Announcing the general availability of Llama 4 MaaS on Vertex AI [English]

Source: developers.googleblog.com | Author: Unattributed | Read the full article in English

Google has just made a significant announcement in the world of artificial intelligence by introducing Llama 4 as a fully managed service through Vertex AI. This new development simplifies the complex process of deploying and managing advanced language models for developers and businesses. Instead of struggling with technical infrastructure and GPU management, users can now access powerful AI capabilities more easily than ever before.

Llama 4 represents a major leap forward in AI technology, offering two distinct model versions: Scout and Maverick. The Scout version is designed to be powerful yet efficient, capable of running on a single GPU, while the Maverick model is the most advanced option, specializing in complex reasoning and image understanding tasks. These models are part of Meta's latest generation of open large language models, now available through Google's cloud platform.

The integration of Llama 4 into Vertex AI's Model Garden means developers now have access to a wide range of foundation models from different sources. This expansion provides more flexibility and options for creating sophisticated AI-powered applications. By offering Llama 4 as a managed API endpoint, Google is making cutting-edge AI technology more accessible, allowing developers to focus on building innovative solutions rather than managing complex technical infrastructure.

Read More (translated)