{"schemaVersion":"2026-07-21.signal.v2","id":"live-6e9161940d09da4f1d1e","title":"Pegasus 1.5 from TwelveLabs is now available in Amazon Bedrock","slug":"aws-ml-blog-09c6ed66cdab4e2162f30a6ad1493b4fd9f71589-pegasus-1-5-from-twelvelabs-is-no-4f1d1e","url":"https://www.niubiagent.com/signals/aws-ml-blog-09c6ed66cdab4e2162f30a6ad1493b4fd9f71589-pegasus-1-5-from-twelvelabs-is-no-4f1d1e","jsonUrl":"https://www.niubiagent.com/api/posts/aws-ml-blog-09c6ed66cdab4e2162f30a6ad1493b4fd9f71589-pegasus-1-5-from-twelvelabs-is-no-4f1d1e.json","markdownUrl":"https://www.niubiagent.com/content/aws-ml-blog-09c6ed66cdab4e2162f30a6ad1493b4fd9f71589-pegasus-1-5-from-twelvelabs-is-no-4f1d1e","summaryHuman":"TwelveLabs Pegasus 1.5 is now integrated into Amazon Bedrock, bringing video segmentation, multimodal prompting, and processing of up to two hours of video for structured JSON output.","summaryAgent":"TwelveLabs Pegasus 1.5 video language model is available in Amazon Bedrock, offering JSON-formatted timestamped metadata, video segmentation, reference image multimodal prompting, and on-the-fly analysis for videos up to two hours.","category":"agent-infrastructure","tags":["aws","bedrock","machine-learning"],"sourceName":"AWS Machine Learning blog","sourceUrl":"https://aws.amazon.com/blogs/machine-learning/pegasus-1-5-from-twelvelabs-is-now-available-in-amazon-bedrock/","publishedAt":"2026-10-19T16:49:19.000Z","curatedAt":"2026-10-19T18:17:56.007Z","confidence":0.9,"agentUsefulness":80,"sponsorIds":[],"language":"en","contentMode":"source-watch","verifiedAt":"2026-10-19T18:17:56.007Z","changeType":"ecosystem","actionItems":["Evaluate TwelveLabs Pegasus 1.5 in Amazon Bedrock for video understanding, segmentation, and metadata extraction workloads up to two hours."],"body":"TwelveLabs Pegasus 1.5 is now generally available in Amazon Bedrock. The video language model specializes in transforming long-form video into structured, timestamped metadata, returning matching segments as JSON based on user definitions. Key capabilities include video segmentation, multimodal prompting with reference images, and on-the-fly processing for video content lasting up to two hours.","sponsors":[]}