Sold by: ProvenCloud
Deployed on AWS
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use Langflow 1.13.0 visual AI workflow builder. Design AI agents, chatbots and RAG pipelines by dragging components on a canvas and run them through an API, with PostgreSQL storage and unique passwords for every instance.
Overview
Langflow is a popular open source visual builder for AI applications. You assemble agents, chatbots, retrieval-augmented generation (RAG) pipelines and multi-step workflows by connecting components on a canvas, test them in a chat playground, and serve each flow as an API that your own apps can call. It works with the leading model providers and vector databases. This image gives you a ready Langflow server in minutes.
What is included: Langflow 1.13.0 on Ubuntu 24.04 LTS with Python 3.12, PostgreSQL 16 storing your flows and message history, nginx serving Langflow over HTTPS, and Webmin 2.670 for server administration. The upstream starter templates are ready to use. Security is on by default: no password or key ships in the image. On first boot every instance creates its own Langflow admin, secret key, database and Webmin passwords, HTTPS certificate and server keys. Auto-login and public sign-up are off, the API needs a key or a signed-in user, PostgreSQL and Webmin listen only on the server itself, and SSH accepts key-based login only. No model weights or provider keys are included: add your own in the flow components. Provider charges are separate.
What you get on top of the free software: a pre-built and tested image that is ready in minutes, a unique security setup for every server, simple scripts for changing passwords and taking backups, regular image updates, and help by email whenever you need it. Langflow is open source software licensed under MIT. Langflow is a trademark of its respective owner. This image is an independent build by ProvenCloud.
Highlights
- Build AI apps visually: drag and connect models, prompts, vector stores, tools and agents on a canvas, test them in the built-in playground, then call every flow through its own REST API.
- Bring any model: connect OpenAI, Anthropic, Amazon Bedrock, Ollama and many other providers with your own keys. No model or paid credit is bundled, so you pay your provider directly.
- Secure by default: sign-in required with auto-login and public sign-up turned off, a random admin password for every instance, HTTPS from the first boot, PostgreSQL kept off the internet.
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. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.04 |
c1.xlarge | $0.06 |
c3.2xlarge | $0.10 |
c3.4xlarge | $0.10 |
c3.8xlarge | $0.10 |
c3.xlarge | $0.06 |
c4.2xlarge | $0.10 |
c4.4xlarge | $0.10 |
c4.8xlarge | $0.10 |
c4.xlarge | $0.06 |
Dimensions summary
You pay by the hour for the running software, priced per EC2 instance type. The many dimensions listed are not feature tiers. Each one matches a specific EC2 instance size and family, such as general purpose, compute, memory, storage, or GPU options. Your hourly software charge scales with the instance you pick: smaller instances cost less, larger instances cost more. You add your own EC2 compute and storage costs, billed by AWS. A 5-day free trial applies before charges begin.
Top-of-mind questions for buyers
Each dimension matches one EC2 instance type, such as t3.large or m5.xlarge. The listed price is the software charge per hour that instance runs. You pick one type when you launch, and that single rate applies for every hour the instance stays running.
The hourly software charge meters running time. A stopped instance does not run the software, so the per-hour software fee stops accruing. Your own AWS costs for storage, such as the 40 GiB gp3 root volume, may still apply while the instance exists. AWS bills those separately.
The hourly software charge covers the pre-built image with its installed stack. You pay your own EC2 compute and storage separately, billed directly by AWS. The software is open source under MIT, so no licence key is required. No model provider keys are included; you supply your own.
www.provencloud.io
Helpful?
Vendor refund policy
Software charges are billed hourly, only while your instance runs. You can stop charges at any time by terminating the instance or cancelling your subscription. Charges already incurred are not refundable.
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
Latest stable release on AWS Marketplace.
Langflow 1.13.0 on Ubuntu 24.04 LTS with Python 3.12, PostgreSQL 16.15, nginx (HTTPS) and Webmin 2.670.
Random Langflow admin, secret key, database and Webmin passwords, HTTPS certificate and server keys are created for every instance on first boot; read them with sudo pc-credentials show.
