Continue is no longer maintained: its Router One config.yaml, and where to move next
Continue, the open-source coding assistant for VS Code and JetBrains that also ships a CLI, is no longer maintained. Its README says the continuedev/continue repository is no longer actively maintained and is read-only for all users, after a final 2.0.0 release of the VS Code extension, CLI and JetBrains plugin; the last VS Code builds, 2.0.0 and the 2.1.0 pre-release, are dated June 19, 2026. The extension still installs, and a local ~/.continue/config.yaml keeps working with the Router One setup below: the openai provider's apiBase points at the gateway, and each request is a Chat Completions call with its own cost trace. Expect no fixes or new model support, so for a new setup pick a maintained tool that takes the same base URL, key and model ID: Cline, Kilo Code, or GitHub Copilot's Custom Endpoint provider, compared further down. Checked against Continue's README and GitHub releases on 2026-09-29.
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
# Continue 2.x is its final release; Cline and Kilo Code take the same values
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]Where to move from Continue
Your Router One values carry over unchanged: the base URL https://api.router.one/v1, a key from the dashboard and an exact model ID from /models go into the OpenAI-compatible settings of any tool below. Continue's README recommends its CLI over its JetBrains plugin, but the CLI lives in the same read-only repository, so it is not a maintained path either. Give the new tool its own key with a maxSpend cap and compare the two in Dashboard → Logs before you remove Continue.
| If you used Continue for… | Consider | Why |
|---|---|---|
| An open-source agent in VS Code or JetBrains | Cline | Its OpenAI Compatible provider takes the same Base URL, key and model ID; it also ships a CLI, and per Cline's docs its JetBrains plugin takes your own provider key |
| A default model per mode, with the model list fetched from the gateway | Kilo Code | A custom provider set to OpenAI Compatible; each agent keeps its own default model |
| Chat and agent sessions inside GitHub Copilot | GitHub Copilot (Custom Endpoint) | BYOK models run on your key without a Copilot plan; inline suggestions stay on GitHub's service |
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 client or application a dedicated API key with a maxSpend cap. A key's spend cap (maxSpend) limits what that key can charge to your wallet: once its cumulative wallet charges reach the cap, its wallet-billed requests return HTTP 402. Requests covered by your plan's quota draw from the account's shared plan quota and do not count toward any key's 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, the wallet charge or plan quota it used, 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, either the request never reached the gateway (client configuration or connectivity) or the gateway refused it before calling a model — a 401 for the key, a 402 for funds, a 429 from your key's or account's limits, or a 400 or 404 for the model ID or endpoint; a streamed request that failed before any output may have no log either. The status and error message the client received tell which, so check them before attributing the error to the gateway or upstream.
FAQ
Continue is no longer maintained. Does my Router One configuration still work?
Yes. Nothing changed on Router One's side: the apiBase https://api.router.one/v1, your key and the catalog model IDs work the same. On Continue's side, its README says the repository is no longer actively maintained and is read-only for all users, after a final 2.0.0 release; the extension still installs and a local config.yaml keeps working, but it will get no fixes and no support for new models or API changes. Moving to a maintained tool is the safer path, and the same three values work in Cline, Kilo Code or GitHub Copilot's Custom Endpoint provider.
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 tool should I move to?
Cline if you want an open-source agent with per-step approvals, in VS Code, in JetBrains IDEs or as a CLI. Kilo Code if you want a default model per agent and a model list fetched from the gateway. GitHub Copilot's Custom Endpoint provider if you already work in Copilot and want chat and agent sessions on your own key. All three take the Router One base URL, key and exact model IDs, so try one with a separate key and a maxSpend cap before you switch fully.
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. A client that lists a model has only read the ID, from its own configuration or from GET /v1/models; 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?
Start from what your client received: the status, the error body and the X-Request-ID header. A 401 (missing, unknown, revoked or expired key), a 402 (wallet balance, or the key's maxSpend cap) and a 429 from your key's or account's rate limits are refused before any model is called, so they never appear in Dashboard → Logs — nor does a 400 or 404 for a wrong model ID or endpoint. For 401, check that the full key is sent and still active in Dashboard → API Keys; for 402, top up or raise the key's maxSpend; for a 403, keep the full error body. For 429, back off and retry later; a 429 that does show up in Logs came back from upstream after the gateway's retries. Keep the request_id and follow the error-codes reference.