Trying to use GPT 5 and up on a workflow agent, but every time it tries to get past the first node it hangs up the call. Looking at the call logs I see, "call in-progress.error-providerfault-openai-llm-failed". Any idea what's causing this and if there's a workaround?

The error

call.in-progress.error-providerfault-openai-llm-failed

means OpenAI's API is failing to process your GPT-5+ requests, likely due to model access or provider-side issues. Actionable step: _Contact Vapi support with your

call_id

and account details for investigation, as recommended in the [documentation](https://docs.vapi.ai/calls/call-ended-reason)._ Alternatively, try switching your workflow agent to a supported model like

gpt-4o

to see if the issue resolves. Source: - [Call ended reason codes (Vapi documentation)](https://docs.vapi.ai/calls/call-ended-reason)

The model is having trouble processing the first request. Please provide a call id and we will look into it deeper

Thanks Kyle, here's that call ID: 019aa82a-75af-7662-ba66-29295e8bbe34

Thanks for sharing the call ID. Just a heads-up that Workflows will be deprecated in the near future. We recommend migrating to Squads v2, which is the supported path forward and provides better stability and ongoing improvements. If you’d like guidance on moving this setup to Squads v2, let us know and we’re happy to help.