Run Roo Code on Mingles Router
Roo Code keeps Cline's provider model: pick “OpenAI Compatible”, fill three fields, and every mode (Code, Architect, Debug) runs on your endpoint.
Pick your model and paste your key — every command and value on this page updates live.
Endpoint: https://router.mingles.ai/v1 · key stays in your browser ·
no key entered? commands show <your-key>.
Install + configure
1. Install Roo Code
VS Code Extensions → Roo Code, or:
code --install-extension RooVeterinaryInc.roo-cline2. Provider → OpenAI Compatible
Roo panel → settings (gear) → Providers → OpenAI Compatible, then Base URL, API Key and Model ID from the table.
3. Set it per mode (optional)
Roo lets each mode use its own configuration profile — e.g. MiniMax for Code, Kimi for Architect. Cheap model for volume, stronger one for planning.
Exact values
| API Provider | OpenAI Compatible |
| Base URL | https://router.mingles.ai/v1 |
| API Key | <your-key> |
| Model ID | deepseek-ai/DeepSeek-V4-Flash-0731 |
Switch model
Profiles make Roo the easiest place to split cheap/strong models per task — the same trick the burn-rate table in your console prices out.
Before you file a bug: read the limits
Reasoning models spend the output budget on internal thinking, output is capped at 8192 tokens, there is no KV cache, and there are no built-in web tools. Most “it broke on Mingles Router” reports are one of these. See Model limits & behavior →
Frequently asked
Is the setup different from Cline? +
No — same provider type and fields. If you migrate from Cline, recreate the profile and you’re done.