Use Nivana in Continue

Continue, the open-source coding assistant for VS Code and JetBrains, can use any OpenAI-compatible model. With Nivana, each chat or edit goes to the model that measures best for that request.

What you need

• A Nivana API key: sign in, open the account menu and choose API keys. New accounts get 2,000 free credits.
• The base URL https://nivana.one/v1 and the model name nivana/auto (or nivana/quality, nivana/speed, nivana/cost to lean the router one way).

Set up Continue

models:
  - name: Nivana
    provider: openai
    model: nivana/auto
    apiBase: https://nivana.one/v1
    apiKey: nvn_sk_…
    roles: [chat, edit, apply]

Add apply and agent to roles to use Nivana in agent mode too: the endpoint supports tool calling, and each step goes to the model that measures best for it.

Limits

Tool calling works: the client’s tools are passed to the routed model, which can call them, and each step is routed on its own. JSON mode and sampling parameters (temperature, max tokens) are ignored, Nivana’s own web search is off when the client sends tools, and very long tool histories are not summarised, so a request larger than every model’s context window fails.

Every response’s model field names the model that actually answered. See the OpenAI-compatible endpoint and how routing works.