Skip to content
Compare NVIDIA technologies
Pick up to four. The comparison starts by saying whether they compete, work together or sit in different layers, then lines up their verified facts. It never names a universal winner.
How they relate
NVIDIA Metropolis and NVIDIA DeepStream SDK work together.
From the published profiles: same product family.
Side by side
| Fact | NVIDIA Metropolis | NVIDIA DeepStream SDK |
|---|---|---|
| Type | Platform | Framework |
| Layers | Applications & solutions, Models & frameworks, Inference & runtime software | Applications & solutions, Inference & runtime software, Accelerated computing |
| What it is | NVIDIA Metropolis is a vision AI application platform and partner ecosystem. It bundles models, libraries and blueprints, such as the Video Search and Summarization (VSS) blueprint, DeepStream and TAO, for building video analytics agents that turn camera streams into events, alerts, search and reports. | DeepStream is NVIDIA's toolkit for building real-time video and multi-sensor analytics pipelines on GPUs and Jetson devices. It is based on GStreamer and part of Metropolis. Its source code has been on GitHub under Apache-2.0 since version 9.0, while the prebuilt runtime libraries stay under an NVIDIA license. |
| Who needs it | Developers, integrators and software vendors who build camera-based analytics for factories, warehouses, retail stores, airports, cities and roads. Operations teams that need to search or summarize large amounts of video, or verify alerts, while keeping video on premises. | Teams that must analyze many camera streams continuously with low latency: traffic and smart city projects, retail and warehouse analytics, factory inspection and safety monitoring. It fits developers comfortable with Linux, GStreamer concepts and C++ or Python, who deploy on NVIDIA GPUs in servers, workstations or Jetson modules. |
| What it is not | Metropolis is not a camera, a video management system or a finished app you install; it is a developer platform, and finished products come from partners or your own team. DeepStream is one part of Metropolis, not the whole of it. The VSS blueprint is not meant to face untrusted networks: NVIDIA states it assumes authentication, TLS and access control are supplied by the surrounding infrastructure. Privacy, consent and legal compliance for camera analytics remain the deployer's responsibility. | DeepStream is not a finished video management system or a dashboard; it is the processing engine you build one with. It is not the same as Metropolis: Metropolis is the wider platform and partner program, and blueprints such as Video Search and Summarization sit on top of DeepStream. It is also not fully open source, because the prebuilt runtime libraries ship under an NVIDIA software license. Speech features are no longer part of it; NVIDIA points speech work to Riva. |
| Prerequisites |
|
|
| Runs on | Edge: IGX Thor, AGX Thor and DGX Spark, On-premises GPU servers (H100, L40S, RTX PRO 6000 Blackwell), Kubernetes with Helm, Cloud GPU instances, including Brev launchables, Partner solutions from the Metropolis ecosystem | x86 servers and workstations with NVIDIA GPUs, Arm servers (SBSA), including DGX Spark, through the DeepStream container, Jetson Orin and Jetson Thor modules, Cloud instances with NVIDIA GPUs, Kubernetes clusters with Helm |
| Availability and licensing | Per the VSS documentation, the blueprint's deployment files and scripts are under Apache 2.0, while its microservices are under the NVIDIA Software and Model Evaluation License Agreement; bundled models, NIM microservices, Elasticsearch and sample data each carry their own license. We recommend checking production terms with NVIDIA before going live. NVIDIA states VSS should run in a trusted, isolated network. | DeepStream 9.1 is the current release in the documentation. The GitHub repository's source code is Apache-2.0 and its documentation CC-BY-4.0, while the prebuilt runtime libraries and packages are released under NVIDIA's Software License Agreement for SDKs; NVIDIA notes that a few libraries remain closed. The repository is maintained but does not accept code contributions. DeepStream is also available as part of NVIDIA AI Enterprise, which adds validation, support and API stability. No price is stated for the SDK itself. |
| When something simpler is enough | If you need basic people counting, line crossing or motion alerts, the analytics built into many cameras or video management systems may, in our view, be enough. For occasional analysis of single images, a hosted vision API is quicker to adopt. A single fixed inspection check on a production line can often be done with a classic machine vision system. If nobody will act on the alerts, adding AI to the video will not create value. | If you analyze a handful of recorded videos offline, a Python loop with OpenCV or FFmpeg and a model framework is simpler and good enough. If you only need motion alerts or recording, the camera or video management software you already have may cover it. If the goal is to ask questions about video in natural language rather than build a custom pipeline, start from the Metropolis Video Search and Summarization blueprint instead of raw DeepStream. Hosted video AI services can also fit when data may leave the site and stream counts are small. |
| Last reviewed | 9 Oct 2026 | 9 Oct 2026 |
| Official resources | Product page (opens in a new tab) Documentation (opens in a new tab) | Product page (opens in a new tab) Documentation (opens in a new tab) |
Each value comes from the technology's profile, where every statement links to its source. Pricing, benchmark and compatibility claims are not shown unless a profile documents them.
Thank you. Your correction was sent.
The editors check it against the sources. If you left an email address, they may reply about it.