Configure Router One models in Continue's config.yaml
Continue is an open-source AI code assistant for VS Code and JetBrains. Its openai provider can connect to Router One through apiBase in config.yaml. This guide sets up Chat Completions: choose compatible models from the current catalog, add one entry per model, and verify each request in the gateway cost trace.
Configure Continue to use the Router One base URL
For a new ~/.continue/config.yaml, use the complete example below, including the required name, version, and schema fields. For an existing file, keep those fields and merge the entry into its models list. Replace the key and model ID with your own; choose a model that supports Chat Completions. useResponsesApi: false keeps this example on /v1/chat/completions, because Continue otherwise defaults to Responses for o-series and GPT-5 models. The older config.json format is deprecated:
# ~/.continue/config.yaml — merge into models if this file already exists
name: Router One
version: 1.0.0
schema: v1
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
useResponsesApi: false
roles: [chat]Which model ID should Continue send?
Copy the exact model ID from /models, preserving case, hyphens, and version suffixes; do not substitute a display name. Open its detail page and match the supported API endpoints, context window, and capabilities such as tool calling to the provider and features selected in Continue. A catalog listing does not mean the client can use every feature of that model. Give each tool a dedicated API key with a maxSpend cap.
Which API protocol is Continue using?
OpenAI-compatible describes an interface format; it does not make Chat Completions (/v1/chat/completions), Responses (/v1/responses), and Anthropic Messages (/v1/messages) interchangeable. Check the installed client version, provider configuration, and actual request path against the model detail page and API compatibility fact sheet. A successful plain-text chat does not establish support for hosted tools, conversation state, or file-editing features.
Verify the Continue call in your request trace
Send a simple text request from Continue, then match its trace in Dashboard → Logs by time, model, and request_id: tokens, cost, latency, and status. Next, test streaming, tool calls, and multi-turn history separately. For failures, retain the actual request path, full error message, and request_id. If there is no matching log, check client configuration and connectivity before attributing the error to the gateway or upstream.
FAQ
How do I use more than one model in Continue?
Add one entry to the existing models list per compatible model — same provider, apiBase, and apiKey, with a different exact ID from /models. Keep useResponsesApi: false for entries using this Chat Completions setup. The example uses roles: [chat]; add edit or autocomplete only after checking that model and testing the role. Agent mode also needs supported tool calling; a successful chat alone does not establish that support.
Which models can Continue use through the gateway?
Choose a current catalog model that supports both the endpoint and the features Continue uses. Check /models and the model detail page for the exact ID, current rates, and capabilities; a family name such as GPT or Claude is not a compatibility guarantee. Seeing a model in the picker confirms discovery, so verify an actual request too.
Models are listed, but requests fail with 400 or 404. What should I check?
Record the actual request path and error message, then check the exact model ID. A 400 can indicate invalid parameters, unsupported tools, or a model/endpoint mismatch; a 404 can indicate an incorrect path or missing resource, so it does not by itself establish that a model was retired. If the error says must be called via, use the named endpoint or select a model supported on the current endpoint. Do not add or remove /v1 or /chat/completions across all clients indiscriminately.
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 401/402/403/429?
Match the request and error message in Dashboard → Logs. For 401, check whether the key was sent and is valid; for 402, check wallet balance and maxSpend; for 403, check key permissions and access restrictions. For 429, distinguish request/token limits from upstream throttling using the error details. Keep the request_id and follow the error-codes reference.