Continue setup (VS Code & JetBrains)

Continue is an open-source AI coding extension for VS Code and JetBrains. Copy one config.yaml, add your key, and use Claude and GPT.

Updated 2026-11-16

1. Get an API key

Sign up in the TokenMilo console, top up and create a key under API Keys.

2. Edit config.yaml

Open ~/.continue/config.yaml (gear icon in the Continue panel) and use:

# ~/.continue/config.yaml
name: TokenMilo
version: 1.0.0
schema: v1
models:
  - name: Claude Sonnet 5.5
    provider: anthropic
    model: claude-sonnet-5-5
    apiBase: https://api.tokenmilo.com/v1
    apiKey: sk-your-tokenmilo-key
    roles: [chat, edit, apply]
    defaultCompletionOptions:
      promptCaching: true
  - name: GPT-6.1 Sol
    provider: openai
    model: gpt-6.1-sol
    apiBase: https://api.tokenmilo.com/v1
    apiKey: sk-your-tokenmilo-key
    roles: [chat, edit, apply]

Note: Claude uses provider: anthropic with https://api.tokenmilo.com/v1 (with /v1); GPT uses provider: openai with https://api.tokenmilo.com/v1.

3. Check it works

Pick “Claude Sonnet 5.5” in the model dropdown, ask something, then check Usage Logs. Model IDs are in the model list.

FAQ

Why does the anthropic apiBase include /v1?

Continue’s Anthropic provider only appends /messages, so use https://api.tokenmilo.com/v1 — without it you get a 404.

Can I use Claude for tab autocomplete?

Not recommended. Autocomplete needs a dedicated completion model; Claude and GPT are best for the chat, edit and apply roles.

Does this work in JetBrains too?

Yes. Both the VS Code and JetBrains extensions read ~/.continue/config.yaml.

Related guides

Need an API key?

Sign up at TokenMilo, top up, and create a key in the console in under a minute.

Get API key See all models