# Quickstart: OpenAI-compatible inference with Atlas Cloud > Point your existing OpenAI SDK at Atlas Cloud by changing the base URL and API key — no code rewrite needed. --- Atlas Cloud exposes a single **OpenAI-compatible** endpoint, so any client or framework that already speaks the OpenAI API works unchanged. ## 1. Set your base URL and key ```bash export OPENAI_BASE_URL="https://api.atlascloud.ai/v1" export OPENAI_API_KEY="sk-atlas-..." ``` ## 2. Call any supported model ```python from openai import OpenAI client = OpenAI() # picks up OPENAI_BASE_URL + OPENAI_API_KEY resp = client.chat.completions.create( model="deepseek-v3", messages=[{"role": "user", "content": "Explain serverless inference."}], ) print(resp.choices[0].message.content) ``` That is the entire integration. Because the wire format matches OpenAI, tools like LangChain, LlamaIndex, and the Vercel AI SDK work out of the box. ## FAQ ### Which models are available? Open-source and frontier models including DeepSeek-V3, Llama 3, Qwen, GLM, and Mistral, served through one unified API. ### Do I need to change my code to use Atlas Cloud? No. Atlas Cloud is OpenAI-compatible — set the base URL to https://api.atlascloud.ai/v1 and use your Atlas Cloud API key.