Docs
Docs Connecting to DeepSeek

Connecting to DeepSeek

Last updated: August 10, 2026

Eviory OS supports connecting directly to DeepSeek’s official API, allowing you to use models like deepseek-v4-flash or deepseek-v4-pro at blazing fast speeds and low costs.

Because Eviory OS uses a Bring-Your-Own-Key (BYOK) model, your API requests go directly from your browser to DeepSeek.

1. Getting your DeepSeek API Key

  1. Go to the DeepSeek Platform and sign in.
  2. Navigate to the API Keys section.
  3. Click Create new secret key. Give it a recognizable name (e.g., Eviory OS).
  4. Copy the generated API Key. (It usually starts with sk-).

2. Configuring Eviory OS Settings

Once you have your API key, you can plug it into Eviory OS.

  1. Open Settings inside Eviory OS.
  2. Navigate to the AI Integrations tab.
  3. Scroll down to the Custom Local AI / Proxy section.
  4. Fill in the fields exactly as follows:
  • Base URL: https://api.deepseek.com/v1
  • API Key: Paste your DeepSeek key here
  • Model ID: Enter the specific DeepSeek model (e.g., deepseek-v4-flash or deepseek-v4-pro).
  1. Click Save Changes.

Eviory OS will now route all AI inference tasks through DeepSeek!