IntegrationsDev tool
Cursor
Use RouteMux models in Cursor through its OpenAI-compatible provider setting.
Cursor accepts any OpenAI-compatible endpoint. Point it at RouteMux and your existing workflow is unchanged.
Configure
In Cursor's model settings, enable a custom OpenAI-compatible provider and fill:
| Field | Value |
|---|---|
| Base URL / Override OpenAI Base URL | https://api.routemux.com/v1 |
| API key | your RouteMux key (sk-...) |
| Model | a slug from GET /v1/models, e.g. openai/gpt-5.5 |
Add the model id yourself
Editors that ship a fixed model dropdown will not list RouteMux slugs. Add the model id
manually — GET /v1/models returns exactly what your key can call.
Verify
Before touching the editor, confirm the pair works:
curl https://api.routemux.com/v1/chat/completions \
-H "Authorization: Bearer sk-..." \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-5.5","messages":[{"role":"user","content":"ping"}]}'If this returns 200 and the editor still fails, the problem is in the editor's config, not in the key.
Notes
- Base URL includes
/v1here — OpenAI clients append only the operation path. 402means an empty wallet. Failed requests are never billed.