Continue

Continue is an open-source AI coding assistant for VS Code and JetBrains. It supports arbitrary OpenAI-compatible providers, so it works with Runars.

Prerequisites

• A Runars API key (Dashboard → API Keys), starting with sk-runars-
• Continue installed in your editor
• Credit balance on your organization

Setup

Open the Continue config (~/.continue/config.json on macOS/Linux, %USERPROFILE%\.continue\config.json on Windows) and add a model under "models":

{
  "models": [
    {
      "title": "Runars GLM 5.2",
      "provider": "openai",
      "model": "glm-5.2",
      "apiKey": "sk-runars-...",
      "apiBase": "https://api.runars.ca/v1"
    }
  ]
}

Save the file. The model appears in Continue's model dropdown.

Using it

Select Runars GLM 5.2 from the model dropdown in the Continue sidebar. Requests route through Runars and debit your organization's credit balance.

Troubleshooting

"Model not found": Confirm the "model" value matches an id returned by GET /v1/models. Unknown ids return 404 model_not_found rather than being silently substituted.

"401 Unauthorized": The API key is missing, wrong, or revoked. Keys are cache-invalidated within ~5s of revocation on Runars.

Embeddings / rerank: Continue's embeddings and rerank features use separate provider types ("embeddingModels", "rerankingModels"). Runars does not serve embeddings — leave those on their default provider or point them elsewhere.

What's next

• Install SDKs — Anthropic & OpenAI SDK setup
• Pricing & billing — credit model, rate limits, auto-reload