Why are simple prompts flagged as violating policy? Only have issues with GPT-5 Model

API
,
20

Hello, I still have the same issue…

CleanShot 2025-08-21 at 12.34.41
CleanShot 2025-08-21 at 12.34.411827×522 56.3 KB

joehu@Mac ~ % curl -sS -i https://api.openai.com/v1/responses \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5","input":"Hello"}'
HTTP/2 400 
date: Thu, 21 Aug 2025 16:37:04 GMT
content-type: application/json
content-length: 318
openai-version: 2020-10-01
openai-organization: user-xt1xoz3vi61hjrlqtufj9omb
openai-project: proj_OdOGwUMWJqjNYtrbIaMWg5y3
x-request-id: req_214528c008c565ee54a6b3d5a902191d
openai-processing-ms: 1078
x-envoy-upstream-service-time: 1083
strict-transport-security: max-age=31536000; includeSubDomains; preload
cf-cache-status: DYNAMIC
set-cookie: __cf_bm=EjghzxrWT8IyJgzdhVcojgV07I8kY9qPgN_WeIhYbeY-1755794224-1.0.1.1-zpw90njwUaj68WbpD53QDkpLb9C8JGciytEMt0kywb544RmdsjSLTDIWEdwbS7UZ2LuxSGmNPw_SQiWVEgQrDKopYtrI2esP57QcjZmAP24; path=/; expires=Thu, 21-Aug-25 17:07:04 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
x-content-type-options: nosniff
set-cookie: _cfuvid=cjf4poJi1KmTgg.D4FCmOZqVGtxS5s_1hDY4jnBy2gw-1755794224628-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
server: cloudflare
cf-ray: 972b8d872befa257-YUL
alt-svc: h3=":443"; ma=86400

{
  "error": {
    "message": "Invalid prompt: your prompt was flagged as potentially violating our usage policy. Please try again with a different prompt: https://platform.openai.com/docs/guides/reasoning#advice-on-prompting",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_prompt"
  }
}%
3 Likes