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

# Piramyd: OpenAI-Compatible Inference Gateway for AI

> Route AI requests to OpenAI, Anthropic, and more through one OpenAI-compatible API. Built-in web search, scraping, and crawling included.

Piramyd is an inference gateway that gives you one unified API for multiple AI providers. Send requests in the OpenAI chat completions format, and Piramyd routes them to the right upstream model—whether that's a Claude, GPT, or a specialized decision model. You also get built-in web search, scraping, and crawling without stitching together separate services.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/quickstart">
    Make your first API call in under five minutes
  </Card>

  <Card title="Authentication" icon="key" href="/authentication">
    Get your API key and learn how to authenticate requests
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/chat-completions">
    Complete reference for every endpoint
  </Card>

  <Card title="OpenAI SDK Compatibility" icon="plug" href="/guides/openai-sdk-compatibility">
    Drop Piramyd in as a replacement for the OpenAI SDK
  </Card>
</CardGroup>

## What Piramyd Does

Piramyd exposes a single versioned API at `https://api.piramyd.cloud/v1` that handles:

* **Chat completions** — OpenAI-compatible `POST /v1/chat/completions` with streaming, tool calling, and vision
* **Anthropic messages** — `POST /v1/messages` for codebases already using the Anthropic SDK
* **System One decisions** — `POST /v1/systemone` for fast, typed classification and scoring with Jev models
* **Web search** — `POST /v1/search` powered by SIRS (multi-engine SearXNG)
* **Web scraping & crawling** — `POST /v1/scrape`, `POST /v1/crawl`, and more via CROWD (Firecrawl)
* **Structured extraction** — `POST /v1/extract` to pull structured data from URLs using an LLM

<CardGroup cols={3}>
  <Card title="Models" icon="layer-group" href="/concepts/models">
    Discover available models at runtime
  </Card>

  <Card title="Context Compaction" icon="compress" href="/concepts/context-compaction">
    Automatic long-conversation management
  </Card>

  <Card title="Tool Calling" icon="wrench" href="/guides/tool-calling">
    Function calling with integrity guarantees
  </Card>

  <Card title="Vision" icon="eye" href="/guides/vision">
    Send images alongside your prompts
  </Card>

  <Card title="Web Intelligence" icon="globe" href="/guides/web-intelligence">
    Search, scrape, and extract web content
  </Card>

  <Card title="Pricing & Tiers" icon="credit-card" href="/concepts/pricing-and-tiers">
    Flat-rate plans with unlimited tokens
  </Card>
</CardGroup>

## Get Started in 3 Steps

<Steps>
  <Step title="Create an account">
    Sign up at [dash.piramyd.cloud](https://dash.piramyd.cloud) to get your API key. A 3-day trial on the Solo plan is available (card required).
  </Step>

  <Step title="Make your first request">
    Use your API key with the OpenAI SDK or any HTTP client. Point `base_url` at `https://api.piramyd.cloud/v1` and send a chat completion.
  </Step>

  <Step title="Discover models dynamically">
    Call `GET /v1/models` to list available models with their capabilities, context windows, and supported endpoints. Never hardcode model IDs.
  </Step>
</Steps>

<Tip>
  Piramyd is a drop-in replacement for the OpenAI SDK — just change `base_url` to `https://api.piramyd.cloud/v1` and your existing code works immediately.
</Tip>