Connecting to 树新在线 API Gateway in Continue.dev
Continue declares model providers through configuration files and supports OpenAI-compatible endpoints. 树新在线's Base URL is https://api.treenew.online/v1 and can be integrated via the openai provider.
Configuration
The configuration file is typically located in the .continue directory under the user home folder and may be named config.json or config.yaml, depending on the actual version. Example configuration:
{
"models": [
{
"title": "树新在线 gpt-5.6-luna",
"provider": "openai",
"model": "gpt-5.6-luna",
"apiKey": "sk-xxx",
"apiBase": "https://api.treenew.online/v1"
}
]
}The API Key must be created on the 「令牌」 page at https://api.treenew.online. The list of available models can be found at https://treenew.online/models/.
Key Notes
Continue's autocomplete (tabAutocompleteModel) and embeddings-related features require additional endpoints. This site only exposes the chat/completions endpoint, so autocomplete and local indexing/embedding retrieval must be configured with other providers. Pure chat and editing functionality remains unaffected.
Verification
curl example:
curl https://api.treenew.online/v1/chat/completions \
-H "Authorization: Bearer sk-xxx" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-luna",
"messages": [{"role": "user", "content": "测试"}]
}'