---
title: "Features"
url: "/docs/guides/"
canonical_url: "https://docs.litellm.ai/docs/guides/"
type: "docs"
last_updated: "2026-10-15"
summary: "Features are what LiteLLM does with your requests across providers: load balancing and fallbacks, streaming, tool calling, media input, prompt caching, and more. Most pages show the code for the Python SDK and the setup for the AI..."
related:
  - "/docs/proxy/lens/scalability"
  - "/docs/proxy/load_balancing"
---
# Features

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt

**Features** are what LiteLLM does with your requests across providers: load balancing and fallbacks, streaming, tool calling, media input, prompt caching, and more. Most pages show the code for the Python SDK and the setup for the AI Gateway. A feature that applies to one product only is in the section for that product.

> New to LiteLLM? Start with the [AI Gateway Quickstart](/docs/proxy/docker_quick_start) or the [Python SDK Quickstart](/docs/learn/sdk_quickstart).

- [Routing & Reliability](https://docs.litellm.ai/docs/proxy/load_balancing): Load balancing, fallbacks, client-side fallbacks, timeouts, and routing rules.
- [Requests & Responses](https://docs.litellm.ai/docs/guides/core_request_response_patterns): Streaming, batching, structured outputs, and reasoning.
- [Tool Calling](https://docs.litellm.ai/docs/guides/tools_integrations): Function calling, web search and fetch, computer use, code interpreter, and knowledge bases.
- [Multimodal](https://docs.litellm.ai/docs/guides/multimodal_io): Vision, audio, PDF input, and image generation in chat.
- [Prompts & Context](https://docs.litellm.ai/docs/guides/prompts_context): Prompt caching, assistant prefill, and predicted outputs.
- [Compatibility](https://docs.litellm.ai/docs/guides/compatibility_extensibility): Provider-specific params, unsupported params, and message sanitization.

## Other pages that were here

[Retries and fallbacks](/docs/completion/reliable_completions), [mock responses](/docs/completion/mock_requests), [message trimming](/docs/completion/message_trimming), [model aliases](/docs/completion/model_alias), and [prompt formatting](/docs/completion/prompt_formatting) are in the [Python SDK](/docs/python_sdk) section. [SSL and HTTP proxy settings](/docs/guides/security_settings) are in the AI Gateway configuration pages, and [custom formats](/docs/extras/creating_adapters) are with the custom plugins. [Fine-tuned models](/docs/guides/finetuned_models) are with the providers, and [Veo video generation](/docs/proxy/veo_video_generation) is with the video endpoints.

## Related pages

- [Scalability design](https://docs.litellm.ai/docs/proxy/lens/scalability.md)
- [Load Balancing](https://docs.litellm.ai/docs/proxy/load_balancing.md)