Sold by: Ant Media
Deployed on AWS
Free Trial
GPU-accelerated live transcoding on g4dn and g5. NVENC and NVDEC offload H.264 and H.265 encoding and decoding for Adaptive bitrate ladders at any resolution you need. Run your own AI models on the same instance. Deploy in two minutes with support for WebRTC, MoQ, LL-HLS, HLS, RTMP(S), SRT, RTSP, NDI, DASH, CMAF, WHIP, and VOD, etc. No per-stream fees.
4.8
Overview
Transcoding is where live streaming budgets go. Put it on silicon built for it.
Adaptive transcoding is the most expensive thing a streaming server does. If your instance count is driven by encoding load rather than audience size, you are paying CPU prices for work dedicated hardware does far better.
Ant Media Server Enterprise on GPU uses NVIDIA NVENC for encoding and NVDEC for decoding, taking both halves of the transcode off the CPU, in H.264 and H.265. Build ladders at any resolution and bitrate your workflow calls for - 4K, 1440p, 1080p, 720p, 360p, audio-only, or your own custom set. There is no fixed resolution ceiling; capacity depends on the GPU you choose and the ladder you configure.
WHAT THE DIFFERENCE LOOKS LIKE
One stream, multiple ABR renditions, 4k down to 360p: a CPU server often struggles with that single stream, while a GPU server handles five to six of them. GPU encoding runs up to 5x faster in demanding workloads.
Without a GPU, Ant Media Server falls back to software encoding - fine for light loads, but stack ABR profiles and CPU becomes the bottleneck long before your network does.
WHEN GPU IS THE RIGHT ANSWER
Multi-rendition OTT and broadcast. The deeper the ladder, the more GPU changes your fleet size - and the effect compounds at higher resolutions.
Multi-camera live production. Several simultaneous feeds, each with its own rendition set, in real time.
Large-scale surveillance and IP camera aggregation. Hundreds of RTSP feeds needing normalisation before storage or playback.
Sports, racing and event broadcasting. Many concurrent events, full ladders, hard start times.
Any deployment adding CPU instances purely to keep up with encoding. If your CPU count climbs faster than your audience, this listing is for you.
AI AND COMPUTER VISION ON THE SAME INSTANCE
A GPU you are already paying for to transcode can also run inference. The Python AI Plugin runs your own models directly on live streams: implement a Python class extending PluginBase, register it, and it processes every frame. Worked examples ship with it - object detection and pose estimation with YOLOv8, face detection with OpenCV, vision-language models through Ollama. Each plugin runs in its own thread, publishes a processed HLS stream with overlays, and persists timestamped detection data retrievable over REST.
Nothing leaves your infrastructure. No external inference service, no per-frame API charges, no video egress to a third party - which matters in surveillance, healthcare, insurance and public safety, where data residency is settled before capability.
ZERO CONFIGURATION
With CUDA 12.6 installed, Ant Media Server detects a supported GPU at startup and uses it automatically - no dashboard toggle, no setting to change. Ubuntu 20.04, 22.04 and 24.04 supported. GPU acceleration applies when transcoding is active; SFU mode forwards without re-encoding, so the GPU stays idle by design.
CHOOSING AN INSTANCE
Most Ant Media GPU deployments run on g4dn (NVIDIA T4) - the lower-cost entry point, comfortable with typical ABR ladders. g5 (NVIDIA A10G) offers more GPU memory and throughput, suiting deeper ladders, higher resolutions, or inference alongside transcoding.
EVERYTHING THE ENTERPRISE EDITION DOES
Sub-500ms WebRTC. Ingest over WebRTC, MoQ, SRT, NDI, RTMP, RTMPS, RTSP, WHIP, and MPEG-TS. Delivery over WebRTC, MoQ, LL-HLS, HLS, CMAF, DASH. Live DVR, S3 recording, CloudFront integration, DRM for Widevine, FairPlay and PlayReady. 99.99% uptime SLA.
PRICING
Per instance-hour. No per-stream, per-minute or per-viewer fees. Capacity is set by the hardware you choose, so scaling is a decision you make rather than a bill you receive. GPU instances typically run continuously, so a 365-day contract is available at a substantial discount.
MIXING GPU AND CPU IN ONE CLUSTER
You do not have to move your whole fleet, and most customers don't. Transcode on GPU origins, deliver from cheaper CPU edges. Set GPUImage to true in the CloudFormation template.
