Run Continue on Mingles Router
Continue takes any OpenAI-compatible model as a config block: provider openai, an apiBase, a key.
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>.
Add the model block
1. Open your Continue config
Continue panel → gear → Configs → Open configuration. Current builds use config.yaml; older ones config.json — the fields are the same.
2. Add the model (config.yaml)
Under models:
models:
- name: Kimi K2.6 (router)
provider: openai
model: deepseek-ai/DeepSeek-V4-Flash-0731
apiBase: https://router.mingles.ai/v1
apiKey: <your-key>
roles: [chat, edit]3. Select it
Pick the model in Continue’s model dropdown. Add a second block with MiniMaxAI/MiniMax-M2.7 for cheaper bulk edits.
Exact values
| provider | openai |
| apiBase | https://router.mingles.ai/v1 |
| apiKey | <your-key> |
| model | deepseek-ai/DeepSeek-V4-Flash-0731 |
Switch model
Each model is its own block — keep both and switch in the dropdown.
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
config.json instead of yaml? +
Same fields in JSON form inside the “models” array: { “title”, “provider”: “openai”, “model”, “apiBase”, “apiKey” }.