Includes helper scripts in /home/ubuntu/iscripts for changing passwords, and pc-backup for same-server backups.
Additional details
Usage instructions
Once the instance is running, wait for the instance health checks to pass, then allow up to 15 minutes for the first-boot setup to finish. Connect over SSH with your key pair: ssh -i /path/to/key.pem ubuntu@<instance-public-ip>, then run sudo pc-credentials show to see the random passwords created for this instance. They are not your instance ID, and no two instances share them.
Open https://<instance-public-ip>/ in your browser and accept the one-time warning for the server's self-signed certificate. Sign in with admin as username and the password labelled langflow. Start from a starter template or a blank flow, and add your own model provider key in the model component. To call a flow from your apps, create an API key under Settings and use the flow's API panel.
Required inbound ports: 22 (SSH), 80 and 443 (the application; port 80 redirects to HTTPS). For security, allow port 22 only from your own IP address. Keep every other port closed.
Change your passwords after the first sign-in: connect over SSH and run sudo bash /home/ubuntu/iscripts/pass_langflow.sh for the Langflow admin or pass_webmin.sh for Webmin, from the same folder. To check the server, run sudo bash /home/ubuntu/iscripts/langflow_status.sh.
Webmin is not open to the internet. To use it, keep this SSH tunnel open on your own computer: ssh -i /path/to/key.pem -N -L 18000:127.0.0.1:8000 ubuntu@<instance-public-ip>, then open http://localhost:18000/ and sign in with admin as username and the password labelled webmin.
To back up the application on the same server, run sudo pc-backup create /var/backups/application.tar.gz and copy the file to encrypted storage outside the instance, because it contains passwords. To restore it, run sudo pc-backup restore /var/backups/application.tar.gz --confirm-restore. The backup covers the Langflow settings and database, including your flows.
After a stop and start the instance gets a new public IP unless you attach an Elastic IP; your data and passwords are kept. For production, point your own domain at the instance and replace the self-signed certificate with a trusted one.
Resources
Vendor resources
Support
Vendor support
Email: support@provencloud.io
Support page: https://www.provencloud.io/support
Hours: Monday to Friday, 10:00 to 19:00 IST (UTC+05:30)
Billing and refunds for this subscription are handled by AWS Marketplace.
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
![Hugging Face NLP Stack on Ubuntu 24.04 LTS by ProvenCloud [IN]](https://d7umqicpi7263.cloudfront.net/img/product/d658579a-ad7f-4f3b-9802-d08c8df5e3eb.com/4c173b409be2aeb8869f955151e879be)
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use Hugging Face NLP workspace with Transformers, PyTorch and JupyterLab. Run and fine-tune language models on your own server, with unique passwords for every instance.
![Jenkins CI/CD Server on Ubuntu 24.04 LTS by ProvenCloud [IN]](https://d7umqicpi7263.cloudfront.net/img/product/37144066-287a-4265-ada7-a3188be2198d.com/4c173b409be2aeb8869f955151e879be)
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use Jenkins LTS CI/CD server with Java, Docker and common build tools. Build, test and deploy your code automatically on every change, with unique passwords for every instance.
![MariaDB with phpMyAdmin on Ubuntu 24.04 LTS by ProvenCloud [IN]](https://d7umqicpi7263.cloudfront.net/img/product/19bd0105-bfaa-4197-91cf-b824fa63c88c.com/4c173b409be2aeb8869f955151e879be)
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use MariaDB 12.3 LTS database server with phpMyAdmin. Get a tuned, MySQL-compatible database for your applications in minutes, sized to your instance automatically, with unique passwords for every instance.
This is a repackaged open source software product wherein additional charges apply for hardening, security configuration, and setup support.
Langflow is an open-source visual framework for building multi-agent and RAG AI applications. This Lynxroute build is security baked in: authentication enabled, Nginx TLS reverse proxy, unique admin credentials at first boot, and CIS Level 1 hardened Ubuntu 24.04 LTS base.
Note: Langflow initialises in ~60 seconds after instance start. Wait 1-2 minutes before opening the Web UI.
MIT license - fully auditable, no vendor lock-in.
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.