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

# Inception Platform

> Build with Mercury — the fastest reasoning and code models, served through an OpenAI-compatible API.

Inception's **Mercury** models use diffusion to generate tokens in parallel, delivering high-quality responses with low latency. They're built for responsive AI applications and agent workflows where speed and quality matter. The API is OpenAI-compatible, so you can be up and running in minutes with the tools you already use.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/get-started">
    Create an account, grab an API key, and send your first request.
  </Card>

  <Card title="Models & Pricing" icon="layer-group" href="/get-started/models">
    Compare Mercury 2.5, Mercury Voice, Mercury 2, Mercury Edit 2, and Mercury Decide — endpoints, context windows, and pricing.
  </Card>

  <Card title="Capabilities" icon="wand-magic-sparkles" href="/capabilities/reasoning-efforts">
    Streaming, tool use, structured outputs, autocomplete (FIM), and next edit.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/chat/create-a-chat-completion">
    Explore the REST endpoints for chat, FIM, edit completions, decisions, and models.
  </Card>

  <Card title="Mercury Decide" icon="list-check" href="/capabilities/decisions">
    Classify, route, and score with typed decisions and probabilities.
  </Card>

  <Card title="Integrations" icon="plug" href="/integrations/cursor">
    Use Mercury in Cursor, Zed, VS Code extensions, LangChain, Vapi, and more.
  </Card>

  <Card title="Cookbooks" icon="book-open" href="/cookbooks/search-agent-mercury">
    End-to-end guides for search, customer support, voice, SQL, and coding agents.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.