Baati builds privacy-preserving AI building blocks that sit between your app and the models you use.
Keep personal data out of your LLM provider.
Baati Redact sits between your app and any OpenAI-compatible model. Names, emails and IBANs leave as placeholders and come back restored in the reply.
Your app sends
Hallo, ich bin Anna Kovács. Meine IBAN ist DE89 3704 0044 0532 0130 00 und meine Mail anna@corp.eu.
The provider sees
Hallo, ich bin [PERSON_1]. Meine IBAN ist [IBAN_1] und meine Mail [EMAIL_1].
Your user gets
Hallo Anna Kovács, ich habe Ihre IBAN DE89 3704 0044 0532 0130 00 erhalten und antworte an anna@corp.eu.
Switch with one line
Point the OpenAI SDK at Baati — no other changes.
Streaming replies restored
Placeholders come back as real values, tokens included.
6 languages
EN · DE · FR · ES · IT · NL
from openai import OpenAI
client = OpenAI(
base_url="https://api.baatilabs.com/v1",
api_key="gw_…",
default_headers={
"x-upstream-base": "https://api.openai.com",
"x-upstream-key": "sk-…",
},
)
resp = client.chat.completions.create(model="gpt-4o-mini", messages=msgs)More models in the kitchen.