> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/helicone/helicone/llms.txt
> Use this file to discover all available pages before exploring further.

# Helicone - Open Source LLM Observability Platform

> Monitor, evaluate, and route requests to 100+ AI models with the leading open-source LLM observability platform and AI Gateway

<div className="bg-gradient-to-br from-[#e4f0f7] to-white py-16 px-4 rounded-xl border border-[#3188ad]/20 shadow-lg mb-12">
  <div className="max-w-4xl mx-auto text-center">
    <h1 className="text-5xl font-bold text-gray-900 mb-6">
      The Open Source LLM Observability Platform
    </h1>

    <p className="text-xl text-gray-700 mb-8 leading-relaxed">
      Monitor, evaluate, and route requests to 100+ AI models. Built for developers who need production-grade observability and intelligent routing.
    </p>

    <div className="flex flex-wrap gap-4 justify-center">
      <a href="/quick-start" className="inline-block bg-[#1491ff] text-white font-semibold px-8 py-4 rounded-md hover:bg-[#0d7de8] transition-colors shadow-md">
        Get Started →
      </a>

      <a href="https://github.com/helicone/helicone" className="inline-block bg-white text-[#0a0a0a] font-semibold px-8 py-4 rounded-md hover:bg-gray-50 transition-colors shadow-md border border-gray-200">
        View on GitHub
      </a>
    </div>
  </div>
</div>

## Why Helicone?

<CardGroup cols={3}>
  <Card title="AI Gateway" icon="network-wired" href="/gateway/overview">
    Access 100+ AI models with one unified API. Intelligent routing, automatic fallbacks, and unified observability built in.
  </Card>

  <Card title="Full Observability" icon="chart-line" href="/observability/overview">
    Track every request, session, and trace. Monitor cost, latency, and quality across your entire AI stack.
  </Card>

  <Card title="Open Source" icon="code-branch" href="https://github.com/helicone/helicone">
    Self-host with Docker or Kubernetes. Your data stays under your control. Apache 2.0 licensed.
  </Card>
</CardGroup>

## Key Features

<CardGroup cols={2}>
  <Card title="Prompt Management" icon="file-code" href="/prompts/overview">
    Version and deploy prompts without code changes. Test iterations with production data.
  </Card>

  <Card title="Session Tracking" icon="diagram-project" href="/observability/sessions">
    Trace complex agent workflows and multi-step processes end-to-end.
  </Card>

  <Card title="Evaluation Framework" icon="flask" href="/evaluation/overview">
    Score and evaluate responses. Build datasets from production traffic.
  </Card>

  <Card title="Cost Analytics" icon="dollar-sign" href="/guides/cost-tracking">
    Track spending across providers. Identify expensive patterns and optimize costs.
  </Card>

  <Card title="Response Caching" icon="database" href="/features/caching">
    Reduce costs by up to 90% with intelligent response caching.
  </Card>

  <Card title="Rate Limiting" icon="gauge-high" href="/features/rate-limiting">
    Control usage per user, team, or API key with custom rate limits.
  </Card>
</CardGroup>

## Quick Start

Get your first request logged in under 2 minutes:

<Steps>
  <Step title="Sign up and get your API key">
    Create a free account at [helicone.ai](https://helicone.ai/signup) and generate your API key.
  </Step>

  <Step title="Send a request through the AI Gateway">
    <Tabs>
      <Tab title="TypeScript">
        ```typescript theme={null}
        import { OpenAI } from "openai";

        const client = new OpenAI({
          baseURL: "https://ai-gateway.helicone.ai",
          apiKey: process.env.HELICONE_API_KEY,
        });

        const response = await client.chat.completions.create({
          model: "gpt-4o-mini", // Or any of 100+ models
          messages: [{ role: "user", content: "Hello!" }],
        });
        ```
      </Tab>

      <Tab title="Python">
        ```python theme={null}
        from openai import OpenAI

        client = OpenAI(
            base_url="https://ai-gateway.helicone.ai",
            api_key=os.getenv("HELICONE_API_KEY")
        )

        response = client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[{"role": "user", "content": "Hello!"}]
        )
        ```
      </Tab>

      <Tab title="cURL">
        ```bash theme={null}
        curl https://ai-gateway.helicone.ai/chat/completions \
          -H "Content-Type: application/json" \
          -H "Authorization: Bearer $HELICONE_API_KEY" \
          -d '{
            "model": "gpt-4o-mini",
            "messages": [{"role": "user", "content": "Hello!"}]
          }'
        ```
      </Tab>
    </Tabs>
  </Step>

  <Step title="View your logs">
    Navigate to your [dashboard](https://us.helicone.ai/dashboard) to see requests, costs, and performance metrics.
  </Step>
</Steps>

## Supported Providers

Access 100+ models from leading AI providers through a single API:

<CardGroup cols={4}>
  <Card title="OpenAI" icon="square" href="/integrations/openai">
    GPT-4, GPT-4o, GPT-3.5
  </Card>

  <Card title="Anthropic" icon="brain" href="/integrations/anthropic">
    Claude 3.5, Claude 3 Opus
  </Card>

  <Card title="Google" icon="google" href="/integrations/overview">
    Gemini, PaLM, Vertex AI
  </Card>

  <Card title="More Providers" icon="plus" href="/gateway/overview">
    Groq, Together, Anyscale, and more
  </Card>
</CardGroup>

## Enterprise Ready

<CardGroup cols={2}>
  <Card title="Self-Hosting" icon="server" href="/self-hosting/overview">
    Deploy on your infrastructure with Docker or Kubernetes. Full control over your data.
  </Card>

  <Card title="Security & Compliance" icon="shield-halved" href="/features/security">
    SOC 2 and GDPR compliant. Encryption at rest and in transit.
  </Card>
</CardGroup>

## Community & Support

<CardGroup cols={3}>
  <Card title="Documentation" icon="book" href="/introduction">
    Comprehensive guides and API reference
  </Card>

  <Card title="Discord Community" icon="discord" href="https://discord.com/invite/zsSTcH2qhG">
    Join 5,000+ developers building with Helicone
  </Card>

  <Card title="GitHub" icon="github" href="https://github.com/helicone/helicone">
    5,000+ stars. Contribute and report issues
  </Card>
</CardGroup>