> ## 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.

# Introduction to Helicone

> Open-source AI Gateway and LLM observability platform for building production AI applications with reliability, visibility, and control

<img src="https://mintlify.s3.us-west-1.amazonaws.com/helicone-helicone-7/images/helicone-og.webp" alt="Helicone Platform" />

## What is Helicone?

Helicone is an **open-source AI Gateway and LLM observability platform** that helps developers build production AI applications with complete visibility and reliability. We solve the hardest problems in production LLM applications: provider outages that break your app, unpredictable costs, and debugging issues that are impossible to reproduce.

<CardGroup cols={2}>
  <Card title="AI Gateway" icon="route">
    Access 100+ LLM models through a unified OpenAI-compatible API with automatic fallbacks, intelligent routing, and 0% markup
  </Card>

  <Card title="Full Observability" icon="chart-line">
    Complete visibility into every request with automatic cost tracking, latency monitoring, and session debugging
  </Card>

  <Card title="Open Source" icon="code-branch">
    Apache 2.0 licensed and self-hostable. Your data stays under your control, always accessible
  </Card>

  <Card title="Production Ready" icon="shield">
    SOC 2 and GDPR compliant with edge deployment for \<50ms overhead. Built for your worst day
  </Card>
</CardGroup>

## Key Features

### 🌐 AI Gateway

Access 100+ AI models with a single API key through our OpenAI-compatible gateway. Switch between OpenAI, Anthropic, Google, Groq, and more by just changing the model name. We handle intelligent routing, automatic fallbacks, and unified billing with 0% markup.

### 🔍 LLM Observability

Inspect and debug every request with automatic tracking of costs, latency, token usage, and errors. Trace multi-step AI workflows and agent sessions with full visibility into the reasoning chain.

### 🎮 Prompt Management

Version control your prompts and deploy changes without code updates. Test iterations in production, A/B test versions, and maintain full history of changes.

### 💰 Cost & Usage Tracking

Understand your unit economics with real-time cost tracking across all providers. Break down spending by user, feature, or any custom dimension. Set budgets and prevent surprise bills.

### 🎛️ Smart Controls

* **Caching**: Save costs and improve latency with automatic response caching
* **Rate Limiting**: Protect your budget with per-user or global rate limits
* **Automatic Fallbacks**: Stay online even when providers go down
* **Security**: Built-in content moderation and LLM security

## Who Uses Helicone?

<CardGroup cols={3}>
  <Card title="Startups" icon="rocket">
    Move fast with instant observability. No need to build monitoring infrastructure from scratch.
  </Card>

  <Card title="Enterprises" icon="building">
    Self-host for complete data control. SOC 2 compliant with enterprise Helm charts available.
  </Card>

  <Card title="AI Engineers" icon="code">
    Debug complex agent workflows. Trace multi-step reasoning with session trees and full context.
  </Card>
</CardGroup>

## Why Helicone?

**Best Price Always**\
We fight for every penny. 0% markup on credits means you pay exactly what providers charge. No hidden fees, no games.

**Invisible Performance**\
Your app shouldn't slow down for observability. Edge deployment keeps us under 50ms overhead. Always.

**Always Online**\
Your app stays up, period. Providers fail, we fallback. Rate limits hit, we load balance. We don't go down.

**Never Be Surprised**\
No shock bills. No mystery spikes. See every cost as it happens. We believe in radical transparency.

**Built for Your Worst Day**\
When production breaks at 3am and everyone's panicking, we're rock solid. Built for when you need us most.

## Getting Started

<Steps>
  <Step title="Quick Start">
    Get your first LLM request logged in under 2 minutes

    <Card title="Quick Start Guide" icon="bolt" href="/getting-started/quick-start">
      Send your first request through the AI Gateway and see it logged in real-time
    </Card>
  </Step>

  <Step title="Understand the Platform">
    Learn how Helicone solves production AI challenges

    <Card title="Platform Overview" icon="compass" href="/getting-started/platform-overview">
      Explore the architecture and see how the gateway, observability, and features work together
    </Card>
  </Step>

  <Step title="Explore Features">
    Go deeper with advanced capabilities

    <CardGroup cols={2}>
      <Card title="Sessions & Agent Tracing" icon="git-branch" href="/features/sessions">
        Debug multi-step AI workflows with full visibility
      </Card>

      <Card title="Prompt Management" icon="wand-magic-sparkles" href="/features/prompts">
        Version and deploy prompts without code changes
      </Card>

      <Card title="Gateway Fallbacks" icon="shield" href="/getting-started/integration-method/gateway-fallbacks">
        Automatic failover when providers go down
      </Card>

      <Card title="Cost Tracking" icon="chart-bar" href="/guides/cookbooks/cost-tracking">
        Understand your LLM economics by user or feature
      </Card>
    </CardGroup>
  </Step>
</Steps>

## Integration Methods

Helicone works in two ways:

<Tabs>
  <Tab title="AI Gateway (Recommended)">
    ### Use Credits for Instant Access

    Add credits to your Helicone account and access 100+ models without signing up for each provider. We manage the API keys and handle billing at cost (0% markup).

