Deepseek
Configure Deepseek as a custom endpoint in LibreChat.
Archived documentation
You are reading the frozen documentation for v0.8.7, which is no longer maintained. Go to the latest docs.
Deepseek serves its chat, coder, and reasoner models through an OpenAI-compatible API that you can add to LibreChat as a custom endpoint.
Get an API key
Create a key from the Deepseek platform. Add it to your .env file:
DEEPSEEK_API_KEY=your-api-keyConfiguration
Add the endpoint under endpoints.custom in your librechat.yaml:
- name: "Deepseek"
apiKey: "${DEEPSEEK_API_KEY}"
baseURL: "https://api.deepseek.com/v1"
models:
default: ["deepseek-chat", "deepseek-coder", "deepseek-reasoner"]
fetch: false
titleConvo: true
titleModel: "deepseek-chat"
modelDisplayLabel: "Deepseek"Notes
deepseek-chatanddeepseek-coderwork with Agents and tools.deepseek-reasoner, codenamed "R1," is supported and streams its thought process, but some OpenAI API parameters may not work with it. R1 can also work with Agents when tools are not used.deepseek-chatis the preferred model for title generation.
