DEVSAIO

Configure Continue (VS Code / JetBrains) with a custom model provider

Add Claude, GPT and Gemini to the Continue extension using one config file and one API key.

DEVSAIO team · 1 min read
Share on X

Continue is an open-source AI assistant for VS Code and JetBrains IDEs. Models are defined in a config file, so adding DEVSAIO models takes a minute.

Edit the config

Open Continue's settings and choose to edit the config file (config.yaml). Add models with the openai provider and a custom apiBase:

yaml
name: My assistant
version: 1.0.0
schema: v1
models:
  - name: Claude (DEVSAIO)
    provider: openai
    model: claude-sonnet-4-6
    apiBase: https://devsaio.lol/v1
    apiKey: YOUR_KEY
    roles: [chat, edit, apply]
  - name: GPT (DEVSAIO)
    provider: openai
    model: gpt-5.6-luna
    apiBase: https://devsaio.lol/v1
    apiKey: YOUR_KEY
    roles: [chat, edit]

Save, then pick the model from the dropdown in the Continue panel.

Autocomplete

Tab autocomplete needs a fast, cheap model because it fires constantly. Add a small model with the autocomplete role, and check your usage after a day of coding to make sure the cost suits you.

Tips

  • Use roles to decide which model does chat vs edits.
  • Keep the key out of shared repos; Continue also supports secrets and environment variables in its config. See their docs for the current syntax.
Try it with one API key

Claude, GPT, Gemini, DeepSeek, image and video models through one OpenAI- and Anthropic-compatible endpoint. Prepaid, pay only for what you use.

Keep reading