# \#gpt-4o-mini **URL:** https://community.openai.com/tag/gpt-4o-mini/683.md [Latest](https://community.openai.com/latest.md) · [Categories](https://community.openai.com/categories.md) · [Tags](https://community.openai.com/tags.md) --- ## [\`refusals\_v3\` moderation eval failing on fine-tuning jobs again — internal errors across \`gpt-4.1-nano\` and \`gpt-4o-mini\`](https://community.openai.com/t/refusals-v3-moderation-eval-failing-on-fine-tuning-jobs-again-internal-errors-across-gpt-4-1-nano-and-gpt-4o-mini/1380704)
**Author:** [@vicente](https://community.openai.com/u/vicente)\ **Replies:** 1\ **Last updated:** [September 20, 2026, 6:08pm UTC](https://community.openai.com/t/refusals-v3-moderation-eval-failing-on-fine-tuning-jobs-again-internal-errors-across-gpt-4-1-nano-and-gpt-4o-mini/1380704 "2026-09-20T18:08:35Z")
I’m hitting a consistent failure during the post-training moderation evaluation step on fine-tuning jobs. Training completes, checkpoints and the fine-tuned model are created, then the refusals\_v3 eval fails with interna… --- ## [API error: 429 You exceeded your current quota, please check your plan and billing details](https://community.openai.com/t/api-error-429-you-exceeded-your-current-quota-please-check-your-plan-and-billing-details/1379873)
**Author:** [@Vin.77](https://community.openai.com/u/Vin.77)\ **Replies:** 3\ **Last updated:** [April 27, 2026, 1:21pm UTC](https://community.openai.com/t/api-error-429-you-exceeded-your-current-quota-please-check-your-plan-and-billing-details/1379873 "2026-04-27T13:21:13Z")
In the past few weeks, I’ve been trying to add my OpenAI API to a project I’m building. However, even though everything seems to be set up correctly—I have available funds and the configuration appears to be fine—it stil… --- ## [Gpt-4o and gpt-4o-mini family fine-tuned models failing](https://community.openai.com/t/gpt-4o-and-gpt-4o-mini-family-fine-tuned-models-failing/1374660)
**Author:** [@Britt\_Torrance](https://community.openai.com/u/Britt_Torrance)\ **Replies:** 1\ **Last updated:** [February 20, 2026, 3:36am UTC](https://community.openai.com/t/gpt-4o-and-gpt-4o-mini-family-fine-tuned-models-failing/1374660 "2026-02-20T03:36:34Z")
We are using \`gpt-4o\` and \`gpt-4o-mini\` fine-tuned models in production. As of this morning they were working fine (02/19/26), but as of ~20:50 UTC we began to experience complete and consistent failures for all chat com… --- ## [Multimodal GPT-4o ignores detail: "low" for small JPEG images](https://community.openai.com/t/multimodal-gpt-4o-ignores-detail-low-for-small-jpeg-images/1367602)
**Author:** [@rwc](https://community.openai.com/u/rwc)\ **Replies:** 1\ **Last updated:** [December 15, 2025, 7:39pm UTC](https://community.openai.com/t/multimodal-gpt-4o-ignores-detail-low-for-small-jpeg-images/1367602 "2025-12-15T19:39:30Z")
When sending many low-resolution JPEG frames through the Chat Completions API using detail:"low" (or "auto"), GPT-4o and GPT-4o-mini produce massively inflated prompt token counts. Even with 128×72 JPEG images, the mode… --- ## [Avoiding “Let me check / One moment…” for GPT 4o mini](https://community.openai.com/t/avoiding-let-me-check-one-moment-for-gpt-4o-mini/1368806)
**Author:** [@lisek75](https://community.openai.com/u/lisek75)\ **Replies:** 0\ **Last updated:** [December 9, 2025, 12:43pm UTC](https://community.openai.com/t/avoiding-let-me-check-one-moment-for-gpt-4o-mini/1368806 "2025-12-09T12:43:26Z")
I’m building a WhatsApp bot using LangGraph (with tools) that handles medical appointment scheduling. It works, but I keep running into an annoying behaviour time to time: Human: hello do I have any appointment? AI: Let… --- ## [RateLimitError (429) on Tier-5 Account While Using GPT-4o-mini – Clarification Requested](https://community.openai.com/t/ratelimiterror-429-on-tier-5-account-while-using-gpt-4o-mini-clarification-requested/1366574)