Deploy Auto Scaling Cluster with GPU
WHEN TO CHOOSE A DIFFERENT LISTING
If concurrent connections rather than transcoding is your bottleneck, Enterprise on x86 or Graviton is cheaper. If you run ECS or EKS, use the container listing - it supports GPU nodes too.
PROVEN IN PRODUCTION
Amnimo runs cloud IP camera surveillance at scale. KDDI distributes low-latency video from smart drones across Japan. Aura eGaming delivers sub-second latency for online gaming.
Try Live samples now.
Highlights
- Hardware encode and decode - any resolution, any ladder: NVENC and NVDEC move both halves of transcoding off the CPU, in H.264 and H.265. Where a 4-core CPU server struggles with a single stream at four ABR renditions, a 4-core GPU server handles 5-6 of the same streams, and GPU encoding runs up to 5x faster in demanding workloads. Build ladders at whatever resolutions and bitrates you need. Detected automatically at startup - no configuration.
- GPU is a cost reduction, not a premium tier: If your fleet is sized by transcoding load rather than connection count, you are paying general-purpose cores to do a job that dedicated silicon does better. Consolidate transcoding onto GPU origins and keep cheaper CPU instances for edge delivery - most Ant Media GPU customers run exactly this mix. A 365-day contract is available at a substantial discount for steady workloads.
- Run your own AI models on the same instance: The Python AI Plugin runs your models directly on live streams - no separate inference pipeline, no frames leaving your infrastructure. Implement a Python class, register it, and it processes every stream: object and pose detection with YOLOv8, face detection with OpenCV, or vision-language models via Ollama. Process HLS output with overlays and timestamped detection data via REST.
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.
Dimension | Cost/hour |
|---|---|
g5.4xlarge Recommended | $0.71 |
g4dn.xlarge | $0.52 |
g4dn.12xlarge | $0.85 |
g5.8xlarge | $0.78 |
g4dn.2xlarge | $0.64 |
g4dn.16xlarge | $0.92 |
p3.8xlarge | $0.78 |
p3.16xlarge | $0.92 |
p2.16xlarge | $0.92 |
g5.2xlarge | $0.64 |
Dimensions summary
You pay by the hour for each running server instance, billed only while the instance is up. The 19 options map to different GPU-accelerated AWS instance types across three families: g4dn, g5, p2, p3, and p3dn. Larger sizes within each family carry more CPU, memory, and GPU capacity, so the hourly rate scales with the instance you choose. The license covers the Enterprise Edition and does not limit connections or viewers. AWS bills the underlying compute separately. To reach more capacity, you run more instances, each charged at its own hourly rate.
Top-of-mind questions for buyers
The hourly rate covers the Enterprise Edition license for one running server instance. It bills only while the instance runs. AWS charges the underlying GPU compute, storage, and data transfer separately. The license adds no fixed limit on connections or concurrent viewers; your capacity depends on the instance size you choose.
The license meters running time only, so a fully stopped instance stops accruing software charges. Underlying AWS storage fees may still apply. To reach higher capacity, you run more instances, each licensed per server and billed at its own hourly rate. Auto-scaling can add or remove instances as load changes.
Licensing is per server. Each running Enterprise Edition instance needs its own hourly license, including origin and edge servers in a cluster. In Kubernetes, each pod running the software requires a separate license. There is no extra fee for cluster licensing beyond the per-instance hourly charges themselves.
antmedia.io+1
Helpful?
Vendor refund policy
We do not currently support refunds, you can try for free and you can cancel at any time.
Custom pricing options
Request a private offer to receive a custom quote.
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
Additional details
Usage instructions
Quick Start Guide: https://www.youtube.com/watch?v=EH6v-yUyzjU
Server is ready to use. No need to install anything. Just wait about 30seconds after server starts because it will create some initial configurations after that visit http://SERVER_IP:5080/ to access web management console.
!!! Important Note: If you have problem with REST API usage with SSL over https then check this: https://github.com/ant-media/Ant-Media-Server/issues/2675#issuecomment-738746129
You can login the Web Management Console with below credentials Username: JamesBond Password: {InstanceId*}
*You can learn instance id on EC2 console . It should be something in the following format i-xxxxxxxxxxxxxxxxx. For instance it is i-028bce455e58e62df
For the ssh access to your instance, user name is ubuntu and port number is 22. You can connect it through ssh with the following command: ssh -i your_keypair_file ubuntu@instance_ip
Note: In case of instance stop/start, IP may be changed by AWS. So we strongly recommend using Elastic IP.
