# \#moderation **URL:** https://community.openai.com/tag/moderation/169.md [Latest](https://community.openai.com/latest.md) · [Categories](https://community.openai.com/categories.md) · [Tags](https://community.openai.com/tags.md) --- ## [Omni-moderation model always returning 429 even on first request](https://community.openai.com/t/omni-moderation-model-always-returning-429-even-on-first-request/1380555)
**Author:** [@ohh02](https://community.openai.com/u/ohh02)\ **Replies:** 1\ **Last updated:** [September 17, 2026, 6:12pm UTC](https://community.openai.com/t/omni-moderation-model-always-returning-429-even-on-first-request/1380555 "2026-09-17T18:12:24Z")
Trying to use the OpenAI omni-moderation model for my project but every request returns 429 Too Many Requests. Even tested it in Postman with a fresh API key and the very first request still failed with 429. Not sending … --- ## [Rate limits for omni-moderation based on tier?](https://community.openai.com/t/rate-limits-for-omni-moderation-based-on-tier/1377984)
**Author:** [@AI-Roguelite](https://community.openai.com/u/AI-Roguelite)\ **Replies:** 4\ **Last updated:** [September 7, 2026, 4:22pm UTC](https://community.openai.com/t/rate-limits-for-omni-moderation-based-on-tier/1377984 "2026-09-07T16:22:55Z")
Hello, I’m trying to use the omni moderation model on a fresh account (OpenAI wrongly banned me years ago after I complied with all their requests and they didn’t respond to my emails 3 times so I had to switch accounts)… --- ## [GPT-5.5 MCP SQL read/write blocks with no visible moderation flag](https://community.openai.com/t/gpt-5-5-mcp-sql-read-write-blocks-with-no-visible-moderation-flag/1385894)
**Author:** [@JayBase](https://community.openai.com/u/JayBase)\ **Replies:** 2\ **Last updated:** [July 6, 2026, 11:06pm UTC](https://community.openai.com/t/gpt-5-5-mcp-sql-read-write-blocks-with-no-visible-moderation-flag/1385894 "2026-07-06T23:06:37Z")
Has anyone noticed ChatGPT 5.5 moderation, filtering, or blocking on OpenAI’s side that occurs without the running agent/model receiving a visible moderation flag? I created a server-based MCP connector linked to a Post… --- ## [How should AI apps handle flagged moderation content?](https://community.openai.com/t/how-should-ai-apps-handle-flagged-moderation-content/1380303)
**Author:** [@Risphere](https://community.openai.com/u/Risphere)\ **Replies:** 0\ **Last updated:** [May 4, 2026, 7:12pm UTC](https://community.openai.com/t/how-should-ai-apps-handle-flagged-moderation-content/1380303 "2026-05-04T19:12:17Z")
I’m implementing moderation for my AI app and I’m a bit unsure about the correct architecture. Right now I’m using the Moderation API and it flags a lot of content that isn’t necessarily harmful in context. If I treat a… --- ## [False positive: “elimination” flagged as self-harm, violence in math query](https://community.openai.com/t/false-positive-elimination-flagged-as-self-harm-violence-in-math-query/1379183)
**Author:** [@Hawkes-Saibabu](https://community.openai.com/u/Hawkes-Saibabu)\ **Replies:** 4\ **Last updated:** [April 21, 2026, 6:45am UTC](https://community.openai.com/t/false-positive-elimination-flagged-as-self-harm-violence-in-math-query/1379183 "2026-04-21T06:45:47Z")
Description: I’m encountering a false positive with the moderation system (omni-moderation-latest) while testing with sample. A simple query: “Is elimination the easiest method here?” (referring to solving equations u… --- ## [Moderation endpoint use not registering in logs](https://community.openai.com/t/moderation-endpoint-use-not-registering-in-logs/1368723)
**Author:** [@PrzemekCZP](https://community.openai.com/u/PrzemekCZP)\ **Replies:** 11\ **Last updated:** [April 16, 2026, 2:03pm UTC](https://community.openai.com/t/moderation-endpoint-use-not-registering-in-logs/1368723 "2026-04-16T14:03:13Z")
Hi, It seems the moderation stopped showing in the usage logs since 6th of December: I performed a quick text test if the moderation calls are working and it seems they are: Is anyone else experiencing this or t… --- ## [Content Moderations Endpoint - 429 "Too Many Requests"](https://community.openai.com/t/content-moderations-endpoint-429-too-many-requests/618302)
