Deploy DeepSeek-R1 on secure, dedicated infrastructure
Get dedicated deployments of DeepSeek models with full control, compliance, and security, running on Baseten Cloud or in your VPC.
++++Get OpenAI quality with more control and lower costs
Unlock dedicated deployments
Launch DeepSeek on Baseten's optimized infrastructure with multi-node, multi-cluster support, fully managed with global availability.
Get enterprise-grade performance
Get the lowest latencies and highest throughputs at scale with Baseten's specialized model performance optimizations.
Cut costs versus OpenAI
Get leading quality and performance at a fraction of OpenAI's cost on Baseten Cloud, Self-hosted, or Hybrid deployments.
++++Secure deployments designed for performance at scale
Deploy any DeepSeek model
With native support for DeepSeek-R1, V3, and distillations, Baseten is the first US-based platform to offer dedicated and self-hosted DeepSeek deployments, as featured by the Latent Space Podcast and The New York Times.
Run multi-node inference
Baseten engineers optimized the complicated orchestration required to split such large models across nodes and clusters. This unlocks serving DeepSeek-R1 on H100 GPUs, ensuring capacity at scale.
Host in your VPC
Deploy DeepSeek directly into your VPC on any cloud provider with Baseten Self-hosted or Hybrid. We support deployments exclusively in US and EU data centers, and model data will never leave your cloud.
Lower inference costs
With performance optimizations at the infrastructure, model, and networking layers, our deployments are cheaper, faster, and more reliable than OpenAI’s hosted models. For cost-sensitive workloads, you can use DeepSeek-R1 distillations for up to 32x cost savings, including Qwen 7B, Qwen 32B, and Llama 70B.
Get started
DeepSeek on Baseten
Try DeepSeek-distilled Qwen 32B
Impressive reasoning capabilities at a more efficient footprint. Try distilled Qwen 32B in two clicks from our model library.
Launch DeepSeek-distilled Llama 70B
Same exceptional Llama, now distilled from DeepSeek-R1. Deploy it on an H100, optimized with TensorRT-LLM.
Learn about DeepSeek on Latent Space
Discover what makes DeepSeek unique yet challenging to run from Baseten Co-founder Amir and Inference Engineer Yineng.
You guys have literally enabled us to hit insane revenue numbers without ever thinking about GPUs and scaling. I know I ask for a lot so I just wanted to let you guys know that I am so blown away by everything Baseten.
Rime’s state-of-the-art p99 latency and 100% uptime is driven by our shared laser focus on fundamentals, and we’re excited to push the frontier even further with Baseten.
Baseten enabled us to achieve something remarkable—delivering real-time AI phone calls with sub-400 millisecond response times. That level of speed set us apart from every competitor.
A week ago we reached out with a hefty goal and within days your team helped us get set up and stable for a launch. It went smoothly, entirely thanks to you guys. 100% couldn’t have gone live without the software and hardware support you guys worked through the weekend to get us. The custom optimized Whisper on Baseten’s autoscaling L4 GPUs saved us.
Inference for custom-built LLMs could be a major headache. Thanks to Baseten, we’re getting cost-effective high-performance model serving without any extra burden on our internal engineering teams. Instead, we get to focus our expertise on creating the best possible domain-specific LLMs for our customers.
You guys have literally enabled us to hit insane revenue numbers without ever thinking about GPUs and scaling. We would be stuck in GPU AWS land without y'all. Truss files are amazing, y'all are on top of it always, and the product is well thought out. I know I ask for a lot so I just wanted to let you guys know that I am so blown away by everything Baseten.
Baseten gets the stuff we don't want to do out of the way. Now, our small, scrappy team can punch above our weight. It's everything from model serving, to auto-scaling, to iterating on products around those models, so we can deliver value to our customers and not worry about ML infrastructure.
Baseten provides an easy way for us to host our models, iterate on them, and experiment without worrying about any of the DevOps involved.
Baseten has allowed us to efficiently build an entirely new machine learning platform in just 4 months. By not needing to worry about managing our model infrastructure, Laurel has been able to drastically reduce our time to develop new predictive features and maintain more than double the number of models from our old platform.
Explore Baseten today
We love partnering with companies developing innovative AI products by providing the most customizable model deployment with the lowest latency.
