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

# LiteLLM observability

> Trace LiteLLM calls to any model it routes to with one integration: prompts, token usage, cost, and latency in Tracevell's transcript view.

## Overview

[LiteLLM](https://www.litellm.ai/) is a framework/library for building LLM applications that simplifies accessing many models across different providers.

## Default configuration

**1. Ensure you have the latest version of Tracevell**

```sh theme={null}
pip install -U 'lmnr[all]'
```

**2. Initialize Tracevell**

Tracevell auto-instruments LiteLLM. No callback is required.

```python theme={null}
import os
import litellm
from lmnr import Tracevell

Laminar.initialize(project_api_key=os.environ["LMNR_PROJECT_API_KEY"])
```

> [!NOTE]
>
> `LaminarLiteLLMCallback` is deprecated and does nothing. Remove it if you already use it.

**3. Run your code and see traces in Tracevell**

Example code:

```python theme={null}
import os
import litellm
from lmnr import Tracevell

Laminar.initialize(project_api_key=os.environ["LMNR_PROJECT_API_KEY"])

response = litellm.completion(
    model="gpt-5-nano",
    messages=[
      {"role": "user", "content": "What is the capital of France?"}
    ],
)
```

![LiteLLM trace](https://mintcdn.com/laminarai/W6ojRY5YjRjfXRin/images/traces/litellm.png?fit=max\&auto=format\&n=W6ojRY5YjRjfXRin\&q=85\&s=4a82323756cd93c5ba0e7919cf30cf4e)

## Related integrations

> [card] [OpenAI](https://tracevell.com/docs/integrations/openai.md)
>
> Trace the OpenAI SDK directly in TypeScript and Python.

> [card] [Anthropic](https://tracevell.com/docs/integrations/anthropic.md)
>
> Trace the Anthropic SDK directly in TypeScript and Python.

> [card] [OpenRouter](https://tracevell.com/docs/integrations/openrouter.md)
>
> Trace OpenRouter requests with model and cost attribution.

> [card] [TypeSafe AI](https://tracevell.com/docs/integrations/typesafe.md)
>
> Trace typed Jev decisions: routing, guardrails, and scoring.

> [card] [LangChain / LangGraph](https://tracevell.com/docs/integrations/langchain.md)
>
> Trace LangChain chains and LangGraph graphs.

> [card] [All integrations](https://tracevell.com/docs/integrations.md)
>
> Browse every provider, framework, coding agent, and browser integration Tracevell supports.


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