> ## 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.

# Portkey Features

> Explore the powerful features of Portkey

## AI Gateway

Connect to 250+ AI models using a single consistent API. Set up load balancers, automated fallbacks, caching, conditional routing, and more, seamlessly.

> [card] [🌐 Universal API](https://docs.portkey.ai/docs/product/ai-gateway/universal-api.md)
>
> Integrate with multiple AI models through a single API

> [card] [💾 Caching](https://docs.portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic.md)
>
> Implement simple and semantic caching for improved performance

> [card] [🔄 Fallbacks](https://docs.portkey.ai/docs/product/ai-gateway/fallbacks.md)
>
> Set up automated fallbacks for enhanced reliability

> [card] [🔀 Multimodal Capabilities](https://docs.portkey.ai/docs/product/ai-gateway/multimodal-capabilities.md)
>
> Handle various data types with multimodal AI capabilities

> [card] [🔁 Automatic Retries](https://docs.portkey.ai/docs/product/ai-gateway/automatic-retries.md)
>
> Implement automatic retries for improved resilience

> [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)
>
> Distribute workload efficiently across multiple models

> [card] [🔑 Integrations](https://docs.portkey.ai/docs/product/integrations)
>
> Manage access to LLMs

> [card] [⏱️ Request Timeouts](https://docs.portkey.ai/docs/product/ai-gateway/request-timeouts.md)
>
> Set and manage request timeouts

> [card] [🐤 Canary Tests](https://docs.portkey.ai/docs/product/ai-gateway/canary-testing.md)
>
> Implement canary testing for safe deployments

> [card] [🚦 Conditional Routing](https://docs.portkey.ai/docs/product/ai-gateway/conditional-routing.md)
>
> Route requests based on specific conditions

> [card] [💳 Budget Limits](https://docs.portkey.ai/docs/product/model-catalog/budget-limits.md)
>
> Set and manage budget limits

## Observability & Logs

Gain real-time insights, track key metrics, and streamline debugging with our OpenTelemetry-compliant system.

> [card] [📜 Logs](https://docs.portkey.ai/docs/product/observability/logs.md)
>
> Access and analyze detailed logs

> [card] [🕵️ Tracing](https://docs.portkey.ai/docs/product/observability/traces.md)
>
> Implement distributed tracing for request flows

> [card] [📊 Analytics](https://docs.portkey.ai/docs/product/observability/analytics.md)
>
> Gain insights through comprehensive analytics

> [card] [🧪 Filters](https://docs.portkey.ai/docs/product/observability/filters.md)
>
> Apply filters for targeted analysis

> [card] [🏷️ Metadata](https://docs.portkey.ai/docs/product/observability/metadata.md)
>
> Manage and utilize metadata effectively

> [card] [💬 Feedback](https://docs.portkey.ai/docs/product/observability/feedback.md)
>
> Collect and analyze user feedback

## Prompt Library

Collaborate with team members to create, templatize, and version prompt templates easily. Experiment across 250+ LLMs with a strong Publish/Release flow to deploy the prompts.

> [card] [🧩 Prompt Templates](https://docs.portkey.ai/docs/product/prompt-library/prompt-templates.md)
>
> Create and manage reusable prompt templates

> [card] [✂️ Prompt Partials](https://docs.portkey.ai/docs/product/prompt-library/prompt-partials.md)
>
> Utilize modular prompt components

> [card] [\{ } JSON Mode Prompting](https://docs.portkey.ai/docs/product/prompt-library/advanced-prompting-with-json-mode.md)
>
> Advanced prompting with JSON mode

## Guardrails

Enforce Real-Time LLM Behavior with 50+ state-of-the-art AI guardrails, so that you can synchronously run Guardrails on your requests and route them with precision.

> [card] [🛡️ Deterministic Guardrails](https://docs.portkey.ai/docs/product/guardrails/list-of-guardrail-checks.md)
>
> Implement rule-based safety checks

> [card] [🤖 LLM-based Guardrails](https://docs.portkey.ai/docs/product/guardrails/list-of-guardrail-checks.md)
>
> Leverage AI for advanced content filtering

> [card] [🤝 Partner Guardrails](https://docs.portkey.ai/docs/product/guardrails/list-of-guardrail-checks.md)
>
> Integrate third-party safety solutions

> [card] [🎒 Bring Your Own](https://docs.portkey.ai/docs/integrations/guardrails/bring-your-own-guardrails.md)
>
> Customize guardrails to your needs

## Agents

Natively integrate Portkey's gateway, guardrails, and observability suite with leading agent frameworks and take them to production.

> [card] [🤖 Autogen](https://docs.portkey.ai/docs/integrations/agents/autogen.md)

> [card] [👥 CrewAI](https://docs.portkey.ai/docs/integrations/agents/crewai.md)

> [card] [🔗 Langchain Agents](https://docs.portkey.ai/docs/integrations/agents/langchain-agents.md)

> [card] [🦙 Llama Agents](https://docs.portkey.ai/docs/integrations/agents/llama-agents.md)

> [card] [φ PhiData](https://docs.portkey.ai/docs/integrations/agents/phidata.md)

> [card] [🔀 ControlFlow](https://docs.portkey.ai/docs/integrations/agents/control-flow.md)

> [card] [🕸️ LangGraph](https://docs.portkey.ai/docs/integrations/agents/langgraph.md)

## More Resources

> [card] [📋 Portkey Plans](https://docs.portkey.ai/docs/product/product-feature-comparison.md)
>
> Compare different Portkey subscription plans

> [card] [💬 Developer Forum](https://docs.portkey.ai/docs/support/developer-forum.md)
>
> Join our community of developers

> [card] [📚 API Reference](https://docs.portkey.ai/docs/api-reference)
>
> Explore our comprehensive API documentation

> [card] [🏢 Portkey Enterprise](https://docs.portkey.ai/docs/product/enterprise-offering.md)
>
> Learn about our enterprise solutions

> [card] [🌐 Portkey Open Source](https://docs.portkey.ai/docs/product/open-source.md)
>
> Contribute to our open-source projects

***

> [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

- [Optimizing Prompts for Customer Support using Portkey | LLama Prompt Ops Integration](https://docs.portkey.ai/docs/guides/prompts/llama-prompts.md)
- [Instructor](https://docs.portkey.ai/docs/integrations/libraries/instructor.md)
- [Jan](https://docs.portkey.ai/docs/integrations/libraries/janhq.md)
- [Langflow](https://docs.portkey.ai/docs/integrations/libraries/langflow.md)
- [LibreChat](https://docs.portkey.ai/docs/integrations/libraries/librechat.md)


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