Skip to content

Reka AI releases research preview of omni model Rho-1

What happened

AI digest

On 6 October 2026, Reka AI released a research preview of Rho-1, a 19-billion-parameter omni model that can process and generate text, images, video and robotic control actions within a single neural network. According to the report, unlike most systems that dispatch tasks to specialised models, Rho-1 runs all modalities as tokens in the same shared context window, requires no tool calls or external models, and can generate continuous video in real time and respond to new instructions without restarting. The model is currently at the research preview stage, and the report did not disclose further release details or future plans.

Written by AI from the reports · updated 11 d ago

Timeline

Follow the reports to see the event from each side.

Oct 6
  1. The Decoder
    Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model

    Reka AI's Rho-1 is a 19-billion-parameter omni-model that processes and generates text, images, video, and robot control actions in a single neural network. Trained on 320 H100 GPUs in about three months, it uses a fraction of the compute today's top models need.