Sold by: Software Sushi
Deployed on AWS
This is a repackaged open source software product wherein additional charges apply for independent packaging, maintenance and a tested coding starter. Run OpenCode in the terminal with real file-edit tools and independently checked sample-workspace results.
Overview
Run OpenCode 1.19.4 as an ordinary Ubuntu user through its terminal interface. Start with the supplied calculator workspace and a clearly labeled local test-provider demonstration that exercises a real file-edit tool and independent Python assertions. The demo retains original output under your user results directory and consumes no paid model service. It is a fixture workflow, not evidence that a commercial model answered.
For your own project, supply provider credentials after launch or attach an appropriately scoped Amazon Bedrock instance role, then select an explicit model. With the instance role, set AWS_PROFILE=default to select the standard temporary-credential SDK chain. No provider key, subscription or model credits are included. The installed configuration supports amazon-bedrock/amazon.nova-lite-v1:0 in us-east-1 with suitable customer permissions; model-provider usage is separate. Coding tools modify project files, so use a backed-up or version-controlled workspace and review changes.
The wrapper disables automatic updates, model-list downloads and third-party plugins. There is no persistent web server, browser URL or inbound application port. Session state is stored in the ordinary user's data directory. Existing sample work is preserved on restart. Back up the workspace and user session data when moving instances. Release source archives and component notices are delivered with the image. OpenCode uses MIT; its runtime and dependencies retain their own license terms.
This is a repackaged open source software product wherein additional charges apply for independent AMI packaging, maintenance and setup documentation. Software Sushi is an independent packager and claims no upstream or AWS endorsement.
Software costs USD 0.03 per running instance-hour. EC2, EBS, data transfer and your model-provider usage are billed separately. Installation support: info@softwaresushi.com .
Highlights
- Terminal coding assistant with a launch-created sample workspace and ordinary-user execution.
- A labeled local fixture exercises actual file edits and independent assertions without paid model usage.
- Select your own provider after launch; preserve workspace, sessions and original task output for review.
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.medium Recommended | $0.03 |
Dimensions summary
This listing bills on a single usage-based dimension. You pay an hourly software rate for running the product on a t3.medium Amazon EC2 instance in your own AWS account. There are no tiers or plan choices to compare. Your cost scales with the number of hours the instance runs. AWS infrastructure such as EC2, storage, and data transfer is billed separately. Any model-provider or external service you connect also bills on its own. You add your own API keys after launch and keep control of the environment.
Top-of-mind questions for buyers
The software runs on a t3.medium Amazon EC2 instance, a burstable general-purpose size with 2 vCPUs and 4 GB of memory. The hourly software charge is tied to running that one instance in your AWS account. You manage the instance, its region, and connected services.
The hourly software charge meters the time the instance runs. When you stop or power off the instance, the software charge stops accruing. AWS may still bill for attached storage such as EBS on a stopped instance. Restarting the instance resumes the hourly software charge.
AWS infrastructure such as EC2, storage, networking, and data transfer is billed separately. The coding assistant connects to LLM providers using API keys you add after launch. Those model providers charge for their own usage on their own accounts. Review each current listing before subscribing.
softwaresushi.com+1
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 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
Use OpenCode in the terminal with a preserved sample workspace, real file-edit tools and independently checked coding results. Launch t3.medium with at least 4 GiB RAM and 32 GiB encrypted gp3 root storage. Require IMDSv2.
Additional details
Usage instructions
Launch t3.medium with at least 4 GiB RAM and 32 GiB encrypted gp3 root storage. Require IMDSv2. Wait for automatic first boot, connect through Session Manager and switch to ubuntu with sudo -iu ubuntu. Run opencode --version and the starter with sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. The supplied local test-provider demo is a labelled fixture and saves results under ~/opencode-demo. For your own project, use a backed-up workspace, configure provider credentials after launch or attach an appropriately scoped Bedrock role, and select an explicit model. For the Bedrock instance role, set AWS_PROFILE=default so the standard SDK uses temporary IMDSv2 credentials; no provider key is needed. The image contains no provider key or subscription. Model usage is separate. No persistent web listener, browser URL or inbound app port is supplied. Back up your workspace and user session data; retain and inspect task output without sharing credentials. Read /opt/sushi/docs/README.md. Software costs USD 0.03 per running instance-hour. EC2, EBS, data transfer and your model-provider usage are billed separately. Getting started: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/opencode/getting-started-e6fe8e9b516a5132.html
Resources
Vendor resources
Support
Vendor support
Software Sushi provides AMI packaging and setup guidance. Contact info@softwaresushi.com for installation questions. Support coverage requires a separate agreement; this offer does not include upstream project 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
Tabby is an open source, self-hosted AI coding assistant server for code completion and chat that runs in your own AWS account. This Ubuntu 24.04 AMI runs the Tabby v0.32.0 CPU server on localhost, with no model weights baked in; model-backed completion is untested until you attach a model. Attach the completion model you choose and keep code and prompts in your own AWS account.
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.
Sushi ML Studio is no-code machine learning that runs in your browser, on your own EC2 instance. Upload a CSV or Excel file, pick the column you want to predict, and it trains and compares against many scikit-learn models, tells you in plain language how good the best one is, and adds predictions to new spreadsheets. Your data never leaves the instance, and you keep the model file and the Python code that reproduces it.
Aider is an AI pair programmer for your terminal. Describe a change in plain English and Aider edits the right files in your git repository, then commits each change so you can review it or undo it. This Ubuntu 24.04 image installs Aider with a git workspace on first boot, with Session Manager access and no inbound ports.
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.