Cline on your own GPUs.

Cline’s OpenAI Compatible provider, filled in from its settings screen.

Protocol: OpenAI Chat Completions
Support: Configured from its docs
Verified: Checked against its docs on 2026-10-04. Config checked against the docs; the streaming Chat Completions request it sends, with a tool call, passed with curl.

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

Official documentation: https://docs.cline.bot/provider-config/openai-compatible (read 2026-10-04).