Tencent WorkBuddy International announced on November 15 that it has officially integrated Google's Gemini4Carbon large model, providing model support for complex reasoning and long-horizon task processing scenarios. It is currently available only to Pro plan users.
Gemini4Carbon is a model launched by Google for long-horizon agentic workflows, suitable for tasks such as complex knowledge work, software engineering, cybersecurity, and scientific reasoning. The model supports multimodal inputs including text, images, audio, and video, and its combined input and output context window can reach up to 1 million tokens, enabling it to handle workflows with large amounts of information and long task chains.
After this integration, WorkBuddy Pro users can directly call Gemini4Carbon within the platform, without having to access it only through Google's own products. However, Tencent has not yet announced the specific usage quota and restrictions for the model within WorkBuddy.
Previously, WorkBuddy had successively integrated models such as Kimi-K3.1-Pro that support a 1-million-token context. The introduction of Gemini4Carbon further enriches the platform's model options and reflects how AI office products are improving complex task processing and agentic workflow support by integrating large model capabilities from different vendors.


