# One config.yaml block between Continue and every model

> Markdown mirror of https://router.one/integrations/continue for AI assistants and crawlers. Router One is an OpenAI-compatible LLM API gateway.
> Last updated: 2026-08-12

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.

## 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`

```bash
# ~/.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.

## See also

- All integration guides: https://router.one/integrations
- Debug 401/403/429 in Continue: https://router.one/llm-api-error-codes
- Open WebUI setup: https://router.one/integrations/open-webui
- Cline setup: https://router.one/integrations/cline
- What the gateway layer does: https://router.one/llm-api-gateway
- OpenAI-compatible API: https://router.one/openai-compatible-api
- API docs: https://router.one/docs
- Canonical page: https://router.one/integrations/continue
- Models and per-model token rates: https://router.one/models (markdown: https://router.one/models.md)
- Pricing: https://router.one/pricing
- API docs (markdown): https://router.one/docs.md
- Company facts: https://router.one/facts/company.md