    **Benefits:**

    * Single integration for all providers
    * Switch models by just changing the name
    * Automatic observability built-in
    * No provider rate limits
    * Unified billing

    ```typescript theme={null}
    import OpenAI from "openai";

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

    // Use any model from any provider
    const response = await client.chat.completions.create({
      model: "gpt-4o-mini", // or claude-sonnet-4, gemini-2.0-flash, etc.
      messages: [{ role: "user", content: "Hello!" }],
    });
    ```
  </Tab>

  <Tab title="Bring Your Own Keys">
    ### Use Your Provider Keys

    Configure your own API keys for OpenAI, Anthropic, and other providers at [Provider Keys](https://us.helicone.ai/providers). You manage billing directly with providers while getting full Helicone observability.

    **When to use:**

    * You have existing provider relationships
    * You need provider-specific features
    * You want direct provider billing

    ```typescript theme={null}
    import OpenAI from "openai";

    const client = new OpenAI({
      baseURL: "https://oai.helicone.ai/v1",
      apiKey: process.env.OPENAI_API_KEY,
      defaultHeaders: {
        "Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`,
      },
    });
    ```
  </Tab>
</Tabs>

## Supported Providers

Helicone integrates with **100+ LLM providers** including:

<CardGroup cols={4}>
  <Card title="OpenAI" icon="circle">
    GPT-4o, GPT-4o-mini, o1, o3
  </Card>

  <Card title="Anthropic" icon="circle">
    Claude Sonnet 4, Opus, Haiku
  </Card>

  <Card title="Google" icon="circle">
    Gemini 2.0, Gemini Pro, Vertex AI
  </Card>

  <Card title="Groq" icon="circle">
    Llama, Mixtral, Gemma
  </Card>

  <Card title="AWS Bedrock" icon="circle">
    Claude, Llama, Titan
  </Card>

  <Card title="Azure OpenAI" icon="circle">
    All Azure-hosted models
  </Card>

  <Card title="Together AI" icon="circle">
    Open-source models
  </Card>

  <Card title="And More" icon="plus">
    Mistral, DeepSeek, Perplexity, X.AI, Fireworks, and more
  </Card>
</CardGroup>

See the [complete list of supported models](https://helicone.ai/models).

## Framework Integrations

Helicone works seamlessly with popular AI frameworks:

* **LangChain** (JS/TS & Python) - Use AI Gateway for unified provider access
* **LlamaIndex** (Python) - Full observability for data applications
* **LangGraph** (Python) - Track stateful multi-actor workflows
* **Vercel AI SDK** (JS/TS) - Build AI-powered applications
* **CrewAI** (Python) - Monitor role-playing AI agents

See all [integrations in our docs](https://docs.helicone.ai/gateway/integrations/overview).

## Open Source & Self-Hosting

Helicone is **Apache 2.0 licensed** and fully open source. Self-host for complete data ownership and control.

<CardGroup cols={2}>
  <Card title="Docker Setup" icon="docker" href="/getting-started/self-host/docker">
    Get started with Docker Compose in minutes
  </Card>

  <Card title="Helm Chart" icon="kubernetes">
    Production-ready Kubernetes deployment (contact [enterprise@helicone.ai](mailto:enterprise@helicone.ai))
  </Card>
</CardGroup>

**GitHub:** [github.com/helicone/helicone](https://github.com/helicone/helicone)\
**⭐ Star us** if you find Helicone useful!

## Community & Support

<CardGroup cols={2}>
  <Card title="Discord Community" icon="discord" href="https://discord.com/invite/HwUbV3Q8qz">
    Join 2000+ developers building with Helicone
  </Card>

  <Card title="Documentation" icon="book" href="/getting-started/quick-start">
    Comprehensive guides and API references
  </Card>

  <Card title="Email Support" icon="envelope">
    [help@helicone.ai](mailto:help@helicone.ai) for questions and feedback
  </Card>

  <Card title="GitHub Issues" icon="github" href="https://github.com/helicone/helicone/issues">
    Report bugs and request features
  </Card>
</CardGroup>

## What's Next?

Ready to get started? Follow our quick start guide to log your first request in under 2 minutes.

<Card title="Quick Start Guide" href="/getting-started/quick-start" icon="rocket" horizontal>
  Send your first LLM request through Helicone and see it logged in real-time
</Card>