For more information follow the instructions on Documentation http://antmedia.io/documentation
Support
Vendor support
Ant Media Server AWS customers can access cutting-edge technology and a community of developers from over 120 countries, enriching their streaming project with collective knowledge and innovation.
Reach out to support via dedicated email at support@antmedia.io
Dedicated support via email, Slack, and live chat from the engineering team that builds the product, with published response and resolution SLAs.
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.
Updated weekly
By Wowza Media Systems, Inc.
Sentiment is AI generated from actual customer reviews on AWS and G2
Functionality
Ease of use
Customer service
Cost effectiveness
Positive reviews
Mixed reviews
Negative reviews
AI generated from product descriptions
Hardware-Accelerated Video Encoding and Decoding
NVENC and NVDEC hardware acceleration for H.264 and H.265 encoding and decoding, offloading transcoding from CPU to GPU with up to 5x faster performance in demanding workloads.
Adaptive Bitrate Streaming
Support for building adaptive bitrate ladders at any resolution and bitrate including 4K, 1440p, 1080p, 720p, 360p, and audio-only renditions with no fixed resolution ceiling.
GPU Instance Compatibility
Automatic GPU detection and utilization at startup on g4dn (NVIDIA T4) and g5 (NVIDIA A10G) instances with CUDA 12.6 on Ubuntu 20.04, 22.04, and 24.04.
On-Instance AI Model Inference
Python AI Plugin framework for running custom machine learning models directly on live streams including YOLOv8 for object and pose detection, OpenCV for face detection, and Ollama for vision-language models with HLS output overlays and REST-accessible detection data.
Multi-Protocol Ingest and Delivery
Support for ingest over WebRTC, MoQ, SRT, NDI, RTMP, RTMPS, RTSP, WHIP, and MPEG-TS with delivery over WebRTC, MoQ, LL-HLS, HLS, CMAF, and DASH including DRM support for Widevine, FairPlay, and PlayReady.
Multi-Format Media Support
Handles video, images, audio, documents, presentations, PDFs and 3D objects as rich-media assets
Comprehensive Video Lifecycle Management
Covers media ingestion, transcoding, metadata enrichment, delivery, playback, distribution, analytics, accessibility, monetization, access control, search and recommendation across the entire video lifecycle
Multiple Video Delivery Modes
Supports VOD (Video-on-Demand), Live streaming, and Real-time video workflows
AWS Native Integration
Tightly integrated with AWS storage services and CloudFront CDN for media delivery
Extensive API and SDK Ecosystem
Provides APIs for transcoding, video conferencing, recording, scheduling, image transformation, interactivity and multi-account management, along with native SDKs for video player, conferencing application, media galleries, broadcast application, video editor and large file upload
Multi-Protocol Streaming Support
Supports ingest protocols including RTMP, RTMPS, RTSP, SRT, WebRTC, UDP, and MPEG-TS; delivery via HLS, LL-HLS, MPEG-DASH, CMAF, WebRTC, RTMP, and RTSP with sub-second latency capabilities.
GPU-Accelerated Transcoding
NVIDIA NVENC-accelerated GPU transcoding with measured capacity of up to 20 concurrent 1080p30 ingest streams and 60 adaptive bitrate renditions per GPU instance, with scalability across g4dn and g5 instance types.
Digital Rights Management
Integrated DRM support for Widevine, FairPlay, and PlayReady content protection with token-based authentication, AES encryption, and audit logging for secure content delivery.
Live Stream DVR and Adaptive Bitrate
Live-stream DVR functionality enabling viewers to rewind and catch up on live content, combined with unlimited adaptive bitrate transcoding for multi-device delivery.
API and Integration Framework
REST APIs, Java APIs, custom modules, and SDKs for integration with third-party video management systems, CDNs, identity providers, analytics engines, and storage systems; includes webhooks and real-time alerting for stream health monitoring.
Standard contract
No
No
No
Customer reviews
reviewer2835279
Remote DJ streaming has expanded event reach and has reduced travel costs for venues
Reviewed on May 02, 2026
Review from a verified AWS customer
What is our primary use case?
I am using Ant Media Server Enterprise for streaming live events. We are a platform where venues can book DJs for their events, and DJs can stream live from their studios to the venue. This way we are reducing the travelling hassles and cost for DJs. Also, in this way, we are reducing the physical boundaries. We have streamed a lot of events across continents.
