Google Gemini 3.1 Pro Expands Preview Access Across Consumer, Developer and Enterprise Tools

Google has announced Gemini 3.1 Pro , a new preview model positioned as a substantial upgrade to the Gemini family for complex tasks. Introduced on February 19, 2026, the model is rolling out across Google's consumer products, developer environments and enterprise platforms, making the release a platform-wide expansion rather than an isolated model update. Google's official Gemini 3.1 Pro announcement describes upgraded core intelligence intended to serve all three audiences. The most consequential part of the announcement is the model's distribution. Developers, enterprises and end users are being offered access through distinct Google products, while Google frames Gemini 3.1 Pro as a step toward more capable agentic workflows . General availability is planned after the preview phase, with broader availability described as coming soon. A broader Gemini 3.1 Pro rollout Google says Gemini 3.1 Pro is designed to be smarter at complex tasks, with improved reasoning as a central focus. The company highlighted a 77.1% score on ARC-AGI-2 , a benchmark it cited as evidence of the model's reasoning progress. That result is a company-reported benchmark figure, not a complete measure of how the model will perform in every production workflow. The release follows earlier Gemini family progress, including Gemini 3 Pro and Gemini 3 Deep Think. However, the announcement's practical message is not limited to a new model name or benchmark. Google is placing Gemini 3.1 Pro into the tools through which people build, deploy and use AI systems. Audience Announced access points Rollout status Developers Gemini API in Google AI Studio, Gemini CLI, Antigravity and Android Studio Preview Enterprises Vertex AI and Gemini Enterprise Preview Consumers Gemini app and NotebookLM Preview rollout What the multi-channel release means A model can matter strategically only if it reaches the environments where work happens. By making Gemini 3.1 Pro available through the Gemini API and development too