For the last ~14h, we are having issues running Responses API in the background mode with file input.
We have tested with both gpt-4o-mini and gpt-5-mini. File upload works correctly.
To start the model, our input looks like this:
{
"model": "gpt-5-mini",
"instructions": "Our instructions",
"input": [
{
"role": "user",
"content": [
{
"type": "input_file",
"file_id": "file-ABC"
}
]
}
],
"background": true
}
This gives us ID in format “resp_XX” with status “queued”.
But when fetching status again in 10s, we get status “failed”, with error part:
“error”: {
“code”: “server_error”,
“message”: “An error occurred while processing your request. You can retry your request, or contact us through our help center at ``help.openai.com`` if the error persists. Please include the request ID wfr_019d1fe6f276773683c484e7582fbca3 in your message.”
},
We have used same pattern in our application for a while, it stopped working ~14h ago. And we noticed that this issue seems to happen with PDF files only. No issue with images (png, jpg).