---
last_updated: 2026-09-28
source_url: https://opper.ai/models/eu/llama
title: "Llama with EU Data Residency: Models Hosted in the EU | Opper AI"
description: "3 of the 13 Llama models on Opper run on EU routes, on Regolo, GreenPT, Scaleway, evroc and Greenference in Italy, France, Sweden and the EU multi-region. Each route shows where it runs, what the provider keeps and what it costs."
---

# Llama models hosted in the EU

> Where each Llama model runs in the EU, what the provider keeps and what it costs, route by route.

Opper is certified against ISO/IEC 27001:2022; the controls, policies and sub-processors are on https://trust.opper.ai.

3 of 13 models · 5 routes · 5 providers · 3 countries

[Run Llama models on Opper](https://opper.ai/meta)

## Every EU route for Llama

One row per model and route, with each model's best route first. Token prices are per million tokens.

| Model | Model id | Runs on | Location | Zero data retention | Training | Context | Input $/1M | Output $/1M |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Llama 3.3 70B](https://opper.ai/meta/llama-3-3-70b-instruct) | `regolo/llama-3.3-70b-instruct` | [Regolo](https://opper.ai/provider/regolo) | Italy | Yes | No | 128K | $0.68 | $3.07 |
| [Llama 3.3 70B](https://opper.ai/meta/llama-3-3-70b-instruct) | `greenpt/llama-3.3-70b-instruct` | [GreenPT](https://opper.ai/provider/greenpt) | EU | Yes | No | 131K | $1.25 | $1.25 |
| [Llama 3.3 70B](https://opper.ai/meta/llama-3-3-70b-instruct) | `scaleway/llama-3.3-70b-instruct` | [Scaleway](https://opper.ai/provider/scaleway) | France | Abuse monitoring | No | 131K | $1.02 | $1.02 |
| [Llama 3.3 70B Instruct](https://opper.ai/meta/llama-3-3-70b-instruct-fp8) | `evroc/llama-3.3-70b-instruct` | [evroc](https://opper.ai/provider/evroc) | Sweden | Yes | No | 128K | $1.14 | $1.14 |
| [Llama 3.1 8B Instruct](https://opper.ai/meta/llama-3-1-8b-instruct) | `greenference/llama-3.1-8b` | [Greenference](https://opper.ai/provider/greenference) | EU multi-region | Yes | No | 16K | $0.01 | $0.02 |

## Llama models not in the EU yet

These Llama models run on Opper outside the EU for now, in the region shown. This page updates within the hour when one gains an EU route.

- [Llama 3.1 70B Instruct](https://opper.ai/meta/llama-3-1-70b-instruct) (US)
- [Llama 3.1 70B Instruct Turbo](https://opper.ai/meta/llama-3-1-70b-instruct-turbo) (US)
- [Llama 3.1 8B Instant](https://opper.ai/meta/llama-3-1-8b-instant) (US)
- [Llama 3.1 8B Instruct Turbo](https://opper.ai/meta/llama-3-1-8b-instruct-turbo) (US)
- [Llama 3.2 11B Vision Instruct](https://opper.ai/meta/llama-3-2-11b-vision-instruct) (US)
- [Llama 3.3 70B Instruct Turbo](https://opper.ai/meta/llama-3-3-70b-instruct-turbo) (US)
- [Llama 4 Maverick 17B 128E Instruct](https://opper.ai/meta/llama-4-maverick-17b-128e-instruct) (Australia)
- [Llama 4 Maverick 17B 128E Instruct FP8](https://opper.ai/meta/llama-4-maverick-17b-128e-instruct-fp8) (US)
- [Llama 4 Scout 17B 16E Instruct](https://opper.ai/meta/llama-4-scout-17b-16e-instruct) (US)
- [Llama Guard 4 12B](https://opper.ai/meta/llama-guard-4-12b) (US)

## Call Llama only in the EU

Every route has its own model id. Call that id on any plan and the request is served on that route, in that location. The examples below call Llama 3.3 70B on Regolo in Italy.