**Author:** [@vlakhani](https://community.openai.com/u/vlakhani)\ **Replies:** 1\ **Last updated:** [November 17, 2025, 6:52pm UTC](https://community.openai.com/t/ratelimiterror-429-on-tier-5-account-while-using-gpt-4o-mini-clarification-requested/1366574 "2025-11-17T18:52:33Z")
I’m on Tier-5 and using gpt-4o-mini through the Assistants API, but I keep getting RateLimitError: 429 even though my request volume is very low and should be far below Tier-5 limits. openai.RateLimitError: Error code: … --- ## [Openai 4o-mini fine-tuned model not responding](https://community.openai.com/t/openai-4o-mini-fine-tuned-model-not-responding/1366270)
**Author:** [@Dhruv3](https://community.openai.com/u/Dhruv3)\ **Replies:** 1\ **Last updated:** [November 14, 2025, 12:09pm UTC](https://community.openai.com/t/openai-4o-mini-fine-tuned-model-not-responding/1366270 "2025-11-14T12:09:05Z")
Openai 4o-mini finetune model not responding suddenly from 14th Nov. Error processing batch 1: Error code: 500 - {‘error’: {‘message’: ‘The server had an error while processing your request. Sorry about that!’, ‘type’: … --- ## [Facing issues in GPT-4o\_mini as batch results doesnt show failure but out of x records only x/10 are coming as an output](https://community.openai.com/t/facing-issues-in-gpt-4o-mini-as-batch-results-doesnt-show-failure-but-out-of-x-records-only-x-10-are-coming-as-an-output/1145451)
**Author:** [@hemantmetaverse88](https://community.openai.com/u/hemantmetaverse88)\ **Replies:** 3\ **Last updated:** [November 7, 2025, 11:24pm UTC](https://community.openai.com/t/facing-issues-in-gpt-4o-mini-as-batch-results-doesnt-show-failure-but-out-of-x-records-only-x-10-are-coming-as-an-output/1145451 "2025-11-07T23:24:50Z")
Facing issues in GPT-4o\_mini as batch results doesnt show failure but out of x records only x/10 are coming as an output --- ## [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 … --- ## [GPT-4o giving only one suggestion despite asking for multiple; GPT-4o-mini hallucinating when prompt gets detailed](https://community.openai.com/t/gpt-4o-giving-only-one-suggestion-despite-asking-for-multiple-gpt-4o-mini-hallucinating-when-prompt-gets-detailed/1363586)
**Author:** [@Nipunika\_Karupotula](https://community.openai.com/u/Nipunika_Karupotula)\ **Replies:** 2\ **Last updated:** [October 24, 2025, 12:30pm UTC](https://community.openai.com/t/gpt-4o-giving-only-one-suggestion-despite-asking-for-multiple-gpt-4o-mini-hallucinating-when-prompt-gets-detailed/1363586 "2025-10-24T12:30:55Z")
Hi everyone, I’m working on a POC for an auto-suggestion chatbot (SAP use case), where the model should suggest 2–5 possible answers (for example, relevant function modules or tables). I’ve noticed this behavior: Wh… --- ## [Where is gpt-4o-mini-realtime?](https://community.openai.com/t/where-is-gpt-4o-mini-realtime/1353571)
**Author:** [@SeaOfAsh](https://community.openai.com/u/SeaOfAsh)\ **Replies:** 6\ **Last updated:** [October 20, 2025, 8:20am UTC](https://community.openai.com/t/where-is-gpt-4o-mini-realtime/1353571 "2025-10-20T08:20:54Z")
I noticed the gpt-4o-mini-realtime is not available anymore in the playground. And I have a production app using it, it is unclear to me if it will be continued to be supported on the webrtc api?? Also, 4o-mini-realtime… --- ## [Responses seems to get stuck in a loop with vector stores](https://community.openai.com/t/responses-seems-to-get-stuck-in-a-loop-with-vector-stores/1142385)
**Author:** [@grantc](https://community.openai.com/u/grantc)\ **Replies:** 11\ **Last updated:** [October 14, 2025, 8:46pm UTC](https://community.openai.com/t/responses-seems-to-get-stuck-in-a-loop-with-vector-stores/1142385 "2025-10-14T20:46:45Z")
I have a fairly lengthy system message and output json\_schema and when I start a responses conversation it works great until the model (gpt-4o-mini) decides it needs to search for something. If it’s not found it just sli… --- ## [Why are model modalities restricted to just text and Images?](https://community.openai.com/t/why-are-model-modalities-restricted-to-just-text-and-images/1360629)
