Purpose-built for
scalable AI inference
Our custom dataflow technology and three-tier memory architecture delivers energy efficiency for fast inference and model bundling.
.png?width=421&height=356&name=SN50%20Homepage%20Banner%20Chip%20Cropped%20v3%20(1).png)
A solution purpose-built for agentic inference
Introducing the SN50 RDU - our fifth-generation AI chip!
The only chip that can deliver the speed and throughput required for agentic AI.
Inference stack by design
Inference at scale
The groundbreaking dataflow technology and memory architecture delivers the performance and speed required for ever-growing AI models.
Energy efficiency
Generating the maximum number of tokens per watt with the highest power efficiency naturally enables fast inference and scalability.
Infrastructure flexibility
SambaStack switches between multiple frontier-scale models, enabling complex agentic AI workflows to execute end-to-end on one node.
Why Modern Al Infrastructure Demands Model Bundling
The Goldilocks Zone for agents
The SN50 delivers 3X the savings compared to competitive chips for agentic inference. Co-Founder and Chief Technologist Kunle Olukotun explains how SN50 tiered memory allows agents to have access to a cache for models and prompts, further improving efficiency.
Sovereign AI Around the World
Meet our network of sovereign AI data center partners. Powered by SambaNova, each delivers top-tier performance and the flexibility of open source within their national borders.
Stay on top of AI trends, data & news
Developers & Enterprises
Build with relentless intelligence
Start building in minutes with the best open-source models including DeepSeek, Llama, and gpt-oss. Powered by the RDU, these models run with lightning-fast inference on SambaCloud and are easy to use with our OpenAI-compatible APIs.
SambaStack
The only chips-to-model computing built for AI
Inference | Bring Your Own Checkpoints
SambaNova provides simple-to-integrate APIs for Al inference, making it easy to onboard applications. Our APIs are OpenAI compatible allowing you to port your application to
SambaNova in minutes.
Auto Scaling | Load Balancing | Monitoring | Model Management | Cloud Create | Server Management
SambaOrchestrator simplifies managing AI workloads across data centers. Easily monitor and manage model deployments and scale automatically to meet user demand.
SambaRack™ is a state-of-the-art system that can be set up easily in data centers to run Al inference workloads. SambaRack SN40L-16 is our fourth generation system optimized for low power inference (average of 10 kWh) and running many models simultaneously.
SambaRack SN50 is our fifth-generation system optimized for fast agentic inference at a fraction of the cost running the largest models, like gpt-oss-120b and DeepSeek.
At the heart of SambaNova's innovation lies the RDU. With a unique three-tier memory architecture and dataflow processing, RDU chips are able to achieve much faster inference using a lot less power than other architectures.
-
Complete AI platform that provides a fully integrated end-to-end agentic AI stack – spanning across agents, models, knowledge, and data.
-
Composable AI platform that is open, unifies structured and unstructured data, queries in any environment, and deploys on any AI model. Build or use pre-built AI agents — all with business-aware intelligence.
-
Sovereign AI platform that keeps data secure and governed while business teams query in any environment. IT stays in control, while business teams self-serve AI — and both can focus on what matters.
Hume AI delivers realistic voice AI real-time with SambaNova
Build with the best open-source models
DeepSeek
We support the groundbreaking DeepSeek models, including the 671-billion-parameter DeepSeek-V3.1, which excels in coding, reasoning, and mathematics at a fraction of the cost of other models.
On our SambaNova RDU, DeepSeek-V3.1 achieves remarkable speeds of up to 200 tokens / second, as measured independently by Artificial Analysis.
Llama
As a launch partner for Meta's Llama 4 series, we've been at the forefront of open-source AI innovation. SambaCloud was the first platform to support all three variants of Llama 3.1 (8B, 70B, and 405B) with fast inference.
We are excited to work with Meta to deliver fast inference on both Scout and Maverick models.
OpenAI gpt-oss-120b
OpenAI recently released gpt-oss-120b, a model that delivers high accuracy in just 120-billion parameter with a Mixture of Experts (MoE) architecture.
As a small but efficient model, it runs extremely fast on SambaNova RDUs at over 600 tokens per second, making it a great choice for near real-time agentic AI.