Sold by: cloudimg
Deployed on AWS
Free Trial
AWS Free Tier
This product has charges associated with it for seller support. TensorFlow Serving, Google's high-performance ML model server, preinstalled with the canonical half_plus_two sample model, a Docker runtime, and an nginx basic-auth gateway. Per-instance credentials rotate on first boot. Backed by twenty-four-seven cloudimg support.
Overview
Image
TensorFlow Serving model status
Image
REST predict request
Image
gRPC predict example
This is a repackaged open source software product wherein additional charges apply for cloudimg support services.
Overview TensorFlow Serving is Google's flexible, high-performance serving system for machine learning models, designed for production environments. This image delivers TF Serving running under Docker behind an nginx basic-auth gateway, ready to serve TensorFlow SavedModels within minutes of launch.
Application Stack The official tensorflow/serving CPU image runs as a Docker container managed by docker compose v2 and supervised by systemd. Two endpoints are exposed: a gRPC predict endpoint on 8500 and a REST predict endpoint on 8501. An nginx reverse proxy on port 80 fronts the REST API and enforces HTTP Basic authentication so the model server is never exposed unauthenticated on the public internet.
Sample Model Google's canonical half_plus_two SavedModel is bundled at /var/lib/tfserving/models/half_plus_two/1/ so the server has a working model to serve on first boot. Replace it with any TensorFlow SavedModel by dropping a new versioned directory under /var/lib/tfserving/models/.
Secure First Boot On first boot a one-shot systemd unit rotates the nginx basic-auth password (per-instance, openssl-generated), writes /etc/nginx/.htpasswd, and saves the credentials and sample curl command to /root/tensorflow-serving-credentials.txt, readable only by root.
Ready To Use Docker, the compose plugin, the tensorflow/serving image, the bundled sample model, nginx, the systemd units and the per-instance password are all configured. Browse to http:///v1/models/half_plus_two with the cloudimg user and the per-instance password to confirm the model is AVAILABLE, then POST instances to /v1/models/half_plus_two:predict to score inputs.
cloudimg Support 24/7 technical support by email and chat. Help with TensorFlow Serving deployment, model upgrades, gRPC and REST integration, nginx hardening, and TLS termination.
Use Cases Low-latency online inference for TensorFlow SavedModels. Multi-model serving via a single container. A/B testing model versions. Edge or regional model hosting with REST or gRPC clients.
TensorFlow and the TensorFlow logo are trademarks of Google LLC. All other product and company names are trademarks or registered trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.
Highlights
- TensorFlow Serving preinstalled and ready, with the canonical half_plus_two sample SavedModel and no manual setup required
- Hardened first boot rotates the nginx basic-auth password on every instance and stores credentials in a root-only file
- Around-the-clock technical support from cloudimg, with expert assistance for TF Serving deployment, upgrades, model swaps and nginx hardening
Details
Sold by
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 7 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. 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.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
Dimension | Description | Cost/hour |
|---|---|---|
c5.xlarge Recommended | c5.xlarge | $0.08 |
t2.micro | t2.micro instance type | $0.04 |
t3.micro | t3.micro instance type | $0.04 |
d3.4xlarge | d3.4xlarge instance type | $0.24 |
t3.small | t3.small instance type | $0.04 |
m5ad.8xlarge | m5ad.8xlarge instance type | $0.24 |
c8ine.8xlarge | c8ine.8xlarge instance type | $0.24 |
g6.4xlarge | g6.4xlarge instance type | $0.24 |
r5a.16xlarge | r5a.16xlarge instance type | $0.24 |
m5a.xlarge | m5a.xlarge instance type | $0.12 |
Vendor refund policy
Refunds available on request.
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
Initial release of TensorFlow Serving 2 with nginx basic-auth gateway and bundled half_plus_two sample SavedModel on a dedicated 20 GiB model volume.
Additional details
Usage instructions
Connect via SSH on port 22 as the default login user for your operating system variant (the user guide lists it per variant). The basic-auth-gated REST API is served on port 80 at the /v1/ prefix. Retrieve the generated credentials with: sudo cat /root/tensorflow-serving-credentials.txt. Health check: curl -u cloudimg:<password> http://<instance-public-ip>/v1/models/half_plus_two. Predict: curl -u cloudimg:<password> -d '{"instances":[1.0,2.0,5.0]}' -H 'Content-Type: application/json' http://<instance-public-ip>/v1/models/half_plus_two:predict. The raw TF Serving REST port 8501 and gRPC port 8500 are also published but unauthenticated -- restrict or remove those security group rules in production.
Resources
Vendor resources
Support
Vendor support
cloudimg provides 24/7 technical support for this product by email and live chat. Our engineers help with deployment, configuration, updates, performance tuning and troubleshooting; critical issues receive a one hour average response. Contact support@cloudimg.co.uk .
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
Up-to-date, customizable, and secure. TensorFlow Serving is an open source high-performance system for serving machine learning models. It allows programmers to easily deploy algorithms and experiments without changing the architecture.
Up-to-date, secure, and ready to deploy on Kubernetes. TensorFlow ResNet is a client utility for use with TensorFlow Serving and ResNet models.
Deep Learning OSS NVIDIA Driver AMI with TensorFlow 2.13 on Amazon Linux 2. Specialized machine learning AMI with complete pre-configured stack. Includes NVIDIA drivers, CUDA, and all necessary libraries for AI projects. Optimized for AWS GPU instances. Immediate deployment without manual configuration. This is a repackaged software product wherein additional charges apply for support provided by Galaxys.
Pre-configured Deep Learning environment with TensorFlow 2.15 and Keras 3.0 on Ubuntu 22.04 LTS. This optimized AMI includes the complete machine learning stack ready for immediate deployment. Perfect for AI research, computer vision, NLP projects, and production ML workflows.
Includes full Python data science toolkit: Jupyter Lab, pandas, NumPy, scikit-learn, OpenCV, and matplotlib. GPU-ready configuration supports both CPU and accelerated computing. Enterprise-grade setup saves hours of installation and configuration time. This product wherein additional charges apply for support provided by Galaxys
Intuz offers TensorFlow, a free and open-source software library designed to assist developers of all levels, from novice to advanced, in building ML models for desktop, mobile, web, and cloud applications.
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.