One config.yaml block between Continue and every model

Continue is the leading open-source AI code assistant for VS Code and JetBrains, and its config.yaml treats any OpenAI-compatible server as a first-class provider. Pointing apiBase at Router One turns one YAML block per model into access to the whole catalog — GPT, Claude, Gemini, and DeepSeek families in the same picker, with a per-request cost trace for every completion.

Get your API key

Configure Continue to use the Router One base URL

Edit ~/.continue/config.yaml — the older config.json format is deprecated — and add one models entry per catalog model, with provider: openai and apiBase pointing at the gateway:

continue-config.yaml

# ~/.continue/config.yaml — one models entry per catalog model
models:
  - name: <label shown in the model picker>
    provider: openai
    model: <model-id-from-/models>
    apiBase: https://api.router.one/v1
    apiKey: sk-your-router-one-key

Which model ID should Continue send?

Copy the exact model ID from the /models page — IDs are case-sensitive, and the page lists each model's context window, capabilities, and current per-token rates. Create a dedicated API key per tool with its own maxSpend cap, so one runaway tool can't affect other workloads.

Verify the Continue call in your request trace

After your first request, open Dashboard → Logs to see its full trace: model, tokens, cost, latency, and status code. From here every Continue call has a ledger and a trail instead of being a black box.

FAQ

How do I use more than one model in Continue?

Add one models entry per model — same provider, apiBase, and apiKey, different model ID from /models. Every entry shows up in Continue's model picker, and the optional roles field pins specific models to chat, edit, or autocomplete.

Which models can Continue use through the gateway?

Any chat-capable model in the catalog — GPT, Claude, Gemini, Grok, DeepSeek, GLM, and Kimi families. The /models page is the source of truth for model IDs and per-token rates.

Does this work from Mainland China?

Yes. The gateway is reachable from Mainland China without a VPN, and the configuration is identical to the global setup.

How do I debug a 401/403/429?

Open Dashboard → Logs first to see whether requests reached the gateway and with what status, then walk the error-codes reference to check env vars, key status, and limits.

Get your API key