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

# Migrating from LiteLLM

> Step-by-step guide to migrate your LiteLLM integration to AI Stats Gateway.

# Migrating from LiteLLM

This guide helps migrate from LiteLLM proxy to AI Stats Gateway.

## Overview

Both provide unified API access. Migration involves:

* Changing base URL
* Updating API key
* Adjusting model names

## Prerequisites

* AI Stats account
* LiteLLM setup

## Migration Steps

### 1. Update Configuration

Replace LiteLLM URL with AI Stats.

<CodeGroup>
  ```bash theme={null}
  # Before (LiteLLM proxy)
  curl http://localhost:8000/v1/chat/completions \
    -H "Authorization: Bearer your-litellm-key" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-4",
      "messages": [{"role": "user", "content": "Hello!"}]
    }'

  # After (AI Stats)

  curl https://api.phaseo.app/v1/chat/completions \
   -H "Authorization: Bearer your-ai-stats-key" \
   -H "Content-Type: application/json" \
   -d '{
  "model": "gpt-4",
  "messages": [{"role": "user", "content": "Hello!"}]
  }'

  ```

  ```python theme={null}
  import openai

  # Before
  client = openai.OpenAI(
      api_key="your-litellm-key",
      base_url="http://localhost:8000/v1"  # LiteLLM proxy
  )

  # After
  client = openai.OpenAI(
      api_key="your-ai-stats-key",
      base_url="https://api.phaseo.app/v1"
  )

  response = client.chat.completions.create(
      model="gpt-4",
      messages=[{"role": "user", "content": "Hello!"}]
  )
  ```

  ```javascript theme={null}
  import OpenAI from "openai";

  // Before
  const client = new OpenAI({
  	apiKey: "your-litellm-key",
  	baseURL: "http://localhost:8000/v1",
  });

  // After
  const client = new OpenAI({
  	apiKey: "your-ai-stats-key",
  	baseURL: "https://api.phaseo.app/v1",
  });

  const response = await client.chat.completions.create({
  	model: "gpt-4",
  	messages: [{ role: "user", content: "Hello!" }],
  });
  ```
</CodeGroup>

### 2. Model Names

LiteLLM uses provider/model format. AI Stats may use different names.

Check `/gateway/models` for available models.

### 3. Test

Run your code to ensure compatibility.

## Common Issues

* **Model support**: Not all LiteLLM models may be in AI Stats.
* **Features**: Some LiteLLM features may differ.

## Next Steps

* Use AI Stats' built-in analytics.