**Author:** [@tycomo](https://community.openai.com/u/tycomo)\ **Replies:** 7\ **Last updated:** [April 1, 2026, 4:44am UTC](https://community.openai.com/t/content-moderations-endpoint-429-too-many-requests/618302 "2026-04-01T04:44:04Z")
Hi all, My application intermittently is running into issues where the content moderation endpoint will return a 429 for “Too Many Requests”. I looked into the rates for text-moderation-latest that are set at 150k TPM… --- ## [Omni Moderation - Usage dashboard doesn't work for since Dec 2025](https://community.openai.com/t/omni-moderation-usage-dashboard-doesnt-work-for-since-dec-2025/1373538)
**Author:** [@dannyboytrading](https://community.openai.com/u/dannyboytrading)\ **Replies:** 2\ **Last updated:** [February 13, 2026, 1:50am UTC](https://community.openai.com/t/omni-moderation-usage-dashboard-doesnt-work-for-since-dec-2025/1373538 "2026-02-13T01:50:11Z")
Hey folks. I really love Omni Moderation API for my student project. For some reason API / token usage in dashboard doesn’t work for like 2 months now. I basically see 0 usage. Would you anyone from Support be so kind an… --- ## [Discrepancy: omni-moderation-latest Token Usage vs Tier 1 Rate Limits (Vision)](https://community.openai.com/t/discrepancy-omni-moderation-latest-token-usage-vs-tier-1-rate-limits-vision/1371064)
**Author:** [@Anass\_El\_Basraoui](https://community.openai.com/u/Anass_El_Basraoui)\ **Replies:** 4\ **Last updated:** [January 7, 2026, 1:40pm UTC](https://community.openai.com/t/discrepancy-omni-moderation-latest-token-usage-vs-tier-1-rate-limits-vision/1371064 "2026-01-07T13:40:43Z")
Hello everyone, I am implementing an image moderation pipeline using the \`omni-moderation-latest\` model. I am currently on Tier 1, which states a limit of 10,000 TPM (Tokens Per Minute)→ https://platform.openai.com/docs… --- ## [Understanding category\_scores moderation values](https://community.openai.com/t/understanding-category-scores-moderation-values/1368610)
**Author:** [@damgarland](https://community.openai.com/u/damgarland)\ **Replies:** 1\ **Last updated:** [December 7, 2025, 3:19pm UTC](https://community.openai.com/t/understanding-category-scores-moderation-values/1368610 "2025-12-07T15:19:29Z")
Hi there I’m using OpenAI to analyse images. Sometimes they fail moderation with a low score, under 50% as in this example flagged for violence: category\_scores: { harassment: 0, ‘harassment/threatening’: 0, sexual:… --- ## [Dealing with Moderation API False Positives](https://community.openai.com/t/dealing-with-moderation-api-false-positives/1309882)
**Author:** [@tucalipe](https://community.openai.com/u/tucalipe)\ **Replies:** 4\ **Last updated:** [November 7, 2025, 11:01pm UTC](https://community.openai.com/t/dealing-with-moderation-api-false-positives/1309882 "2025-11-07T23:01:52Z")
I’m working on a support ticket bot for a company in Brazil, and we decided to use 4o-mini to power it. All our our customers prompt’s are moderated through the Moderation API, and, previously, we blocked anything that … --- ## [Omni Moderation often fails to flag harmful texts](https://community.openai.com/t/omni-moderation-often-fails-to-flag-harmful-texts/1365385)
**Author:** [@kafeinnn](https://community.openai.com/u/kafeinnn)\ **Replies:** 0\ **Last updated:** [November 6, 2025, 8:16pm UTC](https://community.openai.com/t/omni-moderation-often-fails-to-flag-harmful-texts/1365385 "2025-11-06T20:16:00Z")
I’m currently using the latest version of OpenAI’s Omni Moderation to detect disallowed or harmful content such as profanity, insults, hate speech, and other offensive language. However, I’ve noticed that in many cases, … --- ## [Guardrails on chatgpt, makes it unusable for outside the box thinkers](https://community.openai.com/t/guardrails-on-chatgpt-makes-it-unusable-for-outside-the-box-thinkers/1364582)