### Set it up with your agent

Copy this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper and call this route.

```text
Use curl to download, read and follow: https://skills.opper.ai Call Llama 3.3 70B on the EU route regolo/llama-3.3-70b-instruct
```

### Or call it directly

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "regolo/llama-3.3-70b-instruct",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

### Lock it in with a rule

A model access rule with Inference location: EU, set for your organization or a project, means no LLM or embedding call can reach a route outside the EU, even by mistake. Rules are part of the Control Plane. [How model access rules work](https://docs.opper.ai/control-plane/rules/model-access)

## Who you contract with

- Company: Opper Technology AB, Sweden, reg. no. 559446-3720
- Certification: [ISO/IEC 27001:2022](https://trust.opper.ai)
- Processor: Opper, for every model. [Sub-processor list](https://opper.ai/sub-processors)
- DPA: One DPA covers the whole catalogue. [Read the DPA](https://opper.ai/data-processing-agreement)

## Other model families in the EU

- [Claude](https://opper.ai/models/eu/claude): 11 models
- [OpenAI](https://opper.ai/models/eu/openai): 25 models
- [Gemini](https://opper.ai/models/eu/gemini): 11 models
- [Mistral](https://opper.ai/models/eu/mistral): 28 models
- [DeepSeek](https://opper.ai/models/eu/deepseek): 7 models
- [Qwen](https://opper.ai/models/eu/qwen): 19 models
- [GLM](https://opper.ai/models/eu/glm): 10 models
- [Kimi](https://opper.ai/models/eu/kimi): 4 models
- [Grok](https://opper.ai/models/eu/grok): 4 models

## Frequently asked questions

### Is Llama available in the EU?

Yes. 3 of the 13 Llama models on Opper run on EU routes, on Regolo, GreenPT, Scaleway, evroc and Greenference in Italy, France, Sweden and the EU multi-region. Call the route's model id and the request is served in the EU.

### Which Llama models run in the EU?

Llama 3.3 70B, Llama 3.3 70B Instruct and Llama 3.1 8B Instruct. Not in the EU yet: Llama 3.1 70B Instruct, Llama 3.1 70B Instruct Turbo, Llama 3.1 8B Instant, Llama 3.1 8B Instruct Turbo, Llama 3.2 11B Vision Instruct, Llama 3.3 70B Instruct Turbo, Llama 4 Maverick 17B 128E Instruct, Llama 4 Maverick 17B 128E Instruct FP8, Llama 4 Scout 17B 16E Instruct and Llama Guard 4 12B.

### Is Llama GDPR (DSGVO) compliant in the EU?

Running Llama on an EU route keeps processing in the EU, which settles where your data goes. The rest depends on your own processing and the service's terms. On Opper, one Data Processing Agreement covers Llama and every other model, Opper is your single sub-processor, and each route lists what the provider keeps and whether it trains on your data. Opper is certified against ISO/IEC 27001:2022; the controls, policies and sub-processors are on https://trust.opper.ai. [Read the DPA](https://opper.ai/data-processing-agreement)

### Does Llama cost more in the EU?

Sometimes. Comparing input prices, of the 2 Llama models that also run elsewhere, 1 costs less and 1 costs more on their cheapest EU route. Other hosts in Europe set their own prices, so for open-weight models the difference depends on the host. Every route's own price is in the table on this page.

### How do I make sure Llama calls never leave the EU?

On any plan, call an EU route's model id and the request is served there. To lock it in, set a model access rule with Inference location: EU for your organization or a project, and no LLM or embedding call to Llama can reach a route outside the EU, even by mistake. Rules are part of the Control Plane. [Model access rules](https://docs.opper.ai/control-plane/rules/model-access)

## Read this list from an agent

The same routes as JSON: https://opper.ai/models/eu.json. The whole catalogue is public JSON at https://api.opper.ai/v3/models, and coding agents that use MCP can search it with list_models at https://api.opper.ai/mcp.