> Source: https://meetrix.io/store/deepseek-r1/
> Markdown copy of that page. Cite the URL above, not this file.

[Store](https://meetrix.io/store/)  DeepSeek-R1 7B

Open-source reasoning model

# Self-hosted DeepSeek-R1 7B on AWS

Run DeepSeek-R1 7B, a distilled model built on Qwen-7B, behind an OpenAI-compatible API on a GPU instance in your own AWS account.

 [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-oazhlpdnfvmzo)

-   OpenAI-compatible API
-   Strong in Chinese and multilingual
-   Pay per hour

![Self-hosted open-source LLMs on AWS by Meetrix](https://meetrix.io/assets/store/deepseek-r1/deepseek-r1.webp)

## What is DeepSeek-R1 7B?

DeepSeek-R1 7B is a distilled version of DeepSeek R1 built on the Qwen-7B architecture. It is efficient to run, strong at Chinese-language tasks and capable across other languages.

-   ### Distilled reasoning

    DeepSeek R1 capabilities in a 7B model.

-   ### Multilingual

    Optimised for Chinese with strong multilingual support.

-   ### OpenAI-compatible API

    Use OpenAI SDKs with your own endpoint.

-   ### API docs

    Browse and test the API at /docs on your server.

-   ### g4dn GPU instances

    Runs on g4dn instance types in your account.

-   ### Private by default

    Prompts and outputs stay in your own account.

## What's in the Meetrix DeepSeek-R1 AMI

The AMI ships the model and an OpenAI-compatible API server on Ubuntu 22.04.

-   DeepSeek-R1 7B with an OpenAI-compatible API
-   API documentation at /docs
-   Automatic SSL when your domain is hosted on Route 53
-   A certificate script for issuing SSL manually otherwise
-   A CloudFormation template for your own AWS account
-   Optional support from Meetrix

## How to set up a self-hosted DeepSeek-R1 API

1.  ### Check your quota

    Make sure your account has vCPU quota for g4dn instances in your region.

2.  ### Launch the stack

    Subscribe on AWS Marketplace, accept the terms and launch the CloudFormation stack.

3.  ### Point your domain at it

    Create a DNS record for your domain with the server's public IP.

4.  ### Call the API

    Open /docs on your domain or IP, then point your OpenAI client at your server.

## Deploy on AWS

### DeepSeek-R1 7B on AWS

An AMI on AWS Marketplace, launched on a g4dn GPU instance in your own AWS account with a CloudFormation stack.

Deploys with

CloudFormation

Instance family

g4dn (GPU)

OS

Ubuntu 22.04

#### Setup guides

-   [**Developer guide** Launch, SSL, API endpoints, testing](https://meetrix.io/blogs/deepseek-developer-guide/)
-   [**Best open-source LLMs to self-host** How DeepSeek compares](https://meetrix.io/blogs/best-open-source-llms-self-hosted-2026/)
-   [**Self-host an OpenAI-compatible API** Point your SDK at your own server](https://meetrix.io/blogs/openai-compatible-api-self-hosted/)

 [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-oazhlpdnfvmzo)

## DeepSeek-R1 7B API

The server follows the OpenAI API, so clients only need a new base URL.

| Feature | Supported |
| --- | --- |
| Chat and text completions | Yes |
| Model listing | Yes |
| Embeddings | No |
| Interactive docs at /docs | Yes |

## DeepSeek-R1 7B FAQ

What is DeepSeek-R1 7B?

A distilled DeepSeek R1 model built on the Qwen-7B architecture, optimised for Chinese with strong multilingual ability.

Is it OpenAI API compatible?

Yes. Browse the API at /docs on your domain or public IP and use OpenAI SDKs against your server. Embeddings are not supported.

Which instances can I use?

g4dn instances, from g4dn.xlarge up to g4dn.metal.

How is it billed?

Per hour of software use, which varies by instance type, plus the EC2 instance. A 365-day contract is also available.

How do I SSH into the server?

Use your key pair with the ubuntu username.

What if SSL does not set up automatically?

That happens when the domain is not on Route 53. Run the certificate script on the server manually.

## Self-hosted LLM guides

### [DeepSeek R1: Developer Guide](https://meetrix.io/blogs/deepseek-developer-guide/)

Launch the stack, set up SSL and test the API.

### [Best Open Source LLMs to Self-Host in 2026](https://meetrix.io/blogs/best-open-source-llms-self-hosted-2026/)

DeepSeek, Llama, Qwen and more, compared for self-hosting.

### [Self-Host an OpenAI-Compatible LLM API on AWS](https://meetrix.io/blogs/openai-compatible-api-self-hosted/)

Swap the OpenAI base URL without rewriting app code.

### [How to Deploy DeepSeek Coder in AWS](https://meetrix.io/blogs/how-to-install-deespseek-coder/)

The DeepSeek model built for code.

## Need a hand with DeepSeek?

We build and run self-hosted AI infrastructure every day, from model selection to GPU sizing. Tell us what you need.

[Contact us](https://meetrix.io/contact-us/)