Mercury and Mercury Coder are now available on Amazon Bedrock and SageMaker JumpStart!
These services enable you to deploy Mercury models at scale in a robust, secure environment.
1. Data Security: Bedrock lets your services connect to Mercury models while ensuring your data stays within your virtual private cloud (VPC), ensuring that no one outside your organization has access to it.
2. Compliance: Bedrock also adheres to a comprehensive set of industry compliance standards, including GDPR, HIPAA, and SOC 2, ensuring your deployments meet stringent regulatory requirements.
3. Unified API: Access Mercury models alongside a wide array of other Bedrock foundation models through a single, consistent API, simplifying development and integration.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Mercury is reachable through Bedrock's unified API and batch endpoints, so teams barred from third-party inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → endpoints on data residency or compliance grounds can now evaluate a diffusion LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →.
