PrivateMind Docs

PrivateMind gives your organisation private AI infrastructure running frontier open-weight models. You get an OpenAI-compatible API and a full web application, backed by GPU hardware that is either pooled across tenants or dedicated to you alone. Your data never leaves your environment and is never used to train a model. Built for financial services where compliance, data sovereignty, and auditability are non-negotiable.

Using the API

OpenAI-compatible endpoints. Swap your base URL, bring your own SDK, and ship.

Using the app

Chat, file uploads, projects, cloud agents, code execution — all from your browser.

What you can do

Chat & reasoning

Open-weight models with reasoning, long context (256K), and vision. Run on shared hardware or your own GPUs.

Files & RAG

Upload PDFs, DOCX, CSV, and more. Ground responses in your own documents with source attribution.

Tool use & agents

Function calling, JSON-schema tools, cloud agents for scheduled automations, and MCP integrations.

Code execution

Sandboxed Python and Node.js environments. The model writes and runs code, then acts on the output.

Conversations API

List, read, and generate responses from past conversations programmatically with user-scoped keys.

API keys & auth

Bearer-token authentication, key lifecycle management, budgets, and rate limits.

Try it

Grab an API key from the button in the top right, then run this. If you've used the OpenAI API, you already know the shape of every endpoint.

curl -s "https://api.privatemind.com/v1/chat/completions" \
  -H "Authorization: Bearer $PMIND_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fast",
    "messages": [{"role": "user", "content": "Hello, world."}]
  }'

from openai import OpenAI
client = OpenAI(base_url="https://api.privatemind.com/v1", api_key=PMIND_KEY)
resp = client.chat.completions.create(
    model="fast",
    messages=[{"role": "user", "content": "Hello, world."}],
)
print(resp.choices[0].message.content)

import OpenAI from 'openai';
const client = new OpenAI({ baseURL: 'https://api.privatemind.com/v1', apiKey: process.env.PMIND_KEY });
const resp = await client.chat.completions.create({
  model: 'fast',
  messages: [{ role: 'user', content: 'Hello, world.' }],
});
console.log(resp.choices[0].message.content);

Pick your path

If you've used the OpenAI API, you already know how to use PrivateMind. The API is OpenAI-compatible — swap the base URL, grab an API key, and keep using the SDKs and tools you already have.

Prefer a browser? The PrivateMind app gives you chat, file uploads, code execution, and scheduled automations in one place.

What's in these docs

The sidebar covers everything. Here are the most common starting points:

Quickstart — your first API call in five minutes
Models — browse the catalogue live from your environment
Authentication — bearer token format and key management
Chat — the web application, model picker, reasoning toggle, and file uploads
Rate limits & budgets — how limits work and what happens when you hit them
OpenAI SDK — drop-in usage with Python, TypeScript, Go, LangChain, and more