Skip to main content
V3Code is BYOK-friendly: point it at your own model provider keys and it runs against them directly. Your keys live locally and only the calls you make go out — see Privacy.

​
When you need a key

  • Free Auto router requires your own Anthropic API key. Free Auto rides Anthropic’s stack to route between Haiku, Sonnet, Opus, and Fable, so it needs your Anthropic key set. See Models overview.
  • Any provider you want to run yourself — set the key and use that model directly instead of hosted credits.

​
Run models locally

V3Code runs local models right in the editor — fully offline, free, and private, with nothing leaving your machine.
  • Ollama — point V3Code at your running Ollama and it lists your installed models to pick from. (If a call fails, it’s usually because Ollama is powered off.)
  • Built-in local inference — V3Code can download and run models itself, with no separate server to set up. Models are stored locally and run inside the editor.
Local models pair naturally with the semantic index, which already runs its embeddings on-device — so you can work with a fully local setup end to end.

​
Hosted vs. BYOK

  • Hosted (paid plans) — V3Code runs inference for you on its own models and credits; nothing to set up. See Plans and Token wallet.
  • BYOK — you supply the key and pay your provider directly. Good if you already have provider credit or want full control of the model.