Doubao

ByteDance · May 2024

activeClosedmultimodalAPI Available

Description

ByteDance's flagship multimodal AI model powering their consumer-facing AI products. Features strong tool-use capabilities and multimodal understanding, integrated across ByteDance's ecosystem of apps including Douyin (TikTok China).

Key Innovations

Multimodal
MultimodalProcessing multiple types of input (text, images, audio, video) in a single model.
Tool Use
Tool UseAbility to call external tools, APIs, and functions — enabling web browsing, code execution, and real-world actions.