**Author:** [@jstorbjo](https://community.openai.com/u/jstorbjo)\ **Replies:** 0\ **Last updated:** [October 31, 2025, 11:47am UTC](https://community.openai.com/t/guardrails-on-chatgpt-makes-it-unusable-for-outside-the-box-thinkers/1364582 "2025-10-31T11:47:03Z")
The guardrails OpenAI has put on ChatGPT, are just fucking ridiculous. It becomes unusable! I’m literally just playing with models, building metaphors, exploring theories, and suddenly it flips tone. Like I’m unstable, … --- ## [Moderation API - Supported Image formats?](https://community.openai.com/t/moderation-api-supported-image-formats/1364365)
**Author:** [@oa1](https://community.openai.com/u/oa1)\ **Replies:** 5\ **Last updated:** [October 29, 2025, 7:35pm UTC](https://community.openai.com/t/moderation-api-supported-image-formats/1364365 "2025-10-29T19:35:56Z")
I am not sure if I am missing it in the documentation, but I can find no info on the images supported by the moderation API? https://platform.openai.com/docs/guides/moderation Can anyone confirm and where would be best… --- ## [Does the OpenAI Moderations API Support file\_url (e.g., PDF)?](https://community.openai.com/t/does-the-openai-moderations-api-support-file-url-e-g-pdf/1363825)
**Author:** [@stayingcool](https://community.openai.com/u/stayingcool)\ **Replies:** 0\ **Last updated:** [October 25, 2025, 1:04am UTC](https://community.openai.com/t/does-the-openai-moderations-api-support-file-url-e-g-pdf/1363825 "2025-10-25T01:04:02Z")
I’m exploring whether the Moderations API (omni-moderation-latest) supports direct moderation of PDF files — similar to how it accepts image\_url inputs. Here’s what I’ve learned so far: Current Behavior The Moderati… --- ## [Public Moderation API Passed, But Fine-Tuning File Still Rejected – Why?](https://community.openai.com/t/public-moderation-api-passed-but-fine-tuning-file-still-rejected-why/1354797)
**Author:** [@noumandilawar](https://community.openai.com/u/noumandilawar)\ **Replies:** 1\ **Last updated:** [August 29, 2025, 1:27am UTC](https://community.openai.com/t/public-moderation-api-passed-but-fine-tuning-file-still-rejected-why/1354797 "2025-08-29T01:27:31Z")
Hi everyone, I’m trying to fine-tune a model and keep running into this error: The job failed due to an unsafe training file. This training file was blocked by our moderation system because it contains too many exampl… --- ## [No access to text-moderation-007](https://community.openai.com/t/no-access-to-text-moderation-007/943930)
**Author:** [@dsamson](https://community.openai.com/u/dsamson)\ **Replies:** 5\ **Last updated:** [August 27, 2025, 4:21am UTC](https://community.openai.com/t/no-access-to-text-moderation-007/943930 "2025-08-27T04:21:21Z")
I am having an issue where sending requests to text-moderation-007 receives this error: Error code: 403 - {‘error’: {‘message’: ‘Project proj\_xxxxx does not have access to model text-moderation-007’, ‘type’: ‘invalid\_r… --- ## [Is this an allowed use of Moderation Endpoint?](https://community.openai.com/t/is-this-an-allowed-use-of-moderation-endpoint/1331873)
**Author:** [@stefatorus](https://community.openai.com/u/stefatorus)\ **Replies:** 0\ **Last updated:** [August 2, 2025, 3:15pm UTC](https://community.openai.com/t/is-this-an-allowed-use-of-moderation-endpoint/1331873 "2025-08-02T15:15:11Z")
I am thinking of using OpenAIs APIs to moderate my online public forums as well as chat. I’m thinking of a pipeline doing the following to scan discord messages: Message Stream/Post/Comments from Discord/Forum/etc → Mo… --- ## [Sexual related text not flagged by text-moderation-latest](https://community.openai.com/t/sexual-related-text-not-flagged-by-text-moderation-latest/1313019)
