Run Aider on Mingles Router
Aider reads OPENAI_API_BASE and OPENAI_API_KEY like every LiteLLM app — export two vars, pass the model with an openai/ prefix.
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>.
Run it
1. Export the endpoint
Two environment variables — put them in your shell profile to make it permanent:
export OPENAI_API_BASE="https://router.mingles.ai/v1"
export OPENAI_API_KEY="<your-key>"2. Start aider with the model
The openai/ prefix tells LiteLLM to use the generic OpenAI route:
aider --model openai/deepseek-ai/DeepSeek-V4-Flash-07313. Optional: pin it in .aider.conf.yml
Drop this in the repo root so teammates get the same setup:
model: openai/deepseek-ai/DeepSeek-V4-Flash-0731
openai-api-base: https://router.mingles.ai/v1Exact values
| OPENAI_API_BASE | https://router.mingles.ai/v1 |
| OPENAI_API_KEY | <your-key> |
| Model flag | openai/deepseek-ai/DeepSeek-V4-Flash-0731 |
Switch model
Swap the value after openai/ to change models — same env vars.
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
Aider warns it doesn’t know the model’s context window. +
Harmless — LiteLLM has no metadata for third-party ids. Silence it with a .aider.model.metadata.json entry or ignore the warning.