How has it helped my organization?
We tried other streaming services, but Ant Media provided us with the most reliable and affordable services. We received good feedback from our customers.
What is most valuable?
It is easy to set up with a clean user interface. Moreover, we found the adaptive bit rate to be a very good feature, especially for areas with lower internet speeds.
What needs improvement?
I believe more features regarding runtime media editing can be helpful.
For how long have I used the solution?
I have been using this solution for two years.
Which solution did I use previously and why did I switch?
We didn't use any other products.
What's my experience with pricing, setup cost, and licensing?
This is a good affordable solution.
Which other solutions did I evaluate?
We evaluated other options like Dolby and AWS streaming.
What other advice do I have?
All is good.
GirishSolanki
Live streaming workflow has simplified setup and now streams browser-based video to multiple platforms
Reviewed on Apr 14, 2026
Review provided by PeerSpot
What is our primary use case?
I integrated Ant Media to send data from WebRTC to Ant Media and then from Ant Media to YouTube. Ant Media serves as the connector where I send data from Ant Media to YouTube to enable live streaming through Ant Media. This was my requirement and I have integrated it properly.
I integrated Ant Media by sending WebRTC to the Ant Media endpoint. When I create a new video, I create the project site or video name in Ant Media and simultaneously create the video name on YouTube. I use whatever Ant Media endpoint I receive from Ant Media and point it with the WebRTC. When I start the WebRTC live streaming, that command also initiates live streaming in Ant Media, and Ant Media sends all of that to YouTube. Ultimately, I am starting three live streams with the WebRTC: one from WebRTC, one from Ant Media, and one from YouTube. After starting the live streaming, the data from WebRTC is sent to Ant Media and from Ant Media to YouTube. This was the workflow I created and integrated into my project.
The process was straightforward. I only need to use the API endpoint from Ant Media and configure it into my project. The WebRTC automatically fetches it and sends the data through the Ant Media endpoint to YouTube. It is straightforward with no complex business logic required.
What is most valuable?
Ant Media offers many features that depend on the version you choose. When using the beginner and professional versions, those features are related to your payment plan. When using a beginner or lower level, the features involve streaming data, FPS, data file from the image, image resolution, image quality, and other components you need to send from WebRTC to Ant Media. Those configurations are available in Ant Media and show how you want to send those media to YouTube. These are the best features, but you need to pay more to get better functionality or better resolution.
When using a development level, such as dev, UAT, and production environments, while testing, you do not have all the features and you do not have higher quality when sending the data. When you pay more and have a paid version of Ant Media, they will provide you with the best quality for how you want to send the data to YouTube or elsewhere. This is the basic principle: when you pay more, you receive better resolution.
Ant Media is configurable from the web using WebRTC. If I want to do a live streaming project, I would have to create a Flutter application on Android or iOS, but with Ant Media, I can integrate from the browser itself. I only have to pass the Ant Media endpoint API to a Chrome browser from WebRTC. It is easily configurable, and my organization works on live streaming projects. This is the best way to use Ant Media because you can integrate your simplest or quickest version when you have a deadline or specific live streaming needs.
It basically saves time. Previously, we were creating our own web server and media server. We no longer need that media server and can just use Ant Media directly. There is no doubt that we are paying for Ant Media, but once you acquire users, they start using your website and start WebRTC live streaming through your application. You increase your customer base, and then you can move to a paid version. Ultimately, Ant Media saves your time, money, and the cost of buying a separate web server or media server. Instead of that investment, use Ant Media, get the endpoint, configure it, and do the live streaming.
What needs improvement?
Ant Media needs many improvements. Sometimes I am not getting proper video resolution, and it is lagging. Those issues need to be addressed for better resolution and better video quality.
For how long have I used the solution?
I have used Ant Media from last six years.
What other advice do I have?
My advice for others looking into using Ant Media is that if they want to make it a product, they need to buy a higher version. Otherwise, they will experience lagging issues or video quality issues. This review has received a rating of eight point nine out of ten.
reviewer2803338
Live streaming has elevated customer-facing events and now supports more professional broadcasts
Reviewed on Feb 17, 2026
Review from a verified AWS customer
What is our primary use case?
I am creating a streaming service for a customer-facing product I am developing.
How has it helped my organization?
The feature is now more professional and feasible with Ant Media Server.
What is most valuable?
