Run Cline on Mingles Router
Cline's OpenAI-Compatible provider takes a base URL, a key and a model id — the whole integration is three fields.
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 the Cline extension
VS Code Extensions panel → search Cline, or:
code --install-extension saoudrizwan.claude-dev2. Choose the provider
Open the Cline panel → settings (gear) → API Provider → OpenAI Compatible. Not “OpenAI” — that one ignores a custom base URL.
3. Fill the three fields
Base URL, API Key and Model ID from the table below. Save and start a task.
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
Kilo Code and Roo Code are Cline forks — the same three fields work in all three.
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
Does tool use / editing files work? +
Yes. The endpoint returns OpenAI-format tool_calls (translating models’ native format where needed), so Cline’s file edits and commands work without glue.
“Model Not Found”? +
Model ID must be exactly deepseek-ai/DeepSeek-V4-Flash-0731 — case-sensitive — and the Base URL must end in /v1.