Continue

1. Get a SupaNexus API key

Sign in to the Developer Console, open your project → API Keys, create a key, and copy the secret immediately (shown once). One project key works across OpenAI-compatible and Anthropic-compatible clients.

2. Install Continue

Install the Continue extension in VS Code / JetBrains, then open the Continue panel.

3. Edit config.yaml / config.json

Open Continue config ( Continuue settings → Open config file ). Add an OpenAI-compatible model with apiBase set to SupaNexus /v1 and apiKey set to your project key. You can define separate entries for chat vs autocomplete if desired.

# config.yaml (illustrative)
models:
  - name: SupaNexus Chat
    provider: openai
    model: deepseek/deepseek-chat
    apiBase: <BASE_URL>/v1
    apiKey: sk-snx-...

4. Pick a catalog model ID

Use exact IDs from the SupaNexus Models marketplace or GET /v1/models (for example deepseek/deepseek-chat, anthropic/claude-3-5-sonnet). Do not invent vendor-only slugs from other gateways.

5. Reload and verify

Save the config, reload the Continue window if prompted, select the new model in the picker, and send a short chat. Confirm autocomplete (if configured) also uses the same base URL.

6. Troubleshooting

Wrong provider type: use an OpenAI-compatible / openai provider, not Anthropic, when pointing at /v1/chat/completions. Empty replies: check apiBase includes /v1 and the model id is exact. Secrets: prefer Continue’s secret storage over committing keys into the repo config.