Sovereign Website
Mistral, a European brain

An independent Sovereign Website demonstration. Not affiliated with or endorsed by Mistral AI.

The map

Where your words go

When a sovereign website asks a model to write, your brief has to go somewhere. There are three places it can go. This drawing uses only what the providers publish, as read on 20 November 2026.

Where the data goes: three paths from your browser From your browser, path 1 stays on your own device with a local model. Path 2 goes to Mistral's API; data is hosted in the EEA by default, and its EU endpoint processes in the EU. Path 3 goes through your own key to OpenRouter and on to the provider you choose. Your home EU endpoint Your browseryou write the brief 1. Your devicelocal model 2. Mistral APIyour key, Mistral runs it 3. Any provideryour key, via OpenRouter brief + key brief + key brief Where the data goes: three paths from your browser From your browser, path 1 stays on your own device with a local model. Path 2 goes to Mistral's API; data is hosted in the EEA by default, and its EU endpoint processes in the EU. Path 3 goes through your own key to OpenRouter and on to the provider you choose. Your browseryou write the brief 1. Your devicelocal model 2. Mistral APIEU endpoint 3. Any provideryour key, via OpenRouter
Three paths, one interface: the same OpenAI-style call, with a different address. (Source: Mistral docs, Chat completion and Ollama docs, OpenAI compatibility and OpenRouter, Quickstart; as read on 20 November 2026.)

Pick a path

1 On your device

What is sent
Your brief, to a model on your own machine. After the model is downloaded, nothing needs to leave it.
To whom
No one else. For example Ministral 3 run by Ollama. Ollama serves an OpenAI-style endpoint at http://localhost:11434/v1/chat/completions. (Source: Ollama docs, OpenAI compatibility; as read on 20 November 2026.)
What is kept
Whatever you keep, on your own disk.
The model
Ministral 3 was announced on 2 December 2025 in 3B, 8B and 14B sizes, for edge and local use, each with image understanding, under Apache 2.0. (Source: Mistral AI, Mistral 3; as read on 20 November 2026.)
Will it fit
An estimate, not measured. the 3B and 8B, compressed to about 2 to 5GB, should run on a 16GB Raspberry Pi 5, the 8B slowly; on a tablet, the 3B is the realistic one. (Source: A European brain for a sovereign website (Dinis Cruz, SGit Newsroom); as read on 20 November 2026.) Mistral’s official compressed (Q4_K_M) files are 2.15 GB for the 3B and 5.20 GB for the 8B, plus about 0.85 GB for vision. Those are download sizes, not memory use or speed. (Source: Hugging Face, Ministral-3-3B-Instruct-2512-GGUF and Hugging Face, Ministral-3-8B-Instruct-2512-GGUF; as read on 20 November 2026.)

Open the on-device demo

2 To Mistral, in the EU

What is sent
Your brief and your own API key, to Mistral’s API: for processing in the EU, to its EU endpoint.
To whom
Mistral AI was founded in April 2023, and describes itself as “a European leader” in AI. (Source: Mistral AI, About; as read on 20 November 2026.)
Where
By default, data is hosted in the EEA. (Source: Mistral help centre, Where do you store my data; as read on 20 November 2026.) Hosting is not processing: Mistral does not commit to an inference location on the global endpoint, api.mistral.ai. Processing in the EU needs the EU endpoint, api.eu.mistral.ai, billed at 1.1 times list price, without Agents, Batch or the Files API, and serving only the models hosted there. (Source: Mistral docs, Regional inference; as read on 20 November 2026.) Mistral’s regional endpoints were announced as generally available on 11 August 2026. (Source: Mistral AI, Regional inference announcement; as read on 20 November 2026.) Some features may move data temporarily outside the EU to listed subprocessors; Enterprise customers can switch some of these off. (Source: Mistral help centre, Where do you store my data; as read on 20 November 2026.)
What is kept, how long
API inputs and outputs are kept for 30 rolling days to monitor abuse, unless zero data retention is on; Agents API data is kept until the account ends. Zero data retention is only for pay-as-you-go, only for stateless calls, must be requested and may be refused, and does not cover Labs or Public Preview models. (Source: Mistral AI, Privacy policy and Mistral help centre, Zero data retention and Mistral docs, Zero data retention; as read on 20 November 2026.)
Training
Mistral’s inference page says “Data sent through our API isn’t used for model training”, but its help centre says that in Free mode it may use API inputs and outputs for training unless you opt out (a toggle in the Admin panel, under Privacy), and that Labs and Public Preview models may be used for training whatever the plan. (Source: Mistral AI, Cloud inference and Mistral help centre, Do you use my data to train and Mistral help centre, Opting out of training; as read on 20 November 2026.)

Run it side by side

3 To any provider, with your key

What is sent
Your brief and your own key, to OpenRouter, which passes the brief to the provider of the model you pick.
To whom
OpenRouter, then that provider. OpenRouter’s OpenAI-style API is at https://openrouter.ai/api/v1. (Source: OpenRouter, Quickstart; as read on 20 November 2026.)
What is kept, how long
Set by OpenRouter’s terms and the provider’s. This site has not read them for every provider, so it does not say.
Why it matters
Leaving is changing an address, not rebuilding the site.

Your key, and where it goes

Before you pick

Ministral 3, Mistral Small 4 and Voxtral Small are labelled Apache 2.0. Mistral Large 4 is under a modified MIT licence: its announcement says a company offering it as a model-as-a-service needs a separate commercial licence, while Mistral’s help centre describes the condition as a monthly revenue threshold of 20 million dollars. The pages disagree; read the licence file itself before relying on either. (Source: Mistral docs, Ministral 3 8B and Mistral AI, Mistral Large 4 and Mistral help centre, Licences of the open models; as read on 20 November 2026.)

The idea of a Mistral default on every sovereign website is a proposal from Dinis Cruz’s article A European brain for a sovereign website. Nothing has been agreed with Mistral.