Hi,
I’m trying to create a realtime session via API with a POST to the “/v1/realtime/sessions” endpoint, with JSON body:
{
"model": "gpt-4o-realtime-preview-2024-12-17"
}
But I get a 500 Internal server error and body:
{
"error": {
"message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID in your email.)",
"type": "server_error",
"param": null,
"code": null
}
}
I have been getting the same error since yesterday. { "error": { "message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID req_007d4c9424bc9c6c3a7eddd9c63b5d45 in your email.)", "type": "server_error", "param": null, "code": null }
I’m ticked… so much time has been wasted trying to correct this, thinking something has to be wrong with my code. OpenAI needs to do better with notifying developers of known issues, etc.
The only thing OpenAI has in it’s favor has been ease of implementation and documentation. This being a major feature, throws that out the window. Looks like I’ll be moving to Gemini since Google is quickly catching up.
Hi, I have an update on this. It seems that the 500 internal server error is caused by using API Keys associated to service accounts. Instead, keys created on real users work.
I.e:
sk-svcacct-* DOES NOT WORK → 500 error
sk-proj-* WORKS