At Reka, we develop multimodal AI models to make next-generation AI products possible—including AI agents that can see, hear, and speak. Today, we are excited to announce the release of an updated version of Reka Flash. Reka Flash is one of the few models publicly available that supports full interleaved multimodal inputs (text, image, video, audio) in a single model. It has 21 billion parameters with a context length of 128K. Reka Flash is available today on Reka Chat and Reka API. It can also be deployed on-premises or in a private cloud setting.

Unlock Your Multimodal Business Data with Reka and MongoDB

We’re releasing an open and hard evaluation suite for measuring progress of multimodal chat models.