I have a n8n workflow and the OpenAPI integrated into it. I have a node that is supposed to generate an image, and it worked for a long time, but without changing anything it now says “the service is receiving too many requests from you”. I’ve tried waiting 24 hours and still the same problem. Has anyone run into this before?
Probably because of that:
Ok got it thank you! Did this start last night for you as well?
I started having the problem last night as well (PST).
I created a new key and that worked for awhile but then sometime in the past 4-5 hours started having the same issue with 429s (being called from an n8n flow)
So it sounds like the API outage they are having is the root cause it what their support bot was saying.
Interesting, I tried creating a new key and I still ran into the same problem. Is yours saying Cloudflare error 1015 as well?
It looks like OpenAI is now saying API outage is solved and everything is fully operational, but I’m still having the same problem. Is it solved on your end?
Ugh. This is maddening. Yes I am getting the same issue now as well. This flow has worked fine since the model came out and then last night just started giving me these 429 errors.
The specfic error is below. I use replicate.com for some other models and just noticed that the image gen for this model is working there, so seems like there is something specific to n8n potentially?
Really frustrating as I didn’t provision time to triage and find a fix for this but we are down in production due to this.
[
{
“kind”:
“storage#objects”,
“nextPageToken”:
“Cgdza2lsbHMv”,
“items”:
[
{
“kind”:
“storage#object”,
“id”:
“clone-display-bucket/skills//1746372504651372”,
“selfLink”:
“https://www.googleapis.com/storage/v1/b/clone-display-bucket/o/skills%2F”,
“mediaLink”:
“https://storage.googleapis.com/download/storage/v1/b/clone-display-bucket/o/skills%2F?generation=1746372504651372&alt=media”,
“name”:
“skills/”,
“bucket”:
“clone-display-bucket”,
“generation”:
“1746372504651372”,
“metageneration”:
“1”,
“contentType”:
“text/plain”,
“storageClass”:
“STANDARD”,
“size”:
“0”,
“md5Hash”:
“1B2M2Y8AsgTpgAmY7PhCfg==”,
“crc32c”:
“AAAAAA==”,
“etag”:
“COyMpMaQio0DEAE=”,
“temporaryHold”:
false,
“eventBasedHold”:
false,
“timeCreated”:
“2025-05-04T15:28:24.676Z”,
“updated”:
“2025-05-04T15:28:24.676Z”,
“timeStorageClassUpdated”:
“2025-05-04T15:28:24.676Z”,
“timeFinalized”:
“2025-05-04T15:28:24.676Z”
}
],
“error”:
{
“message”:
“Try spacing your requests out using the batching settings under ‘Options’”,
“name”:
“AxiosError”,
“stack”:
“AxiosError: Request failed with status code 429\n at settle (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/axios@1.8.3/node_modules/axios/lib/core/settle.js:19:12)\n at RedirectableRequest.handleResponse (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/axios@1.8.3/node_modules/axios/lib/adapters/http.js:547:9)\n at RedirectableRequest.emit (node:events:530:35)\n at RedirectableRequest._processResponse (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/follow-redirects@1.15.9/node_modules/follow-redirects/index.js:409:10)\n at ClientRequest.RedirectableRequest._onNativeResponse (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/follow-redirects@1.15.9/node_modules/follow-redirects/index.js:102:12)\n at Object.onceWrapper (node:events:633:26)\n at ClientRequest.emit (node:events:518:28)\n at HTTPParser.parserOnIncomingClient [as onIncoming] (node:http_client:716:27)\n at HTTPParser.parserOnHeadersComplete (node:http_common:117:17)\n at TLSSocket.socketOnData (node:http_client:558:22)\n at TLSSocket.emit (node:events:518:28)\n at addChunk (node:internal/streams/readable:561:12)\n at readableAddChunkPushByteMode (node:internal/streams/readable:512:3)\n at TLSSocket.Readable.push (node:internal/streams/readable:392:5)\n at TLSWrap.onStreamRead (node:internal/stream_base_commons:189:23)\n at TLSWrap.callbackTrampoline (node:internal/async_hooks:130:17)\n at Axios.request (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/axios@1.8.3/node_modules/axios/lib/core/Axios.js:45:41)\n at processTicksAndRejections (node:internal/process/task_queues:105:5)\n at invokeAxios (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_openai@4.103.0_encoding@0.1.13_ws@8.17.1_zod@3.25.67/node_modules/n8n-core/src/execution-engine/node-execution-context/utils/request-helper-functions.ts:315:10)\n at proxyRequestToAxios (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_openai@4.103.0_encoding@0.1.13_ws@8.17.1_zod@3.25.67/node_modules/n8n-core/src/execution-engine/node-execution-context/utils/request-helper-functions.ts:707:20)\n at Object.request (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_openai@4.103.0_encoding@0.1.13_ws@8.17.1_zod@3.25.67/node_modules/n8n-core/src/execution-engine/node-execution-context/utils/request-helper-functions.ts:1753:4)”,
“code”:
“ERR_BAD_REQUEST”,
“status”:
429
}
}
]
We have different error codes. Mine is from cloudflare and yours seems to be from google. Hmmmmmm.
I’m experiencing the same issue right now. I can’t generate an image in n8n using the OpenAI API key, although I’m able to generate text and other content using the same key within n8n. I also tested a Python script with the same API key and was able to successfully generate an image. Does anyone have a solution to this?
Yep, I test a cURL and it worked as well. Then, I even tried an HTTP Post in n8n and that didn’t work either.
Does n8n have a dedicated channel to discuss such issues?
It looks like the OpenAI API is not the root cause here.