Cline’s OpenAI Compatible provider, filled in from its settings screen.
Where a request from Cline goes: the two settings Connect writes, the warden in the middle, then one copy of the model per GPU.
In words:Cline sends its requests to LM Warden with Base URL set to the warden and API Key holding a warden key. LM Warden checks the key, speaks OpenAI Chat Completions, queues the request by key priority and hands it to the replica router, which keeps each session on the replica that already holds its cache, one model copy per GPU.
Protocol
OpenAI Chat Completions
Support
Local models only
Local models only, over streaming Chat Completions. Cline has no config file: enter these values under API Provider > OpenAI Compatible. Its Anthropic provider has a custom base URL but no custom header, so router mode is not available.
Requirements
Needs a model with tool calling (agentic edits).
Works best with at least 32,768 tokens of context.
Setup
In the console, Connect writes these files with your warden’s address, your key and the model you picked. Here they are with placeholders.
Local models
Settings > API Provider > OpenAI Compatible.
Settings
Base URL: https://your-warden/v1
API Key: vw_YOUR_KEY
Model ID: your-served-model-name
Context Window Size: 32768