What this does

Configures Continue.dev to send requests to a privately hosted model served over any OpenAI-compatible REST endpoint, enabling use of fine-tuned or specialized models behind a custom API. After completion, Continue routes completions to the specified endpoint.

Steps

Determine the endpoint details. Identify the base URL, model name path, and authentication method. Example: https://model.example.com/v1 with a Bearer token.
Open the Continue config file. Click the gear icon in the Continue sidebar or edit ~/.continue/config.json.

Add a model entry for the custom endpoint.

{
  "title": "Custom Model",
  "provider": "openai",
  "model": "your-model-name",
  "apiBase": "https://model.example.com/v1",
  "apiKey": "your-token-here"
}

Set it as the default. Place the new entry first in the models array.
Save and reload the window. Run "Developer: Reload Window" and verify the connection with a test prompt.

Verification

curl -s -H "Authorization: Bearer YOUR_TOKEN" \
  https://model.example.com/v1/models | python3 -m json.tool | head -10
# Expected: JSON list of available models on the custom endpoint

Common failures

TLS certificate error — Self-signed certificates cause failures. Add the CA bundle to the system trust store.
CORS blocked requests — Ensure the model server sets Access-Control-Allow-Origin headers.
401 Unauthorized — The API key is missing or malformed. Verify the token format.
Model name mismatch — Must exactly match the name registered by the server. Check with /v1/models.
Endpoint unreachable — Test with curl directly from the machine running VS Code.

Operator checkpoint

Before treating this as solved, write down the local runtime, model or package version, hardware/backend if relevant, and the verification output. This keeps the guide useful as a Will-It-Run style decision instead of a one-off command transcript.

How to use Continue.dev with custom model endpoints

What this does

Steps

Verification

Common failures

Operator checkpoint

Related guides