Where does the bug appear (feature/product)? Cursor IDE Describe the Bug I’ve currently reached my usage limit, and I’m using custom OpenAI base URLs while waiting for refreshes. However, the sub-agent seems to be malfunctioning. It reports that the model is unavailable with the slow pool. This me…

Hey, thanks for the report. Looks like this is a bug. Sub-agents aren’t inheriting your custom OpenAI Base URL settings, so they fall back to Cursor’s servers and hit the “slow pool” error because the fast requests have already been used up. Could you please grab the Request ID from the failed sub-…

Hi we’ve been running into the same problem. Are there any workarounds discovered? Is there an estimated timeline to getting this fixed?

getting the same issue, i was wondering why my On Demand usage goes up when i’ve been just using my own custom API keys (OpenAI override). So this is 99% like the cause, sub-agents are using on demand usage instead of inheriting agent model (custom model)

Hey, no updates on this bug yet. Sub-agents still don’t inherit custom API keys or the base URL settings. There isn’t a workaround yet either. The team is aware of the issue. I’ll update this thread when there’s progress.

Where does the bug appear (feature/product)? Cursor CLI Describe the Bug When using Cursor Agent, I get ERROR_NETWORK_ERROR with [resource_exhausted] in the stack. The stack traces runAgentLoop → streamFromAgentBackend → getAgentStreamResponse. I want OpenAI-compatible traffic to go to my LiteLLM g…

Is this fixed in Cursor 3? We really want to maximize our custom API without incurring further cost from our plan.

Sub-agents are not using custom OpenAI base URLs

Support Bug Reports

deanrie (Dean Rie) March 2, 2026, 5:56pm 7

Hey, unfortunately there’s no workaround for this yet. Sub-agents don’t inherit custom API key or base URL settings, and there’s no way for the user to bypass this on their side.

I’ll update the thread when there’s a fix.

Topic		Replies	Views
Cursor Agent always routes requests through its own backend servers (streamFromAgentBackend) regardless of custom base URL settings, so the resource_exhausted error is a Cursor-side quota issue — not your LiteLLM gateway — as confirmed by zero POST /v1/ e Bug Reports chat , byok	1	182	April 3, 2026
Custom models (OpenAI base URL override) not usable in subagents — silently ignored Bug Reports byok , subagents	0	119	April 29, 2026
Custom Model Provider Error Bug Reports byok	1	371	March 7, 2026
Cursor cannot connect to a custom URL compatible with the OpenAI protocol Bug Reports byok	2	566	March 7, 2026
The custom override of the OpenAI base URL is unusable Help byok	1	1272	February 26, 2026

Sub-agents are not using custom OpenAI base URLs

Related topics