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

# Introduction

> How developers build AI applications. Explore our docs to learn how to easily integrate Helicone into your application and explore features that will accelerate your team's development.

<img src="https://mintcdn.com/helicone/psm-vDV7pnoZSp6H/images/helicone-og.webp?fit=max&auto=format&n=psm-vDV7pnoZSp6H&q=85&s=d379c91e81abf298c8db37807b521929" alt="title" width="3600" height="1890" data-path="images/helicone-og.webp" />

## Who Are We?

We are a team of passionate developers who are committed to making best in class tooling for the AI community. We believe that the future of AI is in large language models (LLMs), and we are dedicated to making LLMs more accessible to developers and enterprises. Our goal is to simplify the use and management of LLMs, so that developers can focus on building the next generation of AI-driven applications.

### Getting Started

<CardGroup cols={1}>
  <Card title="Get Started" icon="code" href="/getting-started/quick-start">
    Quickly integrate Helicone into your application and get started.
  </Card>
</CardGroup>

### Integrations

<CardGroup cols={1}>
  <Card title="Gateway" href="/getting-started/integration-method/gateway">
    The optimal method to integrate with Helicone is through our Gateway.
  </Card>
</CardGroup>

<CardGroup cols={3}>
  <Card title="OpenAI" href="/getting-started/integration-method/openai-proxy">
    Python, Node, cURL, Langchain
  </Card>

  <Card title="Anthropic" href="/getting-started/integration-method/anthropic">
    Python, Node, cURL, Langchain
  </Card>

  <Card title="Azure" href="/getting-started/integration-method/azure">
    Python, Node, cURL, Langchain
  </Card>

  <Card title="Anyscale" href="/getting-started/integration-method/anyscale" />

  <Card title="OpenRouter" href="/getting-started/integration-method/openrouter" />

  <Card title="LiteLLM" href="/getting-started/integration-method/litellm" />
</CardGroup>

### Features

<CardGroup cols={2}>
  <Card title="Prompts" href="/features/advanced-usage/prompts">
    Effortlessly monitor prompt versions and inputs
  </Card>

  <Card title="Custom Properties" href="/features/advanced-usage/custom-properties">
    Label and segment your requests
  </Card>

  <Card title="Feedback" href="/features/advanced-usage/feedback">
    Provide user feedback
  </Card>

  <Card title="Caching" href="/features/advanced-usage/caching">
    Save cost and improve latency
  </Card>

  <Card title="Streaming" href="/features/streaming">
    Usage statistics
  </Card>

  <Card title="Rate Limiting" href="/features/advanced-usage/custom-rate-limits">
    Easily rate-limit power users
  </Card>

  <Card title="Retries" href="/features/advanced-usage/retries">
    Smartly retry requests
  </Card>

  <Card title="Fine Tuning" href="/features/advanced-usage/fine-tuning">
    Fine-tune a model on your logs
  </Card>

  <Card title="Customer Portal" href="/features/customer-portal">
    Fine-tune a model on your logs
  </Card>

  <Card title="Key Vault" href="/features/advanced-usage/key-vault">
    Remove request and responses
  </Card>

  <Card title="Jobs" href="/features/jobs/quick-start">
    Visualize chained requests
  </Card>

  <Card title="Omit Logs" href="/features/advanced-usage/omit-logs">
    Remove request and responses
  </Card>

  <Card title="User Metrics" href="/features/advanced-usage/user-metrics">
    Insights into your users
  </Card>
</CardGroup>