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

# Flatkey: AI API Gateway for 160+ Models — One Key, 50% Off

> Flatkey gives you one OpenAI-compatible API key for 160+ official models — GPT, Claude, Gemini, DeepSeek, and more — at up to 50% off official pricing.

Flatkey is an AI API gateway that gives you a single OpenAI-compatible endpoint for 160+ official models from OpenAI, Anthropic, Google, DeepSeek, Qwen, GLM, and more. Change your `base_url` to `https://router.flatkey.ai/v1`, keep your existing code, and start saving immediately — models are priced at up to 50% off official list, and topping up $200 earns $100 free credit.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/quickstart">
    Make your first API call in under 5 minutes
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Full endpoint reference with request and response examples
  </Card>

  <Card title="Model Directory" icon="list" href="/reference/model-list">
    Browse all 160+ models, providers, and live pricing
  </Card>

  <Card title="Pricing & Credits" icon="coins" href="/concepts/billing">
    Understand prepaid top-ups and bonus credit stacking
  </Card>
</CardGroup>

## How Flatkey works

<Steps>
  <Step title="Create your account">
    Sign up at [console.flatkey.ai](https://console.flatkey.ai/sign-up) and top up your balance. No monthly subscription — you only pay for what you use.
  </Step>

  <Step title="Generate an API key">
    Open the **Keys** section in the dashboard and create a new API key. Keep it secret — treat it like a password.
  </Step>

  <Step title="Point your client to Flatkey">
    Set `base_url` to `https://router.flatkey.ai/v1` in your OpenAI-compatible SDK. No other code changes required.
  </Step>

  <Step title="Monitor usage and costs">
    Track every request, token count, and dollar spent in the **Usage** dashboard. Set quotas to cap spend.
  </Step>
</Steps>

## Why teams use Flatkey

<CardGroup cols={3}>
  <Card title="One key, every model" icon="key">
    Access GPT, Claude, Gemini, DeepSeek, Qwen, GLM, and more with a single API key and base URL.
  </Card>

  <Card title="Up to 50% savings" icon="piggy-bank">
    Models priced at 60–90% of official list. Stack with the \$200 top-up bonus for as low as 50% off.
  </Card>

  <Card title="99.9% success rate" icon="shield-check">
    Automatic failover across upstream providers. Live health dashboards for every model.
  </Card>

  <Card title="Zero data retention" icon="lock">
    No storage of prompts or completions. GDPR compliant, SOC 2 and ISO 27001 aligned.
  </Card>

  <Card title="Drop-in replacement" icon="plug">
    OpenAI-compatible API. Change one line of code — no SDK rewrites, no migration overhead.
  </Card>

  <Card title="Prepaid, no surprises" icon="receipt">
    Top up your balance and consume only what you use. No recurring charges or unexpected bills.
  </Card>
</CardGroup>

## Explore the docs

<CardGroup cols={2}>
  <Card title="Authentication" icon="lock-keyhole" href="/authentication">
    Learn how to create and use your Flatkey API key
  </Card>

  <Card title="OpenAI SDK Guide" icon="python" href="/guides/openai-sdk">
    Use Flatkey with the official OpenAI Python or Node.js SDK
  </Card>

  <Card title="Anthropic SDK Guide" icon="robot" href="/guides/anthropic-sdk">
    Route Claude requests through Flatkey with the Anthropic SDK
  </Card>

  <Card title="Model Health" icon="heart-pulse" href="/reference/model-health">
    View real-time success rates and latency for every model
  </Card>
</CardGroup>