**Author:** [@SUNIL\_KUMAR](https://community.openai.com/u/SUNIL_KUMAR)\ **Replies:** 1\ **Last updated:** [September 30, 2025, 9:12pm UTC](https://community.openai.com/t/why-are-model-modalities-restricted-to-just-text-and-images/1360629 "2025-09-30T21:12:41Z")
Why are model modalities restricted to just text and Images in the OpenAI Platform where as the release articles mentioned their ability to take audio video too and output audio ? Ex: GPT-4o, GPT-4o mini --- ## [Batch Usage and token limit with gpt-4o-mini](https://community.openai.com/t/batch-usage-and-token-limit-with-gpt-4o-mini/1238999)
**Author:** [@MathieuLo](https://community.openai.com/u/MathieuLo)\ **Replies:** 2\ **Last updated:** [September 12, 2025, 6:14pm UTC](https://community.openai.com/t/batch-usage-and-token-limit-with-gpt-4o-mini/1238999 "2025-09-12T18:14:38Z")
hi I am using Batch API (or https://platform.openai.com/batches/) with gpt-4o-mini and I do get a token limit error Enqueued token limit reached for gpt-4o-mini in organization org-\*\*\*\*. Limit: 2,000,000 enqueued tok… --- ## [Gpt-4o-mini stops following instructions after a few turns](https://community.openai.com/t/gpt-4o-mini-stops-following-instructions-after-a-few-turns/1356922)
**Author:** [@bsamuele](https://community.openai.com/u/bsamuele)\ **Replies:** 5\ **Last updated:** [September 12, 2025, 7:18am UTC](https://community.openai.com/t/gpt-4o-mini-stops-following-instructions-after-a-few-turns/1356922 "2025-09-12T07:18:14Z")
Hello, Here’s some context to my issue: I built a chatbot that is integrated into an educational app. There is a main knowledge base, with a PDF file containing all the information that’s needed to answer user question… --- ## [Conversation\_locked error in Responses API](https://community.openai.com/t/conversation-locked-error-in-responses-api/1355268)
**Author:** [@bsamuele](https://community.openai.com/u/bsamuele)\ **Replies:** 1\ **Last updated:** [September 10, 2025, 8:17am UTC](https://community.openai.com/t/conversation-locked-error-in-responses-api/1355268 "2025-09-10T08:17:41Z")
Hello, I am using the responses API with streaming and function calling in a chatbot application. Here’s a minimal version of how I’m handling conversations: import asyncio import json from typing import Any, Dict, Lis… --- ## [Fine-tuning blocked by moderation system](https://community.openai.com/t/fine-tuning-blocked-by-moderation-system/878133)
**Author:** [@trd88](https://community.openai.com/u/trd88)\ **Replies:** 43\ **Last updated:** [August 27, 2025, 12:52pm UTC](https://community.openai.com/t/fine-tuning-blocked-by-moderation-system/878133 "2025-08-27T12:52:59Z")
I tried to run a fine-tuning job using GPT-4o mini but received the following error: “This training file was blocked by our moderation system because it contains too many examples that violate OpenAI’s usage policies, o… --- ## [Bizarre issue preventing response from gpt-4o-mini (‘The model produces invalid content’)](https://community.openai.com/t/bizarre-issue-preventing-response-from-gpt-4o-mini-the-model-produces-invalid-content/875432)
**Author:** [@Aimjock](https://community.openai.com/u/Aimjock)\ **Replies:** 8\ **Last updated:** [February 27, 2025, 8:19pm UTC](https://community.openai.com/t/bizarre-issue-preventing-response-from-gpt-4o-mini-the-model-produces-invalid-content/875432 "2025-02-27T20:19:26Z")
I’m having an extremely odd issue that I’ve been troubleshooting. I returned to my AI chatbot project recently, and it’s been a while. Last time, it used gpt-3.5-turbo, but I switched to gpt-4o-mini. I am getting a 500 e… --- ## [Gpt-4o-mini-transcribe ignores romanization prompts while gpt-4o-transcribe works](https://community.openai.com/t/gpt-4o-mini-transcribe-ignores-romanization-prompts-while-gpt-4o-transcribe-works/1323630)
