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.

PrerequisitesCopy Anchor Link

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

SetupCopy Anchor Link

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-5.3 Flash",
      "provider": "openai",
      "model": "glm-5.3-flash",
      "apiKey": "sk-runars-...",
      "apiBase": "https://runars.ca/v1"
    }
  ]
}

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

Using itCopy Anchor Link

Select Runars GLM-5.3 Flash from the model dropdown in the Continue sidebar. Requests route through Runars and debit your organization's credit balance.

TroubleshootingCopy Anchor Link

"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 nextCopy Anchor Link

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