GPT-5 mini uses the Pre-defined "end call" tool in a weird way, ending the call on the first message or mid-conversation, when it's definitely not appropriate to. Which makes the best low-latency model so far unusable. GPT-4.1-mini in the same prompt never had such a problem in over 10k calls. I suppose it has something to do with how this Pre-defined function is manifested in the backend, and how GPT-5 mini handles it

Suggestion: To prevent GPT-5 mini from ending calls inappropriately, review your assistant's system prompt and tool configuration. Make sure the

endCall

tool is only included when necessary, and update your prompt to avoid mentioning or implying call termination except in explicit scenarios. For example:

json
{
  "model": {
    "provider": "openai",
    "model": "gpt-5-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant. Only use the endCall tool if the user clearly requests to end the call or says goodbye."
      }
    ],
    "tools": [
      { "type": "endCall" }
    ]
  }
}

Tip: Remove the

endCall

tool from the

tools

array if you want to fully disable this behavior. [See more in the Vapi documentation.](https://docs.vapi.ai/tools/default-tools#end-call) Sources: - [Default Tools – End Call](https://docs.vapi.ai/tools/default-tools#end-call) - [Prompting Guide – Error Handling & Tool Use](https://docs.vapi.ai/prompting-guide)

I'm having similar issue with GPT-5 and GPT-5-mini, it ends the call as soon as a user speaks. I've removed my global prompt entirely

If your calls are randomly ending while using GPT-5 mini, it's helpful to check for specific call ended reason codes in your call logs. Common reasons could be assistant-related issues or errors in the AI processing pipeline. You can refer to the [call ended reasons documentation](https://docs.vapi.ai/calls/call-ended-reason) for more detailed codes and their meanings. Additionally, if you're seeing frequent logouts or error messages, it might be an issue related to your authentication or account settings. Please ensure that your login credentials are up-to-date and check the account security settings for any irregularities. For detailed error codes or if the issue persists with specific behaviors, providing a Call ID could help in further diagnosis.

I have the same issue. I can use gpt-5-nano and other models in Vapi without any problem, but gpt-5-mini and gpt-5 don’t work. The calls end abruptly and I get this error: "pipeline-error-openai-400-bad-request-validation-failed".

To help track down this issue, could you share: - The call ID - This would really help us figure out what went wrong!

Call 1: 8d08cdc8-e85f-4a6d-ad19-2439b0aa712b

Oh, so you used it via OpenAI's API. And do you have a problem with GPT-5-mini randomly ending calls? Or it works smoothly now?

If you are using Vapi's default API key, you wont encounter the organization verification issue since Vapi is already verified to use these models. AI ID if you are still encountering issues with your calls ending prematurely please share a call id where it occurs and we will review the logs

Here's an call id: e3687e8b-7039-466e-980c-0f83e82aaa61

Hey, thanks for sharing your details. Our team will look into it and get back to you soon with an update.

any update?

Sorry it's taking longer than usual. Our team is looking into it and will get back to you with an update soon.

it's been a month now, it's quite a critical issue...

While we typically recommend other GPT models for stability reasons, there shouldn't be any pipeline errors. Also with recent updates to the platform, most of the pipeline issues with this model should be resolved. If you are still experiencing these errors, please provide a recent call id within the last <7 days and we will investigate further

let's mark this as "solved" - just checked and GPT-5 works perfectly fine. Kudos VAPI team