Use DeepSeek in Continue (VS Code and JetBrains)
Updated 2026-10-18 · A config.yaml example for the Continue coding assistant; works in IntelliJ IDEA and PyCharm too.
Connection details
- Base URL (OpenAI compatible)
- https://api.aifans.fan/v1
- API key
- Create one in the console; it starts with sk- (no account yet? sign up)
- Recommended models
- deepseek-v4.1-flash, deepseek-v4-pro (all models and prices)
Continue is an open-source AI coding assistant for VS Code and the JetBrains IDEs (IntelliJ IDEA, PyCharm, GoLand and more). You connect it to AIFans API in its config file.
Edit the config file
Open the Continue sidebar, go to its settings and open the config file (usually ~/.continue/config.yaml). Add under models:
name: My Config
version: 0.0.1
schema: v1
models:
- name: deepseek-v4.1-flash
provider: openai
model: deepseek-v4.1-flash
apiBase: https://api.aifans.fan/v1
apiKey: YOUR_API_KEY
roles: [chat, edit, apply]
- name: deepseek-v4-pro
provider: openai
model: deepseek-v4-pro
apiBase: https://api.aifans.fan/v1
apiKey: YOUR_API_KEY
roles: [chat, edit]
Save, then pick the model in Continue's model menu. provider: openai means “OpenAI-compatible API”, not “OpenAI models only”.
Notes
- Tab autocomplete needs a FIM completion endpoint; we offer chat endpoints only, so do not give these models the autocomplete role.
- The JetBrains plugin reads the same config file.
- Continue's config format changes from time to time; its own documentation is authoritative.