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

# Introduction

> Route LLM requests across providers for lower cost and higher reliability.

Arbytra is an LLM routing layer that applies quantitative trading methodology to inference cost optimization. You can access models across providers through a single API, define your own routing strategy, and switch models through configuration. Arbytra charges zero price markup. You pay the price that providers charge.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Send your first request in minutes
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Complete API documentation
  </Card>

  <Card title="Python SDK" icon="python" href="/sdk/python">
    Native Python SDK with OpenAI compatibility
  </Card>

  <Card title="TypeScript SDK" icon="js" href="/sdk/typescript">
    Native TypeScript SDK with full typing
  </Card>

  <Card title="Response API" icon="sparkles" href="/response-api/overview">
    OpenAI Response API format with multi-model routing
  </Card>
</CardGroup>

## What Arbytra Provides

* **[Routing and arbitrage](/guides/routing-options)** — Cost, latency, and quality optimization across models and providers. Arbytra runs deep [prompt-caching optimization](/guides/prompt-caching) and [cost optimization](/guides/cost-optimization).
* **[Automatic failover](/guides/error-handling)** — Redundancy and provider-aware rate limit management.
* **Budget controls** — Spending limits at the workspace or API key level. See [Error codes](/contract/error-codes) for budget enforcement behavior.
* **[BYOK](/platform/byok)** — Use your own provider keys, platform keys, or both.

Arbytra provides native SDKs for [Python](/sdk/python) and [TypeScript](/sdk/typescript). It's OpenAI-compatible: both [Chat Completions](/api-reference/chat-completions) and the [Response API](/api-reference/create-response) (preview) work through Arbytra. If you already use an OpenAI client or framework, you can point it at Arbytra with [minimal changes](/openai-compatibility).

## Resources

* [Available Models](https://www.arbytra.com/models) — Supported models and providers. Fetch model directory data with the [Model directory API](/api-reference/model-directory).
* [Pricing](https://www.arbytra.com/pricing) — Pricing information
* [Status page](https://status.arbytra.com/) — Current system health and incident history
* **[Support page](https://www.arbytra.com/support)** — Or email [support@arbytra.com](mailto:support@arbytra.com) for questions, bug reports, or help
* **Security** — Report vulnerabilities to [support@arbytra.com](mailto:support@arbytra.com) (see [security.txt](https://arbytra.com/.well-known/security.txt))

## Machine-readable sources

You can access Arbytra's documentation in machine-readable formats for AI agents and programmatic use.

* [llms.txt](/llms.txt) — Index of all documentation sections in plaintext, following the [llms.txt standard](https://llmstxt.org/)
* [llms-full.txt](/llms-full.txt) — Complete documentation in a single file
* [OpenAPI spec](/openapi.yaml) — OpenAPI 3.1 specification for all API endpoints