HomeTemplates › DeepSeek-R1 (full)
🧠 Self-hosted LLM

Full DeepSeek-R1, on a multi-GPU block

Full DeepSeek-R1 (671B) — SOTA reasoning

From
loading…
cheapest machine that meets this template
Deploy in one click →
Video memory
700 GB
Setup
~15 min
Access
port 8000
Billing
hourly, in BRL

The full R1 is a heavyweight reasoning model and needs a block of GPUs to fit in memory. This template brings up vLLM with sharding configured — you only choose the machine.

Full DeepSeek-R1 (671B MoE) served via vLLM with an OpenAI-compatible API. Frontier reasoning (AIME, math, code). NOTE: needs multiple H100/H200 GPUs or a quantized variant (tune tensor-parallel and the model). For a single GPU, use the DeepSeek-R1-Distill template.

What it is for

How to deploy

  1. Create your account and add balance (card or Pix, no subscription).
  2. In the console, pick the DeepSeek-R1 (full) template and a machine — the console hides the ones that do not meet the requirement.
  3. In about 15 minutes the setup finishes and the access address shows up in the panel, on port 8000.

Done? Just destroy the machine and billing stops with it. No contract, no minimum commitment.

FAQ

How much video memory?

On the order of 700 GB — a block of eight large cards. Check availability in the console before reserving.

Is there a cheaper option?

Yes, the distilled versions run on a single 24 GB card with much of the result.

How long until it answers?

Weight download is long. Plan a window of several minutes before the first test.

Run DeepSeek-R1 (full) today
You only pay for the hours the machine is running.
Deploy in one click →

Related templates

vLLM
OpenAI-compatible API for Llama, Qwen, Mistral and more
TGI (HuggingFace)
HuggingFace Text Generation Inference — vLLM alternative
LiteLLM Proxy
1 OpenAI endpoint routing to 100+ providers (cloud + local)
Ollama
Run DeepSeek, Qwen3, Llama and Mistral with one command