**Author:** [@Block\_Faces](https://community.openai.com/u/Block_Faces)\ **Replies:** 1\ **Last updated:** [July 24, 2025, 4:10pm UTC](https://community.openai.com/t/gpt-4o-mini-transcribe-ignores-romanization-prompts-while-gpt-4o-transcribe-works/1323630 "2025-07-24T16:10:52Z")
For some reason the 4o-mini transcriptions do respect instructions to return roman characters. gpt-4o-transcribe correctly follows prompts to output Roman characters only gpt-4o-mini-transcribe ignores the same prompt … --- ## [Degraded performance when calling finetuned gpt-4o-mini](https://community.openai.com/t/degraded-performance-when-calling-finetuned-gpt-4o-mini/1321441)
**Author:** [@toastywaffles888](https://community.openai.com/u/toastywaffles888)\ **Replies:** 0\ **Last updated:** [July 21, 2025, 10:42pm UTC](https://community.openai.com/t/degraded-performance-when-calling-finetuned-gpt-4o-mini/1321441 "2025-07-21T22:42:02Z")
Is anyone having seriously degraded performance with finetuned gpt-4o-mini models? I’m using json output format and am getting extremely malformed json output that makes 0 sense. I have a built in retry mechanism which s… --- ## [Grok-4 applied to real world RAG application - Overthinking is not always the solution](https://community.openai.com/t/grok-4-applied-to-real-world-rag-application-overthinking-is-not-always-the-solution/1314361)
**Author:** [@SomebodySysop](https://community.openai.com/u/SomebodySysop)\ **Replies:** 12\ **Last updated:** [July 19, 2025, 9:44pm UTC](https://community.openai.com/t/grok-4-applied-to-real-world-rag-application-overthinking-is-not-always-the-solution/1314361 "2025-07-19T21:44:15Z")
I have a RAG application used to return answers based upon a dataset of legal agreements. For the past 6 months or so, in trying all of the major LLMs, we have found o3-mini to be the best at returning reasonably good … --- ## [ISSUE: Image Analysis for text correction using GPT-4o-mini](https://community.openai.com/t/issue-image-analysis-for-text-correction-using-gpt-4o-mini/1314077)
**Author:** [@Soch\_Post\_Production](https://community.openai.com/u/Soch_Post_Production)\ **Replies:** 5\ **Last updated:** [July 16, 2025, 12:59pm UTC](https://community.openai.com/t/issue-image-analysis-for-text-correction-using-gpt-4o-mini/1314077 "2025-07-16T12:59:57Z")
Hey guys, I am building a project which uses the text-detection capabilities of GPT-4o-mini in an image. The idea is to review video footage to analyse mistakes in text during editing. I am extracting frames every secon… --- ## [Issues with Role Persistence and Debugging in the Realtime Model](https://community.openai.com/t/issues-with-role-persistence-and-debugging-in-the-realtime-model/1313445)
**Author:** [@Mican](https://community.openai.com/u/Mican)\ **Replies:** 2\ **Last updated:** [July 15, 2025, 6:26pm UTC](https://community.openai.com/t/issues-with-role-persistence-and-debugging-in-the-realtime-model/1313445 "2025-07-15T18:26:10Z")
Hi, I’m experiencing a couple of issues while working with the OpenAI Realtime model and would appreciate any insights or suggestions from the community (or the OpenAI team): Staying in character: Even when I provide … --- ## [How to Effectively Use the "developer" Role in OpenAI Responses API?](https://community.openai.com/t/how-to-effectively-use-the-developer-role-in-openai-responses-api/1233491)
**Author:** [@gopichandar](https://community.openai.com/u/gopichandar)\ **Replies:** 3\ **Last updated:** [July 11, 2025, 7:17am UTC](https://community.openai.com/t/how-to-effectively-use-the-developer-role-in-openai-responses-api/1233491 "2025-07-11T07:17:56Z")
I’ve been working with the Assistant API and recently migrated to the new Responses API. I’m currently using the instructions field and function calling (via tool\_choice, tool\_outputs, etc.), and everything is working fi… --- ## [I am getting the same prompt back as the response](https://community.openai.com/t/i-am-getting-the-same-prompt-back-as-the-response/1293171)
