Get started with Python + FastAPI

Arcjet is the runtime security platform that ships with your code. Enforce budgets, stop prompt injection, detect bots, and protect personal information with Arcjet’s AI security building blocks.

Tip

Using an AI coding assistant? See the Agent get started guide, or tell your agent: “Set up Arcjet security for my app. Connect to the Arcjet MCP server to get my API key, then add shield, bot detection, and rate limiting.”

This guide shows you how to protect an application with Arcjet by blocking automated clients that inflate costs and enforcing per-user token budgets.

1. Install Arcjet

In your project root, run the following:

mkdir arcjet-fastapi
cd arcjet-fastapi
uv init
uv add arcjet fastapi uvicorn langchain langchain-openai

Requirements

• CPython 3.10 or later on macOS, Windows, and glibc Linux (Debian, Ubuntu, RHEL, and *-slim / manylinux container images)
• Alpine Linux and other musl-based systems aren’t supported. Prefer a glibc container image such as python:3.10-slim or astral/uv:python3.10-trixie-slim

Two runtime dependencies ship native code:

• wasmtime: local WASM rule evaluation
• pyqwest: HTTP client used by connect-python

Those packages publish musllinux wheels, so pip install arcjet can succeed on Alpine without a compiler. Alpine/musl isn’t a supported target. A missing wheel forces a source build that needs Rust and a C toolchain.

2. Set your key

Create a free Arcjet account then follow the instructions to add a site and get a key.

Set your environment variables:

.env

# Export your Arcjet API key from https://console.arcjet.com
ARCJET_KEY="ajkey_..."
ARCJET_ENV=development

# Export your OpenAI API key (used by LangChain)
OPENAI_API_KEY="sk-..."

3. Configure

This configures Arcjet to protect your AI application: block automated clients that inflate costs, and enforce per-user token budgets.

Create a new file at main.py with the contents:

main.py

import logging
import os

from arcjet import (
    Mode,
    arcjet,
    detect_bot,
    detect_prompt_injection,
    shield,
    token_bucket,
)
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from pydantic import BaseModel

app = FastAPI()

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

arcjet_key = os.getenv("ARCJET_KEY")
if not arcjet_key:
    raise RuntimeError("ARCJET_KEY is required. Get one at https://console.arcjet.com")

openai_api_key = os.getenv("OPENAI_API_KEY")
if not openai_api_key:
    raise RuntimeError(
        "OPENAI_API_KEY is required. Get one at https://platform.openai.com"
    )

llm = ChatOpenAI(model="gpt-4o-mini", api_key=openai_api_key)

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "You are a helpful assistant."),
        ("human", "{message}"),
    ]
)

chain = prompt | llm | StrOutputParser()


class ChatRequest(BaseModel):
    message: str


aj = arcjet(
    key=arcjet_key,  # Get your key from https://console.arcjet.com
    rules=[
        # Shield protects your app from common attacks e.g. SQL injection
        shield(mode=Mode.LIVE),
        # Create a bot detection rule
        detect_bot(
            mode=Mode.LIVE,
            # An empty allow list blocks all bots, which is a good default for
            # an AI chat app
            allow=[
                "CURL",  # Allow curl so we can test it
                # Uncomment to allow these other common bot categories
                # See the full list at https://arcjet.com/bot-list
                # BotCategory.MONITOR, # Uptime monitoring services
                # BotCategory.PREVIEW, # Link previews e.g. Slack, Discord
            ],
        ),
        # Create a token bucket rate limit. Other algorithms are supported
        token_bucket(
            # Track budgets by arbitrary characteristics of the request. Here
            # we use user ID, but you could pass any value. Removing this will
            # fall back to IP-based rate limiting.
            characteristics=["userId"],
            mode=Mode.LIVE,
            refill_rate=5,  # Refill 5 tokens per interval
            interval=10,  # Refill every 10 seconds
            capacity=10,  # Bucket capacity of 10 tokens
        ),
        # Detect prompt injection attacks before they reach your AI model
        detect_prompt_injection(
            mode=Mode.LIVE,  # Blocks requests. Use Mode.DRY_RUN to log only
        ),
    ],
)


@app.post("/chat")
async def chat(request: Request, body: ChatRequest):
    # Replace with actual user ID from the user session
    userId = "your_user_id"

    # Call protect() to evaluate the request against the rules
    decision = await aj.protect(
        request,
        # Deduct 5 tokens from the bucket
        requested=5,
        # Identify the user for rate limiting purposes
        characteristics={"userId": userId},
        # Check the user message for prompt injection
        detect_prompt_injection_message=body.message,
    )

    # Handle denied requests
    if decision.is_denied():
        if decision.reason_v2.type == "PROMPT_INJECTION":
            return JSONResponse(
                {"error": "Prompt injection detected — please rephrase your message"},
                status_code=400,
            )
        status = 429 if decision.reason_v2.type == "RATE_LIMIT" else 403
        return JSONResponse({"error": "Denied"}, status_code=status)

    # All rules passed, proceed with handling the request
    reply = await chain.ainvoke({"message": body.message})

    return {"reply": reply}

4. Start app

uv run uvicorn main:app --reload

And send a message to the API endpoint:

curl -X POST http://localhost:8000/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "What is the capital of France?"}'

Requests appear in your Arcjet dashboard in real time.

The requests also appear in the Arcjet dashboard.

FAQs

Do I need to run any infrastructure e.g. Redis?

No, Arcjet handles all the infrastructure for you so you don't need to worry about deploying global Redis clusters, designing data structures to track rate limits, or keeping security detection rules up to date.

What is the performance overhead?

Arcjet SDK tries to do as much as possible asynchronously and locally to minimize latency for each request. Where decisions can be made locally or previous decisions are cached in-memory, latency is usually <1ms.

When a call to the Cloud API is required, such as when tracking a rate limit in a serverless environment, there is some additional latency before a decision is made. The Cloud API has been designed for high performance and low latency, and is deployed to multiple regions around the world. The SDK will automatically use the closest region which means the total overhead is typically no more than 20-30ms, often significantly less.

What happens if Arcjet is unavailable?

Where a decision has been cached locally e.g. blocking a client, Arcjet will continue to function even if the service is unavailable.

If a call to the Cloud API is needed and there is a network problem or Arcjet is unavailable, the default behavior is to fail open and allow the request. You have control over how to handle errors, including choosing to fail close if you prefer. See the reference docs for details.

How does Arcjet protect me against DDoS attacks?

Network layer attacks tend to be generic and high volume, so these are best handled by your hosting platform. Most cloud providers include network DDoS protection by default.

Arcjet sits closer to your application so it can understand the context. This is important because some types of traffic may not look like a DDoS attack, but can still have the same effect. For example, a customer making too many API requests and affecting other customers, or large numbers of signups from disposable email addresses.

Network-level DDoS protection tools find it difficult to protect against this type of traffic because they don't understand the structure of your application. Arcjet can help you to identify and block this traffic by integrating with your codebase and understanding the context of the request e.g. the customer ID or sensitivity of the API route.

Volumetric network attacks are best handled by your hosting provider. Application level attacks need to be handled by the application. That's where Arcjet helps.

What next?

AI runtime protection The runtime policy engine for AI features.

Agent guard integrations Wrap tools in Vercel AI SDK, LangChain, LangChain JS, CrewAI, LangGraph, Genkit, OpenAI Agents, OpenAI Agents Python, Strands Agents, Eve, Mastra, and Claude Agent SDK.

Customize allowed bots Identify bots and configure allow/deny lists.

Testing Write tests for your rules.

Get help

Need help with anything? Email us or join our Discord to get support from our engineering team.