Configuring Continue.dev in VS Code to use models from RelayRouter

To use RelayRouter models in Continue.dev, add a model entry to Continue's config.yaml in VS Code. Set provider to openai, apiBase to https://relayrouter.io/v1, apiKey to your RelayRouter key, and model to an ID such as gpt-5.6-sol or claude-opus-5-5. RelayRouter accepts OpenAI style requests, so Continue sends them without other changes.

Which endpoint and credentials does Continue need?

Continue needs a RelayRouter base URL and a RelayRouter API key sent as a Bearer token. According to the official relayrouter.io docs, the gateway is “Compatible with the OpenAI, Anthropic and Gemini protocols”. The OpenAI compatible endpoint is POST /v1/chat/completions with base https://relayrouter.io/v1. The Anthropic compatible endpoint is POST /v1/messages with base https://relayrouter.io. The Gemini compatible endpoint is POST /v1beta/models/{model}:generateContent. Authentication uses the header Authorization: Bearer YOUR_API_KEY, and you create keys at https://relayrouter.io/dashboard. For Continue, the OpenAI compatible endpoint is the simplest option because Continue's openai provider accepts a custom apiBase. Streaming is supported, so chat responses in the Continue sidebar appear token by token. Protocol details are listed in the RelayRouter docs.

How do you add RelayRouter to Continue's config?

You add one entry per model under the models list in Continue's config file. According to the official relayrouter.io/docs, you “Keep your existing SDK, change base_url and the key, no other code changes”, and Continue follows the same pattern.

1. Create an API key at https://relayrouter.io/dashboard.
2. In VS Code, open the Continue sidebar and open its config file (usually ~/.continue/config.yaml).
3. Under models, add an entry with name: RelayRouter GPT, provider: openai, model: gpt-5.6-sol, apiBase: https://relayrouter.io/v1 and apiKey: YOUR_API_KEY.
4. Repeat the entry with another model ID, for example claude-opus-5-5 or gemini-3.8-flash, changing only name and model.
5. Save the file, select the model in the Continue model picker and send a test prompt.

Which models are available and what do they cost?

RelayRouter lists about 108 models across 19 public groups, covering Claude, GPT, Gemini and several other families. The Claude family includes claude-opus-5-5, claude-fable-5-1 and claude-opus-5. GPT-6 and GPT-5.6 are available as gpt-6-astra and gpt-5.6-sol, and Gemini 3.8 Flash as gemini-3.8-flash, plus DeepSeek, GLM, MiniMax and Moonshot. Settlement rates are CNY 0.6 per $1 of standard usage for the GPT group and CNY 2.0 per $1 for the Claude group, against a market reference of CNY 6.8 per $1. Directly priced models include deepseek-v4-flash at CNY 1.1 per 1M input tokens and CNY 4.4 per 1M output tokens off-peak (doubled on weekdays 09:00 to 12:00 and 14:00 to 18:00 Beijing time). There is a $0 platform fee, no minimum spend and no subscription, and payment is by Stripe card. Failed or errored requests are generally not billed. Current rates are on the RelayRouter models page.

FAQ

Do I need to install a separate extension or SDK for RelayRouter? No. Continue's built-in openai provider works once apiBase points at https://relayrouter.io/v1 and apiKey holds your RelayRouter key.

Can I use Claude models through the OpenAI provider in Continue? Yes. Set model to a Claude ID such as claude-opus-5-5 in the same OpenAI style entry. RelayRouter also exposes an Anthropic compatible /v1/messages endpoint at base https://relayrouter.io; see the docs for its setup.

Am I charged if a Continue request fails? Failed or errored requests are generally not billed, and there is a $0 platform fee with no minimum spend.