Continue setup

Continue is an open-source AI assistant for VS Code and JetBrains. Add Claudech models to its config.yaml with the openai provider and a custom apiBase.

Before you start#

A Claudech API key from API keys. API access unlocks after your first purchase.

Configuration#

Edit ~/.continue/config.yaml (or open it from Continue's settings):

YAML

models:
  - name: Claude Opus 5.5
    provider: openai
    model: claude-opus-5-5
    apiBase: https://api.claudech.com/v1
    apiKey: sk-...
    roles: [chat, edit, apply]
  - name: Claude Fable 5.1
    provider: openai
    model: claude-fable-5-1
    apiBase: https://api.claudech.com/v1
    apiKey: sk-...
    roles: [chat]
  - name: Claude Sonnet 5
    provider: openai
    model: claude-sonnet-5
    apiBase: https://api.claudech.com/v1
    apiKey: sk-...
    roles: [autocomplete]

Reload the window and pick a Claudech model in the chat panel's model selector.

Things to know#

Embeddings. Claudech does not offer an embeddings endpoint. Keep Continue's default embeddings provider for codebase indexing; chat and edits still run on Claudech.
Keys in files. If you share the config, use Continue's secrets support instead of pasting the key.

Troubleshooting#

Symptom	Fix
`401` or "invalid API key"	Re-copy the key without spaces; check it is active under API keys
`404 model_not_found`	`model` must be the Claudech model id exactly
Requests go to OpenAI	`apiBase` is missing or misspelled; it must be `https://api.claudech.com/v1`
`402 insufficient_balance`	Top up under Billing

See all integrations for other editors. Claudech is an independent service and is not affiliated with the makers of Continue.