Announcing the general availability of Llama 4 as MaaS on Vertex AI- Google Developers Blog

This post announces the general availability of Llama 4 and Llama 3.3 70B as managed API endpoints on Vertex AI. It highlights the benefits of using these models as Model-as-a-Service (MaaS), including zero infrastructure management, guaranteed performance, and enterprise-grade security. It provides a Python code example using the OpenAI library to interact with the Llama 4 MaaS endpoint via the ChatCompletion API, demonstrating multimodal requests with image input from Cloud Storage. The post also touches upon cost and quota considerations for using these models on Vertex AI.