Valuable features include live streaming, event scheduling with the Ant Media Enterprise admin panel, and broadcast forwarding to social media platforms.
What needs improvement?
For the auto-managed service on AWS, it would be an improvement if it auto-scaled and the launch from the marketplace function actually added to the currently running instance in a scaled manner instead of creating an isolated instance that cannot be used without CloudFormation.
If the launch from the marketplace button is to make any sense, it should also create the CloudFormation bucket setup.
For how long have I used the solution?
I have been using the solution for 1 to 2 years.
Which solution did I use previously and why did I switch?
I am just starting to develop the product.
What's my experience with pricing, setup cost, and licensing?
Ant Media Enterprise Server gives value for money.
Which other solutions did I evaluate?
Wowza and Red5 Pro were contenders, but the implementation was not straightforward. Ant Media is already built on Red5 and has services from Wowza, so it became the default.
What other advice do I have?
The customer support for this product and service is on point.
If public cloud, private cloud, or hybrid cloud, which cloud provider do you use?
Amazon Web Services (AWS)
reviewer2799663
Secure video workflows have transformed remote financial inspections and digital verifications
Reviewed on Jan 27, 2026
Review from a verified AWS customer
What is our primary use case?
We use Ant Media to power secure, real-time video communication features within our SaaS platform. Specifically, we utilize it for remote inspection and digital verification workflows in the financial and insurance sectors, where low latency and high reliability are critical.
How has it helped my organization?
Ant Media has allowed us to meet strict security and compliance standards required by our enterprise clients without sacrificing performance. Previously, balancing high-quality video with sub-second latency in a regulated environment was a major challenge. Ant Media solved this, enabling us to launch seamless remote services, like eKYC and inspections, much faster than building infrastructure from scratch.
What is most valuable?
Ultra-low latency WebRTC is essential for the real-time interaction nature of our products. The flexibility and integration of Ant Media were impressive, as it integrated smoothly with our existing services. The AWS Marketplace deployment option removed the heavy lifting of infrastructure setup and maintenance, allowing our team to focus on product development.
What needs improvement?
The documentation is generally good, but more deep-dive examples for complex, custom edge-case configurations would be helpful for advanced developers.
For how long have I used the solution?
I have used this solution for 3 years.
Which solution did I use previously and why did I switch?
We switched because previous solutions, which were open source based, could not match the stability and latency performance required for enterprise-grade SLAs.
What's my experience with pricing, setup cost, and licensing?
The pricing is very competitive, especially considering the reduction in DevOps overhead. Using the AWS Marketplace version provides excellent value for the ease of scaling and management it offers.
Which other solutions did I evaluate?
We evaluated open-source alternatives like Janus and Jitsi. We ultimately chose Ant Media because its WebRTC technology was superior, and it offered the enterprise readiness and support that open-source projects lacked.
What other advice do I have?
If you are in a regulated industry such as Finance or Insurance and need a secure, scalable, and ultra-fast streaming solution, Ant Media is the right choice. It is reliable, flexible, and the support team is responsive.
If public cloud, private cloud, or hybrid cloud, which cloud provider do you use?
Amazon Web Services (AWS)
reviewer2745024
Integration into our medical video conferencing is smooth with continuous development and excellent support
Reviewed on Jul 24, 2025
Review from a verified AWS customer
What is our primary use case?
I use the solution for video conferencing in a medical setting.
How has it helped my organization?
AMS allowed us to integrate a streaming platform into our solution fairly easily, with great support from a very accessible developer and company.
What is most valuable?
It is easy to set up and integrate, and the support is excellent. The platform is also under continuous development.
What needs improvement?
For our use case, it is pretty good in its current form. However, the update process on AWS could be a little more streamlined. Even so, it is always done quickly, has never failed, and includes good follow-up from the company.
For how long have I used the solution?
I have been using the solution for 2 years.
Which solution did I use previously and why did I switch?
I did not use any previous solutions before this.
What's my experience with pricing, setup cost, and licensing?
The pricing of the product itself is more than fair. The total costs depend more on the AWS configuration. AMS does not require much in terms of the machine it runs on.
Which other solutions did I evaluate?
I evaluated various solutions before deciding on AMS, including options from both smaller suppliers and big tech companies.
What other advice do I have?
I have no additional advice to share.
If public cloud, private cloud, or hybrid cloud, which cloud provider do you use?
Amazon Web Services (AWS)