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