Intel / post

Voyage embedding models deploy inside your own AWS VPC

Source: x.com
Date: Published Feb 17, 2026

🚀 Voyage AI models are on the @awscloud Marketplace! You can deploy Voyage 4 and voyage-multimodal-3.5 directly within your AWS VPC. Leverage your existing AWS credits and infrastructure to build high-performance RAG and agentic search systems. Full Data Privacy: Models run in your own account and VPC. Seamless Integration: Deploy as real-time inference endpoints via Amazon SageMaker. Unified Billing: One consolidated bill through your AWS account. Get started on AWS: https://t.co/VcYb58ooN7

Feb 17, 2026 View on X

Context

Voyage AI's Marketplace announcement gives developers a deployment option for Voyage 4 and voyage--3.5 inside their own AWS account and virtual private cloud. The model and software run there as a SageMaker endpoint, placing control over data flow and endpoint access within the customer's cloud environment.

This also changes the billing model. The deployment documentation describes hourly charges for both model software and the infrastructure running it. A persistent endpoint continues consuming resources while deployed, so keeping inference in one's own account comes with responsibility for managing that capacity.

Terms in this piece · Glossary

multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.

Read the source x.com