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

# Boole AI: Fast Local and Cloud LLM Inference Platform

> Run 42 open models at 312 tokens/sec on your own GPU, or call our OpenAI-compatible cloud API. Zero telemetry, zero retention, $20 free credits on signup.

Boole AI delivers high-throughput LLM inference two ways: download a single binary and run models on your own GPU at zero per-token cost, or call our cloud API at prices well below market alternatives. Either way, you get the same OpenAI-compatible interface — no code changes needed.

<CardGroup cols={2}>
  <Card title="Local Quickstart" icon="server" href="/quickstart-local">
    Deploy a model binary on your GPU and serve 312 tokens/sec in under 4 minutes.
  </Card>

  <Card title="API Quickstart" icon="bolt" href="/quickstart-api">
    Get an API key and make your first inference call in minutes — 1M free tokens included.
  </Card>

  <Card title="Models" icon="brain" href="/concepts/models">
    Browse 42 supported models including Llama 3.3 70B, Qwen 2.5 72B, and DeepSeek V3.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Explore the full OpenAI-compatible REST API with request and response schemas.
  </Card>
</CardGroup>

## Get Started in Minutes

<Steps>
  <Step title="Create an account">
    Sign up at [booleinference.com/signup](https://booleinference.com/signup) — no credit card required. You receive \$20 in free credits (1M tokens) automatically.
  </Step>

  <Step title="Choose your deployment mode">
    Run locally for zero per-token cost and full data privacy, or use the cloud API for instant access with no hardware required.
  </Step>

  <Step title="Point your existing code at Boole">
    Set `base_url` to `https://api.boole.dev/v1` (cloud) or `http://localhost:8000/v1` (local). No other code changes needed — Boole is fully OpenAI-compatible.
  </Step>

  <Step title="Start inferring">
    Call `chat/completions`, stream responses, use tool calls and structured outputs — everything works out of the box.
  </Step>
</Steps>

## Why Boole AI

<CardGroup cols={2}>
  <Card title="Fastest Local Throughput" icon="gauge-high">
    312 tokens/sec on Llama 3.3 70B on a single A10 GPU — faster than vLLM, TGI, and TensorRT-LLM.
  </Card>

  <Card title="Nightly Compiler Optimization" icon="rotate">
    An automated agent rewrites the model runtime every night, fusing kernels and quantizing weights — only keeping changes that pass a frozen quality gate.
  </Card>

  <Card title="Zero Data Retention" icon="shield-check">
    Prompts and completions are never stored after the response is returned. Full SOC 2 Type II compliance.
  </Card>

  <Card title="OpenAI-Compatible" icon="plug">
    Drop-in replacement for the OpenAI API. Works with every existing SDK and integration unmodified.
  </Card>
</CardGroup>