From zero to first API call in five minutes
Create a free account, get your API key, make your first request. No card required.
Create a free account
Go to hush-ai.uk and sign up. It takes about thirty seconds. No credit card is required.
You will receive an API key in your account dashboard after signing in.
Get your API key
After signing in, find your API key in the account settings. Copy it; you will need it for every API request.
Keep your key secret. Do not expose it in client-side code, public repositories, or browser requests. Use environment variables or a secrets manager.
Set it as an environment variable:
# Linux / macOS export HUSH_API_KEY="your-api-key-here" # Windows (PowerShell) $env:HUSH_API_KEY = "your-api-key-here"
Install the client library
The Hush API is OpenAI-compatible, so you use the official OpenAI client libraries. No Hush-specific SDK needed.
pip install openai
npm install openai
curl is pre-installed on macOS and most Linux distributions. No installation needed.
Make your first request
Point the client at https://hush-ai.uk/v1 instead of the OpenAI endpoint. That is the only change.
import os from openai import OpenAI client = OpenAI( base_url="https://hush-ai.uk/v1", api_key=os.environ["HUSH_API_KEY"] ) response = client.chat.completions.create( model="omega", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is GDPR Article 28?"} ] ) print(response.choices[0].message.content)
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://hush-ai.uk/v1", apiKey: process.env.HUSH_API_KEY, }); const response = await client.chat.completions.create({ model: "omega", messages: [ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "What is GDPR Article 28?" }, ], }); console.log(response.choices[0].message.content);
curl https://hush-ai.uk/v1/chat/completions \ -H "Authorization: Bearer $HUSH_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "omega", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is GDPR Article 28?"} ] }'
Read the response
The response follows the standard OpenAI chat completion format:
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "omega",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "GDPR Article 28 sets out the obligations..."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 25,
"completion_tokens": 80,
"total_tokens": 105
}
}That is it. Your data hit our hardware in the UK, was processed in memory, and the request data is now gone. Not stored, not logged, not trained on.
Next steps
API reference: full endpoint documentation, all parameters, error codes.
Models: compare Omega, Prism and Lambda to choose the right model.
Streaming: receive responses as they are generated.
Pricing: per-token pricing, token packs, cost calculator.
Verify us: don't trust us, check us. Copy-paste terminal commands that prove every claim.
Ready to build?
Your data never leaves hardware we own. Start building private AI applications today.
Create a free account and copy your key →