Sold by: Software Sushi
Deployed on AWS
Free Trial
Langfuse is an open source LLM observability platform for tracing, evaluating and debugging LLM applications. This Ubuntu 24.04 AMI runs the full single-node stack with per-instance credentials created at first boot, and you reach the UI through AWS Systems Manager port forwarding.
Overview
Langfuse 4.56.0 is an open source LLM engineering platform for tracing, evaluating and debugging LLM applications. This AMI runs it inside your own AWS account as a single-node stack, so trace data stays on an EBS volume you control and the UI stays off the public internet.
What you get: Langfuse web and worker plus Postgres, Redis, ClickHouse and MinIO in Docker Compose with pinned image digests, all bound to loopback. First boot generates private per-instance credentials and an admin password (/etc/langfuse/admin.password, readable only with sudo). The AMI contains no customer credentials or databases, and telemetry is disabled.
Getting started: launch t3.large (8 GiB RAM, 40 GiB encrypted gp3 or larger) with an instance profile that has AmazonSSMManagedInstanceCore, allow outbound HTTPS and keep the security group free of inbound rules. Connect with Session Manager, run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh, then forward port 3000 with AWS-StartPortForwardingSession and sign in from your browser. Send traces with OpenTelemetry (OTLP) or a v4 Langfuse SDK and query them with the Observations API v2 (add fields=core,basic,io to include input and output). Upstream documentation: https://langfuse.com/docs .
The bundled ClickHouse is the stable 25.12 release. Its static binary embeds OpenSSL 3.5.0, which has a published CVE; ClickHouse is reachable only on loopback inside the instance. Updated AMIs will follow new stable ClickHouse releases.
This is a single-node deployment, not a clustered or managed service. Back up the Docker volumes and /etc/langfuse together before replacing an instance.
Software fee: USD 0.02 per running t3.large instance-hour with the first five days free for one concurrent instance; the same full software runs throughout and there is no product-imposed time, user or usage limit. EC2, EBS and data transfer are billed separately. No annual offer is configured.
This is a repackaged open source software product wherein additional charges apply for independent AWS packaging, validation, maintenance and setup documentation. Langfuse is MIT-licensed outside separately licensed ee/ paths; enterprise features are not included. Software Sushi supplies the AMI recipe, packaging and setup guide without claiming upstream endorsement.
Highlights
- Trace, evaluate and debug LLM applications with Langfuse 4.56.0, ingesting through OpenTelemetry or the v4 Langfuse SDKs.
- Trace data stays on your EBS volume, and each instance creates its own credentials and admin password on first boot.
- The UI and data services bind to localhost; you reach the UI through Session Manager port forwarding.
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
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
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 |
Dimensions summary
This listing uses one usage-based dimension billed per hour on the t3.large instance size. You pay the hourly software fee only while the instance runs. There are no tiers or add-ons to choose between. The t3.large size provides the 8 GiB of memory the stack needs. AWS charges for infrastructure such as EC2, EBS, and data transfer separately from this software fee. Any free trial appears in the offer terms on the listing.
Top-of-mind questions for buyers
The t3.large size provides 8 GiB of memory, which the stack needs to run. You pair it with an encrypted gp3 root volume of at least 40 GiB and IMDSv2. The image runs the web, worker, and supporting data services together in one instance.
You pay the hourly software fee only while the instance runs. A stopped instance does not accrue the software fee. However, AWS may still charge for the attached EBS storage while the instance is stopped, since storage billing is separate from the software fee.
AWS bills EC2 compute, EBS storage, and data transfer separately from the software fee. The image stores trace data on your EBS volume, so storage grows as your trace volume grows. Review the offer terms on the listing for current rates and any free trial.
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
Langfuse 4.56.0 (MIT, by Langfuse GmbH) on Ubuntu 24.04 LTS as a single-node Docker Compose stack: web, worker, Postgres, Redis, ClickHouse and MinIO, all with pinned image digests. The UI listens on 127.0.0.1:3000 and is reached through Session Manager port forwarding. Per-instance credentials are generated at first boot. Ingest traces with OTLP or a v4 Langfuse SDK and read them back with the Observations API v2. Telemetry is disabled.
Additional details
Usage instructions
- Launch t3.large (8 GiB RAM, 40 GiB or larger encrypted gp3, IMDSv2) with an instance profile that has AmazonSSMManagedInstanceCore and outbound HTTPS. No inbound rules are needed.
- Connect: 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).
- Read the admin password: sudo cat /etc/langfuse/admin.password (user admin@localhost.local ).
- From your workstation: aws ssm start-session --target <instance-id> --document-name AWS-StartPortForwardingSession --parameters '{"portNumber":["3000"],"localPortNumber":["3000"]}', then open port 3000 on your workstation in a browser and sign in.
- Send traces with OTLP to /api/public/otel/v1/traces or with a v4 Langfuse SDK using the project keys from the UI. Read them back with GET /api/public/v2/observations with fields=core,basic,io to include input and output (the default fields omit them). The legacy v2/v3 ingestion endpoint is not accepted in this v4 mode.
- ClickHouse: the bundled ClickHouse is the stable 25.12 release. Its static binary embeds OpenSSL 3.5.0, which has a published CVE; ClickHouse listens only on loopback and is not reachable from the network. Move to a newer AMI when one is released. Docs: https://langfuse.com/docs . Back up the Docker volumes and /etc/langfuse together.
Support
Vendor support
Software Sushi provides AMI packaging and setup guidance. Contact info@softwaresushi.com for installation questions. This offer does not include upstream Langfuse 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
LiteLLM Proxy gives all your applications one OpenAI-compatible API in front of the LLM providers you use, so you can switch or combine models and keep provider keys in one place without changing application code. This Ubuntu 24.04 image starts the open source LiteLLM 1.104.2 gateway on first boot, with loopback-only HTTPS and a per-instance master key.
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.
This is a repackaged open source software product wherein additional charges apply for independent packaging, maintenance and setup guidance. Build and run visual AI workflows with Langflow 1.13.0, private administrator login and persistent SQLite storage.
This product has charges associated with it for seller support. Hossted Platform offers an intuitive dashboard and CLI that delivers comprehensive security, monitoring, logging, and applicative insights.
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.