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

# AI Gateway

> The world's fastest AI Gateway with advanced routing & integrated Guardrails.

## Features

> [card] [Universal API](https://docs.portkey.ai/docs/product/ai-gateway/universal-api.md)
>
> Use any of the supported models with a universal API (REST and SDKs)

> [card] [Cache (Simple & Semantic)](https://docs.portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic.md)
>
> Save costs and decrease latencies by using a cache

> [card] [MCP Support](https://docs.portkey.ai/docs/product/ai-gateway/remote-mcp.md)
>
> Connect to Remote MCP severs, allowing you to connect external tools and data sources.

> [card] [Fallbacks](https://docs.portkey.ai/docs/product/ai-gateway/fallbacks.md)
>
> Fallback between providers and models for resilience

> [card] [Conditional Routing](https://docs.portkey.ai/docs/product/ai-gateway/conditional-routing.md)
>
> Route to different targets based on custom conditional checks

> [card] [Multimodality](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities.md)
>
> Use vision, audio, image generation, and more models

> [card] [Automatic Retries](https://docs.portkey.ai/docs/product/ai-gateway/automatic-retries.md)
>
> Setup automatic retry strategies

> [card] [Circuit Breaker](https://docs.portkey.ai/docs/product/ai-gateway/circuit-breaker.md)
>
> Configure per-strategy circuit protection and failure handling

> [card] [Load Balancing](https://docs.portkey.ai/docs/product/ai-gateway/load-balancing.md)
>
> Load balance between various API Keys to counter rate-limits

> [card] [Canary Testing](https://docs.portkey.ai/docs/product/ai-gateway/canary-testing.md)
>
> Canary test new models in production

> [card] [gRPC (Beta)](https://docs.portkey.ai/docs/product/ai-gateway/grpc.md)
>
> Use gRPC transport for lower latency and efficient binary serialization

> [card] [Request Timeout](https://docs.portkey.ai/docs/product/ai-gateway/request-timeouts.md)
>
> Easily handle unresponsive LLM requests

> [card] [Budget Limits](https://docs.portkey.ai/docs/product/model-catalog/integrations.md#3-budget-%26-rate-limits)
>
> Set usage limits based on costs incurred or tokens used

> [card] [Rate Limits](https://docs.portkey.ai/docs/product/model-catalog/integrations.md#3-budget-%26-rate-limits)
>
> Set hourly, daily, or per minute rate limits on requests or tokens sent

> [card] [Custom Hosts](https://docs.portkey.ai/docs/product/ai-gateway/custom-hosts.md)
>
> Route requests to privately hosted or local models using custom host URLs

> [card] [Gateway to other APIs](https://docs.portkey.ai/docs/api-reference/inference-api/gateway-for-other-apis.md)
>
> Call rerank, video, listen, and other provider paths through [https://api.portkey.ai/v1/](https://api.portkey.ai/v1/)... with the same configs and logging as unified routes

## Using the Gateway

The various gateway strategies are implemented using Gateway configs. You can read more about configs below.

> [card] [Configs](https://docs.portkey.ai/docs/product/ai-gateway/configs.md)

## Open Source

We've open sourced our battle-tested AI gateway to the community. You can run it locally with a single command:

```sh theme={"system"}
npx @portkey-ai/gateway
```

[**Contribute here**](https://github.com/portkey-ai/gateway).

While you're here, why not [give us a star](https://git.new/ai-gateway-docs)? It helps us a lot!

![](https://mintcdn.com/portkey-docs/VWP2Y8zxPP5N4jE6/images/product/ai-gateway/ai-10-gateway.png?fit=max\&auto=format\&n=VWP2Y8zxPP5N4jE6\&q=85\&s=74d524a588b870420b7de2f13a1267e3)

You can also [self-host](https://github.com/Portkey-AI/gateway/blob/main/docs/installation-deployments.md) the gateway and then connect it to Portkey. Please reach out on [hello@portkey.ai](mailto:hello@portkey.ai) and we'll help you set this up!

***

> [card] [Portkey is now PRISMA AIRS AI Gateway. See it in action.](https://www.paloaltonetworks.in/ai-security/ai-gateway?utm_source=portkey\&utm_medium=referral\&utm_campaign=prisma_airs\&utm_content=docs_nav#contact)
>
> Contact Us


## Related topics

- [Gateway Compatibility](https://docs.portkey.ai/docs/integrations/libraries/claude-code-gateway-compatibility.md)
- [Getting Started with AI Gateway](https://docs.portkey.ai/docs/guides/getting-started/getting-started-with-ai-gateway.md)
- [Mistral AI](https://docs.portkey.ai/docs/integrations/llms/mistral-ai.md)
- [Reka AI](https://docs.portkey.ai/docs/integrations/llms/reka-ai.md)
- [Together AI](https://docs.portkey.ai/docs/integrations/llms/together-ai.md)


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