Quick Start — 60 Seconds to Smarter AI

Kairos is a drop-in replacement for the OpenAI API. Change one line — the base URL — and everything else stays the same.

Step 1: Get your API key

Go to Dashboard → API Keys → Create Key. Choose the "Production" template.

Step 2: Change your base URL

javascript
import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: 'kai_your_key_here',
  baseURL: 'https://api.kairos-ctx.ai',
})

const response = await client.chat.completions.create({
  model: 'auto',  // Kairos routes to the optimal model
  messages: [{ role: 'user', content: 'Summarize this legal contract...' }],
})
console.log(response.kairos?.routedModel)        // e.g. "claude-3-5-sonnet"
console.log(response.kairos?.compressionSavingsUsd) // e.g. 0.0021
python
from openai import OpenAI

client = OpenAI(
    api_key="kai_your_key_here",
    base_url="https://api.kairos-ctx.ai",
)
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
bash
curl https://api.kairos-ctx.ai/v1/chat/completions \
  -H "Authorization: Bearer kai_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello!"}]}'

What happens to every request

1. Authentication — Your kai_ key is validated, rate limits and budget checked

2. Context Compression — Task-relevant tokens only reach the LLM, others are removed

3. DLP Scan — PII detected and handled per your active compliance mandates

4. Routing — Request sent to optimal model based on your rules

5. Inference — Forwarded to LLM provider using your stored provider key

6. Response — Returned with cost, savings, routing trace, audit hash

Kairos never stores message content. Audit logs record metadata only (tokens, cost, routing, DLP events) unless you explicitly enable context snapshots.