DeepSeek-R1 is available now with secure, compliant, dedicated deployments

Model library / DeepSeek

DeepSeek

A foundation model research lab dedicated to creating state-of-the-art open-source generative models

DeepSeek models

DeepSeek-R1

LLM

R1SGLangH200

DeepSeek-R1 Qwen 7B

LLM

R1QwenTRT-LLMH100 MIG 40GB

DeepSeek-R1 Qwen 32B

LLM

R1QwenTRT-LLMH100

DeepSeek-R1 Llama 70B

LLM

R1LlamaTRT-LLMH100

DeepSeek-V3

LLM

V3SGLangH200

About DeepSeek

DeepSeek is a foundation model research lab dedicated to creating commercially-licensed open-source LLMs.

DeepSeek's models include:

DeepSeek-R1, a reasoning model on par with OpenAI o1
DeepSeek-V3, a SOTA LLM that rivals GPT-4o
Distilled versions of R1 based on Qwen and Llama models that offer excellent reasoning capabilities on midsize LLMs.

Deploy any model in just a few commands

Avoid getting tangled in complex deployment processes. Deploy best-in-class open-source models and take advantage of optimized serving for your own models.

Start deploying

$

truss init -- example stable-diffusion-2-1-base ./my-sd-truss

$

cd ./my-sd-truss

$

export BASETEN_API_KEY=MdNmOCXc.YBtEZD0WFOYKso2A6NEQkRqTe

$

truss push

INFO

Serializing Stable Diffusion 2.1 truss.

INFO

Making contact with Baseten 👋 👽

INFO

🚀 Uploading model to Baseten 🚀

Upload progress: 0% | | 0.00G/2.39G