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

# API Reference

> Reference documentation for using the OpenAI‑compatible proxy with LLMGrid.

# OpenAI Compatible Proxy: API Reference

LLMGrid provides an **OpenAI‑compatible proxy**, allowing you to use existing OpenAI SDKs and tooling without changing your application logic.

To use LLMGrid, simply replace the `base_url` in your SDK configuration with your LLMGrid proxy endpoint.

***

## Compatibility Overview

The LLMGrid proxy is fully compatible with the OpenAI API surface, including:

* Chat completions
* Embeddings
* Streaming responses
* Tool / function calling
* SDK‑based clients

This enables seamless integration with:

* OpenAI SDKs
* Popular orchestration frameworks
* Custom applications built on OpenAI‑style APIs

***

## SDK Examples

### OpenAI Python SDK

```python theme={null}
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LLMGRID_API_KEY",
    base_url="https://<your-llmgrid-proxy>"
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "user", "content": "Explain retrieval‑augmented generation"}
    ]
)

print(response.choices[0].message.content)
```