The models behind GDPRchat
Behind each OpenAI name is not OpenAI — it is our best current European model for that task, updated every week as benchmarks move. Or address a specific European model directly. Every model runs on EU infrastructure, under EU data-protection law.
OpenAI names → European models
Drop-in aliases. Keep your OpenAI model name; we serve the European equivalent and upgrade it automatically.
gpt-4gpt-4-turbogpt-4ogpt-4.1chatgpt-4o-latesto1o1-minio3o3-minigpt-4o-minigpt-3.5-turbocodecodexgpt-4-codegpt-4o-codecode-davinci-002The mapping is generated from our live model registry — it changes the moment we approve a better model, with no action on your side.
Direct access to our fleet
Prefer to pin a specific model? Address any of these by its id.
mistral-large-latestLong-form answers, reasoning and tool use, with strong coverage across all 24 EU languages.
mistral-medium-latestBalanced everyday answers, and it reads images (vision) reliably.
mistral-small-latestFast, low-cost utility work: short answers, titles, tagging and classification.
codestral-latestCode generation and completion across many programming languages.
mistral-medium-3.5-128bFast general answers with excellent tool-calling — our current answer and routing primary.
qwen3.5-397b-a17bVery strong at code and mathematics; large context window.
A Chinese-origin model that censors or distorts certain political and historical topics. We keep an automatic safeguard on even when you select it directly: prompts about the subjects below are quietly served by a values-safe European model instead — so you never receive censored output.
The choices behind this — right-sizing models for lower energy use, and the language-dependent political bias we guard against — are written up at frits.ai/research.