canary 1B v2 — NVIDIA
- NVIDIA Canary Qwen 2.5B — NVIDIA
- NVIDIA Cosmos 3 Edge — NVIDIA
- NVIDIA Cosmos Reason2 2B — NVIDIA
- NVIDIA NV-Embed-v2 — NVIDIA
- NVIDIA Nemotron 3 Embed 1B — NVIDIA
- NVIDIA Nemotron 3 Embed 8B — NVIDIA
- NVIDIA Nemotron 3 Nano 30B-A3B — NVIDIA
- NVIDIA Nemotron 3 Nano 4B — NVIDIA
- NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning — NVIDIA
- NVIDIA Nemotron 3 Super 120B-A12B — NVIDIA
- NVIDIA Nemotron 3 Ultra 550B-A55B — NVIDIA
- NVIDIA Nemotron 3.5 Lightning 30B-A3B — NVIDIA
- NVIDIA Parakeet TDT 0.6B v3 — NVIDIA
- North Micro Vision Instruct — Cohere
- North Mini Code 1.0 — Cohere
- OLMo 1B Hf — Allen Institute for AI (Ai2)
- OLMo 2 0325 32B Instruct — Allen Institute for AI (Ai2)
- OLMo 2 0425 1B Instruct — Allen Institute for AI (Ai2)
- OLMo 2 1124 7B Instruct — Allen Institute for AI (Ai2)
- OLMoE 1B 7B 0125 Instruct — Allen Institute for AI (Ai2)
- OlmOCR 2 7B 1025 — Allen Institute for AI (Ai2)
- OlmOCR 7B 0225 Preview — Allen Institute for AI (Ai2)
- Olmo 3 1125 32B — Allen Institute for AI (Ai2)
- Olmo 3 32B Think SFT — Allen Institute for AI (Ai2)
- Olmo 3 7B Instruct — Allen Institute for AI (Ai2)
- Olmo 3 7B Think — Allen Institute for AI (Ai2)
- OpenEuroLLM final models (planned) — OpenEuroLLM
- OpenEuroLLM initial model release (planned) — OpenEuroLLM
- Pharia-1-Embedding-4608-control — Aleph Alpha
- Pharia-1-LLM-7B-control-aligned — Aleph Alpha
- Phi 1 5 — Microsoft
- Phi 2 — Microsoft
- Phi 3 Mini 128K Instruct — Microsoft
- Phi 3 Mini 4K Instruct — Microsoft
- Phi 3 Vision 128K Instruct — Microsoft
- Phi 3.5 Mini Instruct — Microsoft
- Phi 3.5 MoE Instruct — Microsoft
- Phi 3.5 Vision Instruct — Microsoft
- Phi 4 Mini Instruct — Microsoft
- Phi 4 Mini Reasoning — Microsoft
- Phi 4 Reasoning — Microsoft
- Phi Mini MoE Instruct — Microsoft
- Phi Tiny MoE Instruct — Microsoft
- Phi-4 — Microsoft
- Phi-4-multimodal-instruct — Microsoft
- Pixtral 12B — Mistral AI
- Pythia 1.4B — EleutherAI
- Pythia 12B — EleutherAI
- Pythia 160M — EleutherAI
- Pythia 1B — EleutherAI
- Pythia 2.8B — EleutherAI
- Pythia 410M — EleutherAI
- Pythia 6.9B — EleutherAI
- Pythia 70M — EleutherAI
- Qianfan OCR — Baidu
- Qwen2.5 0.5B Instruct — Alibaba Qwen
- Qwen2.5 1.5B Instruct — Alibaba Qwen
- Qwen2.5 3B Instruct — Alibaba Qwen
- Qwen2.5 72B Instruct — Alibaba Qwen
- Qwen2.5 7B Instruct — Alibaba Qwen
- Qwen2.5 Coder 14B Instruct — Alibaba Qwen
- Qwen2.5 Coder 32B Instruct — Alibaba Qwen
- Qwen2.5 Coder 7B Instruct — Alibaba Qwen
- Qwen2.5 VL 7B Instruct — Alibaba Qwen
- Qwen3 0.6B — Alibaba Qwen
- Qwen3 1.7B — Alibaba Qwen
- Qwen3 14B — Alibaba Qwen
- Qwen3 30B A3B Instruct 2507 — Alibaba Qwen
- Qwen3 32B — Alibaba Qwen
- Qwen3 4B — Alibaba Qwen
- Qwen3 4B Instruct 2507 — Alibaba Qwen
- Qwen3 Coder 480B A35B Instruct — Alibaba Qwen
- Qwen3 Coder Next — Alibaba Qwen
- Qwen3 Embedding 0.6B — Alibaba Qwen
- Qwen3 Embedding 4B — Alibaba Qwen
- Qwen3 Embedding 8B — Alibaba Qwen
- Qwen3 Next 80B A3B Instruct — Alibaba Qwen
- Qwen3 Next 80B A3B Thinking — Alibaba Qwen
- Qwen3 Reranker 0.6B — Alibaba Qwen
- Qwen3 Reranker 4B — Alibaba Qwen
- Qwen3 Reranker 8B — Alibaba Qwen
- Qwen3 TTS 12Hz 1.7B — Alibaba Qwen
- Qwen3 VL 4B Instruct — Alibaba Qwen
- Qwen3 VL Embedding 2B — Alibaba Qwen
- Qwen3 VL Embedding 8B — Alibaba Qwen
- Qwen3 VL Reranker 2B — Alibaba Qwen
- Qwen3 VL Reranker 8B — Alibaba Qwen
- Qwen3-8B — Alibaba Qwen
- Qwen3-Coder-30B-A3B-Instruct — Alibaba Qwen
- Qwen3-VL-8B-Instruct — Alibaba Qwen
- Qwen3.5 2B — Alibaba Qwen
- Qwen3.5 4B — Alibaba Qwen
- Qwen3.5 9B — Alibaba Qwen
- Qwen3.6 35B A3B — Alibaba Qwen
- Qwen3.8-27B — Alibaba Qwen
- Stablelm 2 1 6B — Stability AI
- Stablelm 3B 4e1t — Stability AI
- Stablelm Zephyr 3B — Stability AI
- Teuken 7B Instruct v0.6 — OpenGPT-X (Teuken)
- Unlimited OCR — Baidu
- Voxtral Small 24B — Mistral AI
- WeVisDoc 2B — Tencent
- Whisper Base — OpenAI
- Whisper Large — OpenAI
- Whisper Large V2 — OpenAI
- Whisper Medium — OpenAI
- Whisper Small — OpenAI
- Whisper Tiny — OpenAI
- Whisper large-v3 — OpenAI
- Whisper large-v3-turbo — OpenAI
- Wildguard — Allen Institute for AI (Ai2)
- Yi 1.5 34B Chat — 01.AI
- Yi 1.5 6B Chat — 01.AI
- Yi 1.5 9B Chat — 01.AI
- Yi 34B — 01.AI
- Yi 6B — 01.AI
- Yi 9B 200K — 01.AI
- Yi-Coder 9B — 01.AI
- Yi-Coder 9B Chat — 01.AI
- Youtu LLM 2B — Tencent
- gpt-oss-120b — OpenAI
- gpt-oss-20b — OpenAI
- gte-multilingual-reranker-base — Alibaba Qwen
- inclusionAI: Ling 3.0 Flash Sante (free) — OpenRouter
- multilingual-e5-large — Microsoft
See also: Hosting · Data residency for LLM APIs · Residency and regions · Models · Pricing · Platform status