Developers &
Enterprise
Get started developing in minutes with the best open-source models including DeepSeek, Llama, and OpenAI running on SambaCloud. Easily grow to enterprise scale with dedicated infrastructure in the cloud or on-premises with SambaStack.
Learn more → Developers &Enterprise
Enterprise
Government &
Public Sector
Run AI workloads and manage your most sensitive operations entirely within your national borders with SambaStack for Public Sector — a scalable, high-performance solution designed for on-premises deployment in your nation’s most secure data centers.
Learn more → Government &Public Sector
Public Sector
Data Centers
AI demand is increasing and energy is limited. Build the most energy-efficient token generation AI factory using your existing footprint and energy with SambaStack for Data Center, a fully managed service you can stand up in just months.
Learn more → Data CentersAI agents that run in seconds, not minutes
Speed and latency matter. SambaNova delivers fast inference on the best and largest open-source models, powered by SambaNova’s RDUs.
Best performance on the largest models
AI models are getting bigger and more intelligent. SambaNova runs the largest models, including DeepSeek and Llama, with full precision and all the capabilities developers need.
Generate the most tokens for every kWh
Generate the maximum number of tokens per watt using the highest efficiency racks on the market.
DeepSeek
We support the groundbreaking DeepSeek models, including the 671-billion-parameter DeepSeek-R1, which excels in coding, reasoning, and mathematics at a fraction of the cost of other models.
On our SambaNova RDU, DeepSeek-R1 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. SambaNova Cloud 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
OpenAI's Whisper model — supported on our SambaNova RDU — has become a cornerstone for audio-based AI applications. By leveraging our platform's fast processing speeds, developers can unlock new use cases in voice-based AI agents to create more immersive experiences.
Introducing SambaManaged: A Turnkey Path to AI for Data Centers
OpenRouter uses SambaNova Cloud to deliver high speed LLM performance
SambaNova Launches its AI Platform in AWS Marketplace
SambaNova 2.0: Build with Relentless Intelligence
Introducing SambaManaged: A Turnkey Path to AI for Data Centers
DeepSeek R1-0528 is Live on SambaNova Cloud
Introducing Whisper Large-V3 to SambaNova Cloud
Qwen3 Is Here - Now Live on SambaNova Cloud
Meta Llama 4 Maverick & Llama 4 Scout on SambaNova Cloud
LLM-Judge for Multilingual Document Question Answering
The Only Inference Provider with High Speed Support for the Largest Models
