Overview

Product video
Build visual AI workflows with Langflow 1.13.0 on Ubuntu 24.04. Connect input, OpenAI-compatible model and output components in the browser, save your flow and run it in the playground. The installed sushi-langflow demo command also saves a three-node flow, runs a short prompt against your configured provider and independently reads back the saved result.
First boot creates a unique administrator identity and encryption key, then starts the non-root application automatically on 127.0.0.1:7860. Public signup and automatic login are disabled. Reach the editor through an authenticated SSH or Systems Manager port-forwarding session; the application port is not exposed to the public network.
This single-instance image uses one application worker and SQLite in /var/lib/langflow. Back up that state together with /etc/langflow, including the original encryption and administrator configuration. Custom component uploads, component-path overrides and code interpreter components are disabled. SSRF protection is enabled, with an empty private-host allowlist by default.
Bring your own compatible model-provider account, endpoint and API key after launch. No provider subscription, model weights or model credits are included. The shipped model component bundle is OpenAI-compatible; provider usage is billed by your provider. Software and dependency notices and source archives are delivered on the instance. Langflow is MIT-licensed; 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 storage, data transfer and model-provider calls are billed separately. Installation support: info@softwaresushi.com .
Highlights
- Langflow 1.13.0 visual editor with a saved input-to-model-to-output workflow and a real-provider CLI demo.
- Unique first-boot administrator credentials, authenticated tunnel access and persistent single-instance SQLite storage.
- Bring your own OpenAI-compatible model provider; software, infrastructure and provider charges are separate.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.03 |
Dimensions summary
Top-of-mind questions for buyers
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.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
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
0.2.1: the documented demo now runs with no arguments. It waits for startup, then saves, runs and reads back a local Chat Input to Chat Output flow without a provider key; the provider demo still accepts --model and --api-key-file. Langflow 1.13.0 visual workflow editor with private administrator login, persistent SQLite and the installed real-provider demo. Recommended t3.large with 8 GiB RAM and 32 GiB encrypted gp3 root storage.
Additional details
Usage instructions
Launch t3.large with 8 GiB RAM and at least 32 GiB encrypted gp3 root storage, using IMDSv2. Allow several minutes for automatic first boot. Connect with Systems Manager Session Manager and run sudo -iu ubuntu, or use SSH as ubuntu. Run sushi-langflow help and sushi-langflow status. Read the initial administrator credentials with cat /etc/langflow/admin.json in that private terminal. Forward local port 7860 to 127.0.0.1:7860 on the instance and open http://127.0.0.1:7860 locally. Run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh with no arguments: it waits for Langflow, saves a local Chat Input to Chat Output flow, runs it and reads it back, with no provider key or outbound model call, and prints SUSHI_CUSTOMER_DEMO_PASSED. To use your own OpenAI-compatible provider, put only the key in a mode 0600 file owned by ubuntu and add --model MODEL --api-key-file FILE; each model execution can incur provider charges. Read /opt/sushi/docs/README.md and /opt/sushi/docs/DEMO.md. Back up /var/lib/langflow and /etc/langflow together; preserve the original encryption key and administrator identity. Software is USD 0.03 per running instance-hour; EC2, EBS storage, data transfer and model-provider calls are separate.
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.