Connect Continue

Add a text model to Continue's local YAML configuration with a custom API base and a private secret reference.

AELDER · SERVICE BASE URL

https://aelder.dev/v1

LOCAL CONFIGURATION

Let my agent set this up

Copy this task to an agent already running on your computer. Enter your API key locally when asked.

Help me connect Continue to AELDER using this guide: https://aelder.dev/docs/continue/
Service Base URL: https://aelder.dev/v1
First inspect my installed version, active profile and configuration. Explain any mismatch with the guide before changing anything.
Use the documented local configuration or CLI method. Do not automate the GUI, install software or change permissions without asking.
Preserve existing accounts, providers, models, defaults, permissions and unrelated settings. Propose the smallest change, show a redacted diff, and back up any files before editing.
Have me enter my API key locally using the tool's secret storage or an environment variable. Never ask me to paste a key into chat, print it, or include it in a command, diff, log or commit.
Use the exact model ID I choose from my account's model list. Do not invent model IDs or assume every model supports every API format or tool feature.
Validate syntax and configuration loading before making any generation request. If there is no dry-run, say so.
Explain any proposed paid test, the model and what it sends, and ask for approval before running it. Do not send project files or private conversation history as a test.
Finish with the settings changed, checks performed and steps to restore the backup.

Continue’s OpenAI provider accepts a custom API base. This guide configures the existing editor extension for Chat Completions; it does not configure VS Code’s separate built-in chat.

Prepare your service key and an exact model ID from our models endpoint.

1. Add the model to your local configuration

Open Continue’s active local config.yaml from its configuration controls. The usual user file is ~/.continue/config.yaml on macOS/Linux or %USERPROFILE%\.continue\config.yaml on Windows. Keep existing models, rules and tools; add this entry under the existing models list:

models:
  - name: My API model
    provider: openai
    model: YOUR_MODEL_ID
    apiBase: https://aelder.dev/v1
    apiKey: ${{ secrets.SERVICE_API_KEY }}
    useResponsesApi: false
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use

Replace YOUR_MODEL_ID with the exact service ID. Keep the AELDER Base URL including /v1. Do not append /chat/completions or add a local provider prefix. name is only the display label.

For a new file, also add the required top-level metadata:

name: My local configuration
version: 1.0.0
schema: v1

The explicit useResponsesApi: false keeps this setup on Chat Completions, including model names for which Continue would otherwise choose Responses. Keep useLegacyCompletionsEndpoint unset: the legacy /completions API is a different route. See Continue’s OpenAI provider guide.

Only declare tool_use for a model whose tool calling has been confirmed. Keep image capabilities absent for this text setup. Set defaultCompletionOptions.contextLength and maxTokens only from verified model limits. The configuration reference explains model roles and capabilities.

2. Enter the key locally

In your private user file ~/.continue/.env (Windows: %USERPROFILE%\.continue\.env), add or update:

SERVICE_API_KEY=YOUR_SERVICE_API_KEY

Replace the value locally. Keep this file private and outside version control; do not put a real key in config.yaml or chat. An agent can prepare the YAML and secret reference while you enter the secret yourself.

Continue resolves this secret from local .env files; a workspace .env or .continue/.env can take precedence over the user file. Check for a conflicting variable when the wrong key appears to be used. Continue’s secrets documentation describes resolution order.

3. Select and verify

Save the files, select the local configuration and choose My API model in Continue. If the entry is missing, run Developer: Reload Window in VS Code, as described in Continue’s FAQ.

Start a fresh conversation and ask for CONNECTION_OK without tools. Check the reply and the matching request record in your service dashboard. Then try a small file-reading task with normal approvals to check tool calls. These requests use API balance.

The listed roles cover chat/edit/apply. Autocomplete, embeddings and reranking need their own compatible models and APIs; this entry does not configure them. For failures, check the active configuration, secret resolution, /v1 base and exact model ID before using our API troubleshooting.

Need the key? Open your AELDER dashboard. For direct API calls, see the API reference.