Sold by: Code CreatorÂ
Deployed on AWS
This product has charges associated with it for the provision and deployment of the application and AMI support. Launch a private AI chat server in your own AWS account using GPT OS with Ollama and Open WebUI. Keep data private, use your GPU for fast responses, and start chatting in minutes.
Overview
This is a repackaged open source software product wherein additional charges are applied for the deployment of the application and AMI support and compliance. Private AI Chat Server GPT OS gives you a complete self hosted chat assistant that runs inside your AWS environment. It combines Open WebUI for a polished chat experience, Ollama for local model serving, Qdrant for vector search, and Nginx for a friendly landing page. Your prompts and responses stay on your instance for maximum privacy and control.
On first launch you create the admin account and can begin chatting right away. The default model is GPT OS twenty billion served by Ollama with GPU acceleration for strong performance. You can add more models, adjust system prompts, raise or lower maximum tokens, and tune generation settings from the Settings menu. A built in smoke test confirms that containers, GPU access, and the model endpoint are healthy. Most users will be ready to go after a short warm up period.
This image is ideal for teams that need a private assistant for knowledge work, prototyping, or internal tools without sending data to external services. It is designed for NVIDIA GPU instances such as the g5 family and supports persistence across reboots. The result is a fast and flexible chat server that you control end to end.
Highlights
- Private by default All chat data stays on your AWS instance with no third party data sharing. You control access, users, and retention.
- Fast and capable GPU acceleration on g5 instances with a tuned 20B model served by Ollama for quick, high quality responses.
- Simple to launch and manage One click start, a built in smoke test, and Open WebUI for easy model selection and settings like max tokens and temperature.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 22.04
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g5.2xlarge Recommended | $0.02 |
g5.16xlarge | $0.02 |
g5.24xlarge | $0.02 |
g5.12xlarge | $0.02 |
g5.8xlarge | $0.02 |
g5.4xlarge | $0.02 |
g5.xlarge | $0.02 |
g5.48xlarge | $0.02 |
Vendor refund policy
No contracts. We do not currently support refunds, but you can cancel at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
n/a
Additional details
Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Netskope Private Access Publisher
By Netskope
The Netskope Private Access publisher AMI enables Netskope to discover local resources that remote users will connect to.
Zscaler Private Access Connector
By Zscaler, Inc.
ZPA Connectors provide the secure authenticated interface between a customer's servers and the Zscaler Private Access cloud.
App Connectors can be deployed in several forms. Zscaler distributes a standard virtual machine (VM) image for deployment in enterprise data centers, local private cloud environments such as VMware, or public cloud environments such as Amazon Web Services (AWS) EC2. Additionally, Zscaler provides packages that can be installed on supported Linux distributions.
Connectors can be co-located with your enterprise applications, or they can be deployed in any location that has connectivity to the applications. Typically, they are deployed on network segments that can access secured applications and the ZPA cloud simultaneously, such as in a DMZ. Connectors only connect outbound; they do not need any inbound open ports to operate correctly.
Zscaler Private Access Service Edge
By Zscaler, Inc.
The ZPA Private Service Edges are brokers that are a single-tenant instance that provide the functionality of a ZPA Public Service Edge in an organization's environment. Your organization hosts them either within your site or on a cloud service, but Zscaler manages them. On the other hand, ZPA Public Service Edges are deployed in Zscaler data centers around the world.
As with a ZPA Public Service Edge, a ZPA Private Service Edge manages the connections between Zscaler Client Connector and App Connectors. It registers with the ZPA Cloud. This allows a ZPA Private Service Edge to download the relevant policies and configurations so it can enforce all ZPA policies. It also caches path selection decisions.
ZPA Private Service Edges can be deployed in several forms. Zscaler distributes images for deployment in enterprise data centers and local private cloud environments such as VMware.
Usage Engine Private Edition
By DigitalRoute
Usage Engine Private Edition is a vendor-agnostic usage data management software that enables companies to unlock the value of their service usage data to optimize business efficiency and increase customer experience. It is fast to deploy in a private or public cloud, with the flexibility to provide timely, accurate data into revenue operations and billing, customer success, and product management teams. This means you can speed up invoicing, improve customer experiences, prevent revenue leakage, and reduce time spent on IT maintenance. It is built to be operated on Kubernetes and serves communications service providers and large enterprise companies across industry verticals, particularly those with in-house IT departments, and offering subscription-based services.
Entra Private Network Connector
By Microsoft Private Network Connector
Microsoft Entra Private Network Connector | Solution template to deploy a virtual machine with a pre-installed Microsoft Entra Private Network Connector.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.