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

# LiteLLM

> Langtrace and LiteLLM Integration Guide

Langtrace integrates directly with LiteLLM, offering detailed, real-time insights into performance metrics such as cost, token usage, accuracy, and latency.
<Note>You'll need API key from Langtrace. Sign up for [Langtrace](https://langtrace.ai) if you haven't done so already.\*</Note>

## LiteLLM SDK

1. Setup environment variables:

```bash Shell theme={null}
export LANGTRACE_API_KEY=YOUR_LANGTRACE_API_KEY
```

2. Add callback to your LiteLLM client

```python main.py theme={null}
import litellm
litellm.success_callback = ['langtrace']
```

3. Use LiteLLM completion

```python main.py theme={null}
from litellm import completion

response = completion(
    model="gpt-4",
    messages=[
        {"role": "user", "content": "this is a test request, write a short poem"}
    ],
)
print(response)
```

## LiteLLM Proxy

1. Create `config.yaml`:

```yaml config.yaml theme={null}
model_list:
  - model_name: gpt-4
    litellm_params:
      model: openai/gpt-4

litellm_settings:
  callbacks: ["langtrace"]

environment_variables:
  LANGTRACE_API_KEY: <YOUR_LANGTRACE_API_KEY>
```

2. Run LiteLLM Proxy

```bash Shell theme={null}
litellm --config config.yaml --detailed_debug
```

3. Test your setup

<CodeGroup>
  ```bash Curl theme={null}
  curl --location 'http://0.0.0.0:4000/chat/completions' \
      --header 'Content-Type: application/json' \
      --data ' {
      "model": "gpt-4",
      "messages": [
          {
          "role": "user",
          "content": "what llm are you"
          }
      ]
      }'
  ```

  ```python OpenAI v1.0.0+ theme={null}
  import openai

  client = openai.OpenAI(base_url="http://0.0.0.0:4000", api_key="YOUR_OPENAI_API_KEY")
  response = client.chat.completions.create(
      model="gpt-4",
      messages=[
          {"role": "user", "content": "this is a test request, write a short poem"}
      ],
  )
  print(response)
  ```
</CodeGroup>

You can now view your traces on the Langtrace dashboard

<img src="https://mintcdn.com/langtraceai-2/m7BVnnhK3Cx2yRxS/images/litellm.png?fit=max&auto=format&n=m7BVnnhK3Cx2yRxS&q=85&s=9faa70b45a5a2af61d739f60193d8f50" alt="traces" width="2886" height="1766" data-path="images/litellm.png" />

Want to see more supported methods? Checkout the sample code in the [Langtrace Langchain Python Example](https://python.langchain.com/docs/get_started/installation/)