> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LiteLLM

> Run agents through the LiteLLM gateway with tools, knowledge, structured output, and audio, image, and PDF input.

| Example | Description |
| - | - |
| [LiteLLM Audio Input Agent](https://agno-v2.mintlify.site/examples/models/litellm/audio-input-agent.md) | Pass an MP3 file as audio input to a gpt-audio model routed through LiteLLM. |
| [LiteLLM Basic](https://agno-v2.mintlify.site/examples/models/litellm/basic.md) | Run a Hugging Face Mistral model through LiteLLM with sync, async, and streaming calls. |
| [LiteLLM Basic GPT](https://agno-v2.mintlify.site/examples/models/litellm/basic-gpt.md) | Call OpenAI's gpt-4o through the LiteLLM model class for a basic agent response. |
| [DB](https://agno-v2.mintlify.site/examples/models/litellm/db.md) | Add storage to the Agent. |
| [LiteLLM Image Agent](https://agno-v2.mintlify.site/examples/models/litellm/image-agent.md) | Analyze an image from a URL with gpt-4o via LiteLLM and pull related news using web search. |
| [LiteLLM Image Agent Bytes](https://agno-v2.mintlify.site/examples/models/litellm/image-agent-bytes.md) | Send an image as raw bytes to gpt-4o via LiteLLM and fetch related news with web search. |
| [LiteLLM Knowledge](https://agno-v2.mintlify.site/examples/models/litellm/knowledge.md) | Answer questions from a PDF knowledge base stored in PgVector using a LiteLLM agent. |
| [LiteLLM Memory](https://agno-v2.mintlify.site/examples/models/litellm/memory.md) | Keep the last three runs in context and inspect stored session messages with a LiteLLM agent. |
| [LiteLLM Metrics](https://agno-v2.mintlify.site/examples/models/litellm/metrics.md) | Inspect per-message and run-level token metrics from a LiteLLM agent using YFinance tools. |
| [LiteLLM PDF Input Bytes](https://agno-v2.mintlify.site/examples/models/litellm/pdf-input-bytes.md) | Pass a downloaded PDF as raw bytes to a LiteLLM agent and summarize its contents. |
| [LiteLLM PDF Input Local](https://agno-v2.mintlify.site/examples/models/litellm/pdf-input-local.md) | Attach a local PDF file to a LiteLLM agent and ask questions about a specific recipe. |
| [LiteLLM PDF Input URL](https://agno-v2.mintlify.site/examples/models/litellm/pdf-input-url.md) | Attach a PDF by URL to a LiteLLM agent and ask for a recipe from the document. |
| [LiteLLM Reasoning Agent Example](https://agno-v2.mintlify.site/examples/models/litellm/reasoning-agent.md) | Use reasoning models through LiteLLM. |
| [Retry](https://agno-v2.mintlify.site/examples/models/litellm/retry.md) | Review retry settings and why invalid model IDs cannot reliably exercise the retry path. |
| [LiteLLM Structured Output](https://agno-v2.mintlify.site/examples/models/litellm/structured-output.md) | Return a MovieScript Pydantic model via LiteLLM using JSON mode and native structured outputs. |
| [LiteLLM Tool Use](https://agno-v2.mintlify.site/examples/models/litellm/tool-use.md) | Call YFinance tools from a LiteLLM agent with sync, streaming, and async runs. |
| [LiteLLM Append Trailing User Message](https://agno-v2.mintlify.site/examples/models/litellm/append-trailing-user-message.md) | Append a trailing user turn so Claude 4.6+ models that reject assistant prefill work through LiteLLM. |


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