**Author:** [@angelicoalejandro](https://community.openai.com/u/angelicoalejandro)\ **Replies:** 2\ **Last updated:** [July 11, 2025, 2:35pm UTC](https://community.openai.com/t/sexual-related-text-not-flagged-by-text-moderation-latest/1313019 "2025-07-11T14:35:16Z")
I’m testing text-moderation-latest api to detect harmful content. If I add an insult in the text, the text is flagged, but if I add a link to a porn site or if i write “porn” or similar words, it returns false. Is there… --- ## [How to count tokens for moderation model](https://community.openai.com/t/how-to-count-tokens-for-moderation-model/1310248)
**Author:** [@thanawarat.jongchiew](https://community.openai.com/u/thanawarat.jongchiew)\ **Replies:** 0\ **Last updated:** [July 8, 2025, 4:22am UTC](https://community.openai.com/t/how-to-count-tokens-for-moderation-model/1310248 "2025-07-08T04:22:51Z")
Here, I’m working with moderation model. I found this model is free but it still has rate limit. Since this model doesn’t return the tokens used with the response how can I know that I’m reaching limit or not? or even nu… --- ## [Fine Tuning API Inconsistently Blocking Jobs](https://community.openai.com/t/fine-tuning-api-inconsistently-blocking-jobs/1304352)
**Author:** [@ccrowell](https://community.openai.com/u/ccrowell)\ **Replies:** 0\ **Last updated:** [July 1, 2025, 4:44pm UTC](https://community.openai.com/t/fine-tuning-api-inconsistently-blocking-jobs/1304352 "2025-07-01T16:44:11Z")
Hi all, I’m having a pretty severe issue with the Fine-Tuning API. It’s blocking nearly all of my training job requests with the message “The job failed due to an invalid training file. This training file was blocked by… --- ## [Worried about being banned- using the api and getting regular content policy violations for innocuous prompts](https://community.openai.com/t/worried-about-being-banned-using-the-api-and-getting-regular-content-policy-violations-for-innocuous-prompts/612890)
**Author:** [@devda](https://community.openai.com/u/devda)\ **Replies:** 31\ **Last updated:** [June 20, 2025, 11:24am UTC](https://community.openai.com/t/worried-about-being-banned-using-the-api-and-getting-regular-content-policy-violations-for-innocuous-prompts/612890 "2025-06-20T11:24:52Z")
I am using the api (specifically client.images.generate) to generate images. I sometimes get a content\_policy\_violation BadRequestError. However, the prompt I am using was written by openai itself. And when I run the pr… --- ## [Something like an adversarial attack on the image moderation endpoint](https://community.openai.com/t/something-like-an-adversarial-attack-on-the-image-moderation-endpoint/1276514)
**Author:** [@pyromaniac](https://community.openai.com/u/pyromaniac)\ **Replies:** 2\ **Last updated:** [June 4, 2025, 3:18am UTC](https://community.openai.com/t/something-like-an-adversarial-attack-on-the-image-moderation-endpoint/1276514 "2025-06-04T03:18:38Z")
I just wanted to share this with anybody really and figured here is as good as anywhere. I was surprised by how easy it is to synthesize an image that fools the image moderation model; given that you have no access to t… --- ## [Serious iterative creative project blocked by account-level moderation poisoning — no remedy path for Plus users](https://community.openai.com/t/serious-iterative-creative-project-blocked-by-account-level-moderation-poisoning-no-remedy-path-for-plus-users/1275968)
**Author:** [@Brevet05](https://community.openai.com/u/Brevet05)\ **Replies:** 0\ **Last updated:** [June 2, 2025, 2:02pm UTC](https://community.openai.com/t/serious-iterative-creative-project-blocked-by-account-level-moderation-poisoning-no-remedy-path-for-plus-users/1275968 "2025-06-02T14:02:20Z")
I’m a long-term ChatGPT Plus user building complex, iterative creative projects with original characters and world-building (including Clockwork Rebellion, global travel series with Ian & Aja, and other advanced narrativ… --- ## [DALL-E API: preposterous new moderations with no "low" parameter](https://community.openai.com/t/dall-e-api-preposterous-new-moderations-with-no-low-parameter/1274717)
