Pegasus 1.5 from TwelveLabs is now available in Amazon Bedrock
TwelveLabs Pegasus 1.5 brings timestamped video segmentation to Amazon Bedrock
TwelveLabs' Pegasus 1.5 video language model is now available on Amazon Bedrock, introducing structured timestamped metadata extraction, multimodal prompting with reference images, and on-the-fly processing without pre-indexing. The model handles videos up to two hours long and returns JSON-structured segment data directly from S3. This signals accelerating enterprise adoption of video understanding as a managed cloud AI capability, reducing the friction of building video intelligence pipelines.