Amazon Bedrock introduces Global cross-Region inference for TwelveLabs’ Pegasus 1.2, expanding model availability to 23 new regions in addition to the seven regions where the model was already available. You can now also access the model in all EU regions in Amazon Bedrock using Geographic cross-Region inference. Geographic cross-Region inference is ideal for workloads with data residency or compliance requirements within a specific geographic boundary, while Global cross-Region inference is recommended for applications that prioritize availability and performance across multiple geographies.
Pegasus 1.2 is a powerful video-first language model that can generate text based on the visual, audio, and textual content within videos. Specifically designed for long-form video, it excels at video-to-text generation and temporal understanding. With Pegasus 1.2’s availability in these additional regions, you can now build video-intelligence applications closer to your data and end users, reducing latency and simplifying your architecture.
For a complete list of supported inference profiles and regions for Pegasus 1.2, refer to the Cross-Region Inference documentation. To get started with Pegasus 1.2, visit the Amazon Bedrock console. To learn more, read the product page and Amazon Bedrock documentation.
Categories: marketing:marchitecture/artificial-intelligence,general:products/amazon-bedrock
Source: Amazon Web Services
Latest Posts
- Amazon Bedrock expands Claude models in-region support in the UK (London)
- MC1483844: Microsoft Copilot Adds GPT-6.1 Sol and Claude Sonnet 5.5 Models Across Microsoft 365 Apps
- Workers – Web Crypto adds ML-KEM and ML-DSA support
- Durable Objects – Pending I/O operations allow Durable Objects to continue long-running work without a connected client
