#GPT-5 returns empty responses with medium reasoning effort despite consuming reasoning tokens

1 messages · Page 1 of 1 (latest)

knotty jettyBOT
#

Reported by @quartz oyster

Bug Report: GPT-5 returns empty responses with medium reasoning effort despite consuming reasoning tokens
`Steps to Reproduce`

Steps to Reproduce:

  1. Use GPT-5 model with reasoning_effort="medium" and verbosity="medium"
  2. Send any text or image analysis request
  3. Set max_completion_tokens to 1000-4000
  4. Make API call to OpenAI
`Expected Result`

GPT-5 should return a non-empty response with content analyzing the input, similar to how gpt-5-chat-latest or gpt-4o responds.

`Actual Result`

GPT-5 returns completely empty responses (0 characters) while still consuming 1000-4000 reasoning tokens and taking 17-58 seconds to respond. The API call succeeds (no errors), but content is empty
string. Works fine with reasoning_effort="minimal" or using gpt-5-chat-latest/gpt-4o models

`Environment`

Windows 11 Pro

#
Additional Information

Please provide relevant details to help resolve the issue, such as:

  • ChatGPT Shared Link (if applicable).
  • Screenshots or videos demonstrating the problem.

-# ➜ Need to contact support? Visit the OpenAI Help Center.

quartz oyster
quartz oyster
#

Anyone can help with this