gpt-image-2.6-sunburst / gpt-image-2.6-flare, gpt-image-2.5-sunburst / gpt-image-2.5-flare, gpt-image-2, and reverse-engineered routes such as gpt-image-2.6-all. Official-relay routes (2.6 / 2.5 / 2) are moderated by OpenAI; reverse-engineered routes are moderated by their respective providers (-all runs on the ChatGPT web line, -vip runs on the Adobe Firefly line). Status codes and strictness vary by route, but none of these decisions come from APIYI.Short answer
- Moderation comes from the provider, not from APIYI’s own rules. Official-relay GPT Image (2.6 / 2.5 / 2) is judged by OpenAI; reverse-engineered
-all/-viproutes are judged by their respective providers. APIYI relays the request and passes provider errors through; it cannot overturn a decision or whitelist a prompt. - It cannot be turned off. OpenAI provides no switch for official-relay routes, reverse-engineered routes are still bound by their providers’ policies, and APIYI cannot disable moderation on your behalf.
moderationonly acceptsauto/low;lowlowers strictness but is not a bypass. - Slow failures usually come from output-side moderation: the image is generated first and filtered afterward, so a failed request takes about as long as a successful one. The gateway now returns
400/451as soon as a safety rejection is confirmed instead of retrying until timeout.
Upstream makes the call; APIYI relays the result
Official-relay GPT Image content safety is enforced by OpenAI on the provider side, at two stages:gpt-image-2.6-all runs on the ChatGPT web line, and gpt-image-2.5-sunburst-vip runs on the Adobe Firefly line. The decision maker and strictness can differ.
APIYI relays the request to the provider and passes the provider’s response and error back unchanged. There is no “ignore moderation” switch on the platform for a request that the provider has rejected; there is no off switch in the parameters either, and changing groups does not disable moderation.
400 / 451, not a custom APIYI threshold.Why it is slow and then fails
Output-side review explains the latency
Output-side review runs after the image is generated. The model has already produced the image when the classifier decides whether it can be returned. A failed request therefore spends the same generation time as a successful one, which is why you may wait a long time only to receive an error. In existing tests,451 image_safety failures took 80–95 seconds, and some complex reference-image cases exceeded 200 seconds. Successful requests can fall in the same range, so do not use latency alone to identify moderation; read the error message and status code first.
Retries add to the total wait
When the provider returns a retryable error, the gateway performs a limited retry; some reverse-engineered routes also retry on another account, which adds more latency. The current optimization is to return400 / 451 as soon as a content-safety rejection is confirmed, instead of letting the request run until timeout. If you still see a long wait before the error, the time is mainly generation plus output-side review, not an infinite retry loop.
Common 400 and 451 responses for content safety
Can it be turned off or lowered?
It cannot be turned off. OpenAI provides no switch for official-relay routes, reverse-engineered routes are still bound by their providers’ policies, and APIYI cannot bypass the provider’s decision. The only knob ismoderation, and its effect is limited. On the GPT Image text-to-image API, it accepts only two values:
moderation: "low" lowers filtering strictness but does not guarantee a pass; it is especially unreliable for output-side blocks. In existing tests, adding it still returned 400 safety_violations=[sexual]. Do not rely on it in production.
What to do with a 400 / 451
Confirm it is content safety
error.code / message. If it contains safety_violations, moderation_blocked, content_policy_violation, or image_safety, it is a content-safety block, not a parameter or network error.Do not retry the same input
Describe the image instead of deleting words
Regress 2 to 3 times
FAQ
Why does the ChatGPT web app work while the API is blocked?
Why does the ChatGPT web app work while the API is blocked?
Does switching to gpt-image-2.6-all or Nano Banana remove moderation?
Does switching to gpt-image-2.6-all or Nano Banana remove moderation?
Why am I still blocked when moderation is set to low?
Why am I still blocked when moderation is set to low?
400 safety_violations with low.The same prompt passes sometimes and fails other times. Is moderation unstable?
The same prompt passes sometimes and fails other times. Is moderation unstable?
If the content is compliant, can I appeal or get a whitelist?
If the content is compliant, can I appeal or get a whitelist?
X-Shellapi-Request-Id response header) and the request body to support; we can check the route and the source of the error. However, the platform cannot promise to override the provider’s decision, and there is no per-prompt whitelist. See How to find the Request ID.Related docs
Can an image be rejected after generation?
451 image_safety output-side review works, with an anonymized retest and clothing-prompt fixes.