Quickstart

Add AI to Your App in 5 Minutes

Get your API key, make your first call, and ship AI features. No backend required.

Prerequisites

A Behest AI account (free, sign up at behest.ai/dashboard — no credit card required)
Any HTTP client — fetch, axios, requests, curl, or your language of choice

1Get Your API Key

Sign up at behest.ai/dashboard
Create a new project
Configure your allowed CORS origins (e.g., http://localhost:3000 for local development)
Copy your project API key

Your project URL will look like https://your-project.behest.app

2Make Your First API Call

Two headers to attribute every request

Behest groups token usage and cost by X-End-User-Id (the end user) and X-Session-Id (the conversation thread). Set both on every request so your dashboard can show per-user and per-session spend instead of one aggregate bucket.

Use any unique identifier for X-Session-Id — typically a chat session ID or a user-{userId}-conv-{conversationId} pair. The header is optional, but skipping it collapses every request into a single “no session” bucket in your analytics.

JavaScript (fetch)

const response = await fetch(
  "https://your-project.behest.app/v1/chat/completions",
  {
    method: "POST",
    headers: {
      "Authorization": "Bearer your-api-key",
      "Content-Type": "application/json",
      "X-End-User-Id": userId,
      // Uniquely identifies a conversation thread for per-session cost attribution.
      "X-Session-Id": `user-${userId}-conv-${conversationId}`,
    },
    body: JSON.stringify({
      model: "gemini-2.5-flash",
      messages: [
        { role: "user", content: "Summarize this contract" }
      ],
    }),
  }
);

const data = await response.json();
console.log(data.choices[0].message.content);

Python (requests)

import requests

response = requests.post(
    "https://your-project.behest.app/v1/chat/completions",
    headers={
        "Authorization": "Bearer your-api-key",
        "Content-Type": "application/json",
        "X-End-User-Id": user_id,
        # Uniquely identifies a conversation thread for per-session cost attribution.
        "X-Session-Id": f"user-{user_id}-conv-{conversation_id}",
    },
    json={
        "model": "gemini-2.5-flash",
        "messages": [
            {"role": "user", "content": "Summarize this contract"}
        ],
    },
)

data = response.json()
print(data["choices"][0]["message"]["content"])

curl

# X-Session-Id uniquely identifies a conversation thread for
# per-session cost attribution in your analytics dashboard.
curl -X POST https://your-project.behest.app/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -H "X-End-User-Id: user-123" \
  -H "X-Session-Id: user-123-conv-abc" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [
      {"role": "user", "content": "Summarize this contract"}
    ]
  }'

3What Happens Automatically

When you make that API call, Behest handles everything behind the scenes:

CORS handled — Browser requests just work

Auth validated — API key verified, tenant isolated

PII scrubbed — Sensitive data detected and protected

Prompts defended — Injection attacks blocked

Rate limits enforced — Per-IP, per-project, per-user

Memory persisted — Conversation context maintained

Tokens tracked — Usage and spend recorded

Fully observable — Traces, metrics, and logs captured

Next Steps

API Reference

Full endpoint documentation, request/response schemas, and error codes.

CORS Guide

How Behest handles CORS so you can call your LLM from the browser.

Add AI to React

Complete React component example with state management and streaming.

Add AI to Next.js

Server Component and Client Component patterns for Next.js apps.

Multi-Tenant Auth

JWT, API keys, tenant isolation, and per-user rate limiting.

PII Protection

Configure PII Shield modes, actions, and per-entity settings.