# Cursor-managed models are routed through Override OpenAI Base URL **URL:** \ **Category:** Bug Reports\ **Tags:** byok, openai\ **Created:** [August 21, 2026, 4:09pm UTC](https://forum.cursor.com/t/cursor-managed-models-are-routed-through-override-openai-base-url/169088 "2026-08-21T16:09:48Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![pulipuli.chen](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/pulipuli.chen/32/118256_2.png) [@pulipuli.chen](https://forum.cursor.com/u/pulipuli.chen)\ **Post date:** [August 21, 2026, 4:09pm UTC](https://forum.cursor.com/t/cursor-managed-models-are-routed-through-override-openai-base-url/169088/1 "2026-08-21T16:09:48Z")
### Where does the bug appear (feature/product)? Cursor IDE ### Describe the Bug When Override OpenAI Base URL is enabled, Cursor routes requests for Cursor-managed models through the configured custom OpenAI-compatible endpoint. For example, when I select gpt-5.6-luna from Cursor’s built-in model picker, the request is still sent to my custom proxy instead of Cursor’s backend. I confirmed this behavior through the proxy logs. My intended setup is to use both Cursor subscription models and custom models from my own OpenAI-compatible proxy in the same Cursor profile. ### Steps to Reproduce 1. Configure a custom OpenAI-compatible Base URL in Cursor. 2. Enable Override OpenAI Base URL. 3. Select a Cursor-managed model from the built-in model picker, for example gpt-5.6-luna. 4. Send a request. 5. Check the custom proxy logs. 6. The request for gpt-5.6-luna is sent to the custom proxy. If gpt-5.6-luna is intentionally unavailable on the proxy, Cursor returns: `The requested model is not available` ### Expected Behavior Cursor-managed models selected from the built-in model picker should continue to use Cursor’s backend. Custom models should use the configured custom OpenAI Base URL. Ideally, the routing should behave like this: `Cursor-managed model → Cursor backend` `Custom model → Custom OpenAI Base URL` Enabling **Override OpenAI Base URL** should not redirect Cursor-managed subscription models to the custom endpoint. ### Screenshots / Screen Recordings ![image.png](https://us1.discourse-cdn.com/cursor1/original/3X/1/f/1f366b62afe855416df8f06f263c5b85068196b0.png) ### Operating System Linux ### Version Information Version: 3.12.17 VS Code Extension API: 1.128.0 Commit: 0fb762053c34788bb7760d5673f8a6d4c8589d50 Date: 2026-07-17T02:53:53.006Z Layout: IDE Build Type: Stable Release Track: Default Electron: 40.10.3 Chromium: 144.0.7559.236 Node.js: 24.15.0 V8: 14.4.258.32-electron.0 xterm.js: 6.1.0-beta.256 OS: Linux x64 6.17.0-40-generic ### For AI issues: which model did you use? GPT-5.6 Luna (gpt-5.6-luna) ### For AI issues: add Request ID with privacy disabled 5e466056-a8a2-4b1e-b437-bb91234259fb ### Additional Information This behavior was also confirmed by Cursor staff in the original feature-request thread: [https://forum.cursor.com/t/custom-base-urls-for-each-custom-model/147219/13](https://forum.cursor.com/t/custom-base-urls-for-each-custom-model/147219/13) Cursor staff explained that, with **Override OpenAI Base URL** enabled, all requests currently go through the custom endpoint, including Cursor-managed models from the built-in picker. The current workaround is to manually disable **Override OpenAI Base URL** when using Cursor subscription models, and enable it again when using custom models. I created this separate report at the request of Cursor staff so that this routing issue can be tracked independently from the original per-model Base URL feature request. I can also provide proxy logs showing that requests for `gpt-5.6-luna` are reaching the custom endpoint. ### Does this stop you from using Cursor Sometimes - I can sometimes use Cursor ---
**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\ **Post date:** [August 21, 2026, 5:40pm UTC](https://forum.cursor.com/t/cursor-managed-models-are-routed-through-override-openai-base-url/169088/5 "2026-08-21T17:40:16Z")
Hey, thanks for moving this into a separate thread and confirming it via proxy logs. That made it much easier for us to verify on our side. What you’re seeing matches the current routing logic. While Override OpenAI Base URL is enabled, all OpenAI-family requests go through your custom endpoint, including models picked from the built-in picker like gpt-5.6-luna. Your config is correct. Right now, the feature works exactly like that, and there isn’t a carve-out for managed models yet. We’re tracking the request for per-model routing, where built-in models would keep going to the Cursor backend and custom models would go to your endpoint. I can’t share a timeline yet, but I’ll reply in the thread once there’s an update. For now, the workaround is the same. Turn off Override OpenAI Base URL when using Cursor models, then turn it back on for custom ones. ---
**Author:** ![Radius\_Kuntoro](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/radius_kuntoro/32/118988_2.png) [@Radius\_Kuntoro](https://forum.cursor.com/u/Radius_Kuntoro)\ **Post date:** [September 15, 2026, 3:14pm UTC](https://forum.cursor.com/t/cursor-managed-models-are-routed-through-override-openai-base-url/169088/7 "2026-09-15T15:14:41Z")
Now that you don’t offer GPT 6 Astra, I feel a BYOK key per model feature is more needed. When switching to BYOK, you lose too many Cursor features. But sometimes I want to try these newer models or use them just for reviews, and still use the Cursor models for most of my prompting without needing to toggle on/off in the Settings. ---
**Author:** ![deanrie](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/deanrie/32/1263_2.png) [@deanrie](https://forum.cursor.com/u/deanrie)\ **Post date:** [September 15, 2026, 7:42pm UTC](https://forum.cursor.com/t/cursor-managed-models-are-routed-through-override-openai-base-url/169088/8 "2026-09-15T19:42:51Z")
Hey, thanks for the feedback. That exact setup, built-in models routed through the Cursor backend and custom models through your own endpoint, with no manual switching, is what we’re tracking. I can’t share a timeline yet, but I’ll reply in the thread once there’s an update. Until then, the workaround is the same. Turn off Override OpenAI Base URL when you’re using Cursor models, and turn it back on for your custom models. I get that flipping the toggle back and forth is annoying, especially when you want to quickly use a different model for review. We’ll factor that into the request. ---
**Author:** ![harden\_James](https://avatars.discourse-cdn.com/v4/letter/h/dfb087/32.png) [@harden\_James](https://forum.cursor.com/u/harden_James)\ **Post date:** [October 23, 2026, 8:01am UTC](https://forum.cursor.com/t/cursor-managed-models-are-routed-through-override-openai-base-url/169088/9 "2026-10-23T08:01:33Z")
### Could you support separate Base URLs for official Cursor models and third-party models? Currently, the global Base URL setting makes it difficult to use both simultaneously. It would be great to switch between them without changing global settings.