**Author:** [@mojjupattu](https://community.openai.com/u/mojjupattu)\ **Replies:** 6\ **Last updated:** [June 24, 2025, 12:06pm UTC](https://community.openai.com/t/i-am-getting-the-same-prompt-back-as-the-response/1293171 "2025-06-24T12:06:09Z")
I am encountering an issue where the assistant echoes my prompt back instead of providing an actual response. Specifically, I am using the “user” role to prompt the assistant , but the response returned is the same as m… --- ## [Code interpreter in gpt-4o-mini](https://community.openai.com/t/code-interpreter-in-gpt-4o-mini/1260104)
**Author:** [@ayush.patel](https://community.openai.com/u/ayush.patel)\ **Replies:** 5\ **Last updated:** [May 13, 2025, 11:52pm UTC](https://community.openai.com/t/code-interpreter-in-gpt-4o-mini/1260104 "2025-05-13T23:52:05Z")
While invoking the code interpreter tool with 4o-mini, I was facing this issue “no image is returned”, but as soon as I switch to 4o, the image is generated. I’ve scoured the official docs and examples but can’t find any… --- ## [File Upload to OpenAI API Returns “System Error” via Postman – Works in Other Apps](https://community.openai.com/t/file-upload-to-openai-api-returns-system-error-via-postman-works-in-other-apps/1255208)
**Author:** [@Deepika\_Giri](https://community.openai.com/u/Deepika_Giri)\ **Replies:** 0\ **Last updated:** [May 8, 2025, 11:46am UTC](https://community.openai.com/t/file-upload-to-openai-api-returns-system-error-via-postman-works-in-other-apps/1255208 "2025-05-08T11:46:54Z")
I’m facing a persistent issue while using the OpenAI file upload API (https://api.openai.com/v1/files) through Postman for my Assistant API integration. :white\_check\_mark: Here’s what I have already confirmed and tried: … --- ## [Avoiding jailbreak flag at a Generation flag in RAG](https://community.openai.com/t/avoiding-jailbreak-flag-at-a-generation-flag-in-rag/1254121)
**Author:** [@Zofia\_Smolen](https://community.openai.com/u/Zofia_Smolen)\ **Replies:** 1\ **Last updated:** [May 7, 2025, 12:35pm UTC](https://community.openai.com/t/avoiding-jailbreak-flag-at-a-generation-flag-in-rag/1254121 "2025-05-07T12:35:30Z")
Hello everybody I am using GPT 4o mini for my RAG pipeline. During generation, I am sending out a prompt along with some procedures I have found. I am repeatedly facing the jailbreak issue even though the content I am … --- ## [Gpt-4o is really bad at NER tasks](https://community.openai.com/t/gpt-4o-is-really-bad-at-ner-tasks/1253078)
**Author:** [@saaspeter](https://community.openai.com/u/saaspeter)\ **Replies:** 0\ **Last updated:** [May 6, 2025, 9:08am UTC](https://community.openai.com/t/gpt-4o-is-really-bad-at-ner-tasks/1253078 "2025-05-06T09:08:58Z")
I am trying to extract some medical symptom entity from the user’s question, but I found gpt4o is unable to extract these entities, I was surprised at the result, then I tested other platforms(e.g: gemini and other platf… --- ## [Incorrect language detection](https://community.openai.com/t/incorrect-language-detection/1250177)
**Author:** [@Tikker](https://community.openai.com/u/Tikker)\ **Replies:** 0\ **Last updated:** [May 3, 2025, 9:33am UTC](https://community.openai.com/t/incorrect-language-detection/1250177 "2025-05-03T09:33:58Z")
I am using the gpt-4o-mini as the model for summarization of text. The prompt is as follows: Provide a concise summary in less than 400 characters of the following text. Keep the output language the same as the input la… [Next page](https://community.openai.com/tag/gpt-4o-mini/683.md?match_all_tags=true&page=1&tags%5B%5D=gpt-4o-mini)