Sold by: Software Sushi
Deployed on AWS
Open WebUI is a self-hosted, ChatGPT-style chat interface for any OpenAI-compatible model endpoint. Give your team one private place to chat with the models you choose. This Ubuntu 24.04 AMI runs Open WebUI v0.11.4 on localhost with a session secret generated per instance, reachable through Session Manager port forwarding.
Overview
Open WebUI v0.11.4 is a browser-based chat interface with conversations, user accounts and model selection that connects to any OpenAI-compatible API. This AMI is for teams that want a private chat front end in their own AWS account, pointed at the provider or gateway they already use.
What you get: Open WebUI in a non-root runtime listening on 127.0.0.1:8080, a fresh session secret generated on first boot (/etc/open-webui/webui.env, root-only), and persistent data under /var/lib/open-webui. No model weights, provider keys or user database are included. Local Ollama and CUDA bundles are not installed, so you connect an external OpenAI-compatible endpoint.
Getting started takes a few minutes: launch t3.large (8 GiB RAM, 32 GiB encrypted gp3 or larger), attach an instance profile with AmazonSSMManagedInstanceCore, allow outbound HTTPS and keep the security group free of inbound rules. Connect, run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh, then forward port 8080 and open that local address in your browser. Create your account right away: the first account becomes administrator. Then add your OpenAI-compatible base URL, API key and model IDs in the admin settings. The usage instructions and the linked project documentation cover each step.
Pricing: a software fee of USD 0.02 per running t3.medium instance-hour. An optional five-day free trial for one concurrent instance changes software billing only and then converts to the hourly fee; the same full software is installed before and after it. This is not a separate trial or evaluation edition, and there is no product-imposed time, user or usage limit. Additional concurrent instances incur software fees. EC2, EBS, data transfer and any model-provider charges are billed separately, including during the free trial.
This is a repackaged software product wherein additional charges apply for independent AWS packaging, maintenance and setup documentation. Open WebUI is provided under the Open WebUI License, including its branding conditions. Software Sushi supplies the AMI recipe and a separately derived runtime without claiming upstream endorsement. Back up /var/lib/open-webui together with /etc/open-webui.
Highlights
- A private, ChatGPT-style chat UI for your team, connected to any OpenAI-compatible endpoint.
- The UI binds to localhost and you reach it through Session Manager. The session secret is generated per instance.
- No baked weights or keys. Chats and settings persist on your EBS volume.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
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 |
|---|---|
t3.large Recommended | $0.02 |
t3.medium | $0.02 |
Dimensions summary
You pay an hourly software fee for each running instance, billed by the hour. Pricing is tied to the Amazon EC2 instance size you choose. The t3.medium rate applies when you run the software on a t3.medium instance, and the t3.large rate applies on a t3.large instance. These are two independent size options, not stacked tiers. You pick one size based on your needs. EC2, EBS storage, data transfer, and your separate model-provider charges are billed outside this software fee.
Top-of-mind questions for buyers
The t3.medium instance provides 2 vCPU and 4 GiB of RAM. The t3.large instance offers more compute and memory for teams that need headroom. The product needs at least 4 GiB of RAM and a 24 GiB encrypted root volume. You pick the size that fits your load.
The software fee applies for each running instance, billed by the hour. A stopped instance does not accrue the software fee. Stopped instances may still incur separate AWS storage charges for the attached EBS volume. The software meter counts running time only.
The software fee covers the packaged image only. EC2 compute, EBS storage, and data transfer are billed separately by AWS. You also connect your own external model endpoint, and that provider charges you directly. No model keys or provider accounts are included.
docs.softwaresushi.com
Helpful?
Vendor refund policy
We offer a full refund of software charges for the first 48 hours billing starts if the product does not perform as described. To request a refund, email info@softwaresushi.com with your EC2 instance ID and a description of the issue. AWS infrastructure costs (EC2, EBS, data transfer) are billed by AWS and are not eligible for refund by us.
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) .
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
Open WebUI v0.11.4 on Ubuntu 24.04 LTS, packaged by Software Sushi in a non-root CPython 3.12 runtime with hash-locked Python wheels. Version 0.1.5 adds a separate non-root, CPU-only Ollama v0.40.6 engine with the pinned Qwen3 0.6B Q8_0 model, so chat works offline right after launch; the engine is reachable only from the UI over a private Docker network. Recommended instance is now t3.large (8 GiB) with 32 GiB storage. The UI listens on 127.0.0.1:8080 through Session Manager port forwarding; a session secret is generated at first boot. Data persists under /var/lib/open-webui. Includes a guided walkthrough (bash /opt/sushi/docs/demo.sh). You can also connect your own OpenAI-compatible endpoint; no provider keys or user database are included.
Additional details
Usage instructions
- Launch t3.large (8 GiB RAM, 32 GiB or larger encrypted gp3, IMDSv2) with AmazonSSMManagedInstanceCore and outbound HTTPS. No inbound rules are needed.
- Connect with aws ssm start-session --target <instance-id>. After cloud-init finishes, run: sudo -iu ubuntu bash /opt/sushi/docs/demo.sh (expect SUSHI_CUSTOMER_DEMO_PASSED).
- From your workstation: aws ssm start-session --target <instance-id> --document-name AWS-StartPortForwardingSession --parameters '{"portNumber":["8080"],"localPortNumber":["8080"]}', then open 127.0.0.1:8080 in your browser (plain http).
- Create your account immediately: the first account becomes administrator.
- The bundled local model sushi-qwen3-0.6b:q8_0 is available right away. To use a larger model, add your OpenAI-compatible base URL and API key in admin settings (the README shows a pinned LiteLLM proxy for Amazon Bedrock). Back up /var/lib/open-webui and /etc/open-webui together. Documentation: https://docs.openwebui.com/ Support: info@softwaresushi.com Launch guide: https://docs.softwaresushi.com/launch-kit/
Resources
Support
Vendor support
Software Sushi provides AMI packaging and setup guidance. Contact info@softwaresushi.com with your product version and the steps you took; never send credentials or private data. Guaranteed response times require a separate agreement. This offer does not include Open WebUI Inc. 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
Crawl4AI turns web pages into clean Markdown and JSON for LLM, RAG and data pipelines. This Ubuntu 24.04 AMI runs Crawl4AI with a built-in headless browser behind a private, token-protected HTTPS API, so developers can extract content from JavaScript-heavy pages in their own AWS account.
Production-ready Hermes AI messaging agent on hardened Ubuntu 24.04. Add your model-provider and Telegram credentials and run it in your AWS account.
Evaluate assistant answers with DeepEval on Ubuntu 24.04, with optional model judging and saved JSON score reports. This is paid repackaged open-source software.
Open Interpreter lets a language model write and run code to get real work done from plain-English requests: analyze and chart data, clean up files, convert formats and automate scripts. This Ubuntu 24.04 image runs it on an isolated cloud instance instead of your laptop, asks before running any code and works with the model provider you choose.
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.