The console
One call, three places to send it. The code is the same OpenAI-style request each time; only the address, the model and the key change. (Source: Mistral docs, Chat completion and Ollama docs, OpenAI compatibility and OpenRouter, Quickstart; as read on 20 November 2026.)
Mistral API: the call
curl https://api.mistral.ai/v1/chat/completions \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "ministral-3b-2512",
"messages": [{"role": "user", "content": "Say hello in five words."}]}'
Model Ministral 3 3B, model name ministral-3b-2512, is listed as Apache 2.0, released 2 December 2025, at 0.10 dollars per million tokens in and 0.10 out. (Source: Mistral docs, Ministral 3 3B and Mistral docs, Pricing; as read on 20 November 2026.)
What this call sends, and to whom
- Your brief and your API key, to Mistral AI. Mistral’s chat endpoint is
https://api.mistral.ai/v1/chat/completions; the EU one ishttps://api.eu.mistral.ai/v1/chat/completions. (Source: Mistral docs, Chat completion and Mistral docs, Regional inference; as read on 20 November 2026.) - 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 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.)
- 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.)
- 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.)
On your device: the call
ollama pull ministral-3:3b
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "ministral-3:3b",
"messages": [{"role": "user", "content": "Say hello in five words."}]}'
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.)
What this call sends, and to whom
- Your brief, to your own machine only. Ollama serves an OpenAI-style endpoint at
http://localhost:11434/v1/chat/completions. (Source: Ollama docs, OpenAI compatibility; as read on 20 November 2026.) - Ollama lists
ministral-3with the tags3b,8band14b. (Source: Ollama, ministral-3; as read on 20 November 2026.) - An estimate, not measured. Whether it fits a Pi or a tablet is still to be measured. (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.)
Any provider: the call
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "MODEL_ID_FROM_OPENROUTER_MODELS_PAGE",
"messages": [{"role": "user", "content": "Say hello in five words."}]}'
Model Any model OpenRouter lists, Mistral’s included.
What this call sends, and to whom
- Your brief and your OpenRouter key, to OpenRouter, then to the provider of the model you pick. OpenRouter’s OpenAI-style API is at
https://openrouter.ai/api/v1. (Source: OpenRouter, Quickstart; as read on 20 November 2026.) - What is kept, and for how long, is set by OpenRouter’s terms and the provider’s; this site has not read them for every provider, so it does not say.
- Pick a model name from OpenRouter’s models page and put it in place of
MODEL_ID_FROM_OPENROUTER_MODELS_PAGE.
Tokens and time, per call
Every answer from these endpoints carries a usage block with prompt, completion and total tokens. The real calls this site’s demo agent made while building the demos, from its call log:
| UTC | Model | What for | Prompt | Completion | Total |
|---|---|---|---|---|---|
| 22:55 | ministral-3b-2512 | A five-word hello, to check the answer and its usage fields | 9 | 7 | 16 |
| 23:00 | ministral-3b-2512 | The same through the OpenAI-compatible path, /openai/v1 | 9 | 6 | 15 |
| 23:03 | ministral-3b-2512 | A call from a browser page, to check it can read the answer | 6 | 5 | 11 |
| 23:05 | ministral-3b-2512 | The side-by-side demo, end to end (a short brief, at most 150 tokens out) | 38 | 150 | 188 |
Time per call was not logged for these. The side-by-side demo shows the time taken, in milliseconds, and the tokens for every call you make.
Run the same brief on Mistral beside another model All the demos
The idea of offering Mistral beside other models on every sovereign website is a proposal in Dinis Cruz’s article A European brain for a sovereign website. Nothing has been agreed with Mistral.