> ## 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: One Key, 160+ Official AI Models, Up to 50% Off

> Flatkey is an AI API gateway for GPT, Claude, Gemini, DeepSeek, and 160+ models via one OpenAI-compatible key. Access official models at up to 50% off.

Flatkey is an AI API gateway that lets you access 160+ official models from OpenAI, Anthropic, Google, DeepSeek, Qwen, GLM, and more — all through a single OpenAI-compatible API key. It is a drop-in replacement for any OpenAI-compatible client: change one line of code (`base_url`) and your requests are routed through Flatkey at up to 50% off official pricing, thanks to discounted base rates and stackable bonus credits on every top-up.

## What Flatkey gives you

<CardGroup cols={2}>
  <Card title="One key, all models" icon="key">
    A single API key and base URL routes to GPT, Claude, Gemini, DeepSeek, Qwen, GLM, and more. No per-provider keys to manage.
  </Card>

  <Card title="Up to 50% savings" icon="piggy-bank">
    Models priced at 60–90% of official list. Top up $200, get $100 bonus credit — stacked, as low as half the official price.
  </Card>

  <Card title="99.9% reliability" icon="shield-check">
    Automatic failover across upstream providers. Live health dashboards show real success rates from production traffic.
  </Card>

  <Card title="Zero data retention" icon="lock">
    Prompts and completions are never stored. GDPR compliant, SOC 2 and ISO 27001 aligned controls.
  </Card>

  <Card title="Prepaid balance" icon="receipt">
    Top up once, consume as you go. No subscriptions, no surprise invoices.
  </Card>

  <Card title="Full API compatibility" icon="plug">
    OpenAI-compatible endpoints: chat completions, responses, embeddings, image generation, and models list.
  </Card>
</CardGroup>

## Supported providers

Flatkey routes to official APIs from every major AI vendor:

| Provider   | Example models                                        |
| ---------- | ----------------------------------------------------- |
| OpenAI     | gpt-4o, gpt-4o-mini, gpt-5, gpt-image-2               |
| Anthropic  | claude-opus-4, claude-sonnet-4, claude-haiku-4        |
| Google     | gemini-2.5-pro, gemini-2.5-flash, gemini-flash-latest |
| DeepSeek   | deepseek-v3, deepseek-v4-pro, deepseek-v4-flash       |
| Qwen       | qwen3.5-plus, qwen3.7-max, qwen3.5-flash              |
| Z.ai / GLM | glm-4.7, glm-5-turbo, glm-5.2                         |

See the full [Model Directory](/reference/model-list) for all 160+ models with live pricing and health data.

## How it works

Flatkey sits between your application and AI providers. When you send a request:

1. Your client calls `https://router.flatkey.ai/v1` with your Flatkey API key.
2. Flatkey authenticates the request and deducts the cost from your prepaid balance.
3. The request is forwarded to the official provider API (OpenAI, Anthropic, etc.).
4. The response is returned directly to your client — no transformation of the content.

Your prompts and completions are never stored. Flatkey only records metadata (model, token counts, timestamps) for billing and analytics.

## Next steps

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

  <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 SDK — Python or Node.js
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Full endpoint reference for all supported API methods
  </Card>
</CardGroup>