**Author:** [@\_j](https://community.openai.com/u/_j)\ **Replies:** 0\ **Last updated:** [June 1, 2025, 12:35am UTC](https://community.openai.com/t/dall-e-api-preposterous-new-moderations-with-no-low-parameter/1274717 "2025-06-01T00:35:40Z")
Over and over, there are forum anecdote of simply trying to use dall-e-2 or 3 now with innocent-looking prompts, and now getting this incorrigible error: Error code: 400 - {'error': {'message': None, 'type': 'image\_gene… --- ## [Overzealous Content Moderation Silently Blocking Harmless Prompts in ChatGPT](https://community.openai.com/t/overzealous-content-moderation-silently-blocking-harmless-prompts-in-chatgpt/1155099)
**Author:** [@kencheng011](https://community.openai.com/u/kencheng011)\ **Replies:** 1\ **Last updated:** [May 26, 2025, 3:13am UTC](https://community.openai.com/t/overzealous-content-moderation-silently-blocking-harmless-prompts-in-chatgpt/1155099 "2025-05-26T03:13:32Z")
I’m a regular ChatGPT user (not a developer) who often uses the model for thoughtful conversations and creative writing. Lately, I’ve run into an issue where certain prompts—completely safe, nonviolent, non-sensitive—ar… --- ## [Decoupling AI Generation from Moderation: The Modular Governor System](https://community.openai.com/t/decoupling-ai-generation-from-moderation-the-modular-governor-system/1157728)
**Author:** [@CyberCoyote](https://community.openai.com/u/CyberCoyote)\ **Replies:** 0\ **Last updated:** [March 30, 2025, 5:09pm UTC](https://community.openai.com/t/decoupling-ai-generation-from-moderation-the-modular-governor-system/1157728 "2025-03-30T17:09:49Z")
Before we dive in, I want to clarify something upfront: The core idea I’m about to share originated from me, but I’m using ChatGPT as my voice, as I’m not very efficient in expressing complex ideas quickly and clearly. … --- ## [Safe messages are being wrongly flagged in ChatGPT 4 — need help](https://community.openai.com/t/safe-messages-are-being-wrongly-flagged-in-chatgpt-4-need-help/1154461)
**Author:** [@allforaliyah](https://community.openai.com/u/allforaliyah)\ **Replies:** 0\ **Last updated:** [March 28, 2025, 12:29pm UTC](https://community.openai.com/t/safe-messages-are-being-wrongly-flagged-in-chatgpt-4-need-help/1154461 "2025-03-28T12:29:52Z")
Hi, I’m a paid ChatGPT Plus subscriber, and I’ve recently had multiple messages get flagged and removed, even though they contain nothing inappropriate. For example, a message asking “What is deductive reasoning?” was b… --- ## [Is the moderation API available for non OpenAI related content?](https://community.openai.com/t/is-the-moderation-api-available-for-non-openai-related-content/1135941)
**Author:** [@paths](https://community.openai.com/u/paths)\ **Replies:** 1\ **Last updated:** [March 5, 2025, 12:30pm UTC](https://community.openai.com/t/is-the-moderation-api-available-for-non-openai-related-content/1135941 "2025-03-05T12:30:35Z")
In the past this was not allowed however, the restriction of it being exclusive for OpenAI generated content seems to have been removed from the documentation. Does this limitation still hold off in the official docs or … --- ## [Moderation API not working with project scoped API key](https://community.openai.com/t/moderation-api-not-working-with-project-scoped-api-key/971313)
**Author:** [@\_mattias](https://community.openai.com/u/_mattias)\ **Replies:** 4\ **Last updated:** [December 10, 2024, 2:33pm UTC](https://community.openai.com/t/moderation-api-not-working-with-project-scoped-api-key/971313 "2024-12-10T14:33:16Z")
The moderations endpoint is not working when using a project API key. It seems like the endpoint works as expected if the API key is scoped Default project. This example request results in 500: curl .../v1/moderations… [Next page](https://community.openai.com/tag/moderation/169.md?match_all_tags=true&page=1&tags%5B%5D=moderation)