I'm getting the error:`AiError: 3040: Capacity temporarily exceeded, please try again.` This appears

I'm getting the error:

AiError: 3040: Capacity temporarily exceeded, please try again.

AiError: 3040: Capacity temporarily exceeded, please try again.

AiError: 3040: Capacity temporarily exceeded, please try again.

AiError: 3040: Capacity temporarily exceeded, please try again. This appears to happen intermittently, I have had this occur in the past, and it eventually resolves itself. Is there any information as to the cause, how to prevent it and what can be done to resolve it when these errors occur?

BblindChicken I'm getting the error:`AiError: 3040: Capacity temporarily exceeded, please try ...

Chaika•10/20/25, 11:44 PM

as far as been said in the past, they just need to scale
When I use worker ai, I get an error.
workers-ai
might be helpful for them if you include the model name here.

CChaika as far as been said in the past, they just need to scale https://discord.com/cha...

blindChickenOP•10/21/25, 12:52 AM

In this case I was calling "@cf/meta/llama-4-scout-17b-16e-instruct""@cf/meta/llama-4-scout-17b-16e-instruct"

blindChickenOP•10/21/25, 12:53 AM

So what you are suggesting is that this is model specific. Then I should be able to catch the error and then call a backup model.

BblindChicken So what you are suggesting is that this is model specific. Then I should be able...

Chaika•10/21/25, 12:59 AM

yes, def model specific. Also those look resolved now, I have some workers ai usage and saw ~43 of those around the time you reported, but none for the past bid

CChaika yes, def model specific. Also those look resolved now, I have some workers ai u...

blindChickenOP•10/21/25, 1:01 AM

Yes, these generally don't last long. But the problem is that when they occur they basically break my app. So I need some kind of a fallback so that my users can continue to be served.

koalaspider•10/21/25, 12:44 PM

Hi @samjs, the AI does not respond on the deploy version but the dev version works fine. I rebuilt everything on the deploy version yesterday. The built process was completed and no error. But when it comes to wrangler deploy, it said "A request to the Cloudflare API failed.
Authentication error [code: 10000]"

robinsloan•10/21/25, 2:48 PM

Just want to register here that the Workers AI users of the world would love to see the new DeepSeek-OCR among the offerings!

koalaspider•10/21/25, 3:16 PM

My suspect is the execution of "npx wrangl deploy" lack of permission. But I already has a build token which I gave almost all the permission I can think of..

Kkoalaspider My suspect is the execution of "npx wrangl deploy" lack of permission. But I al...

samjs•10/21/25, 3:55 PM

If it's wrangler deploy that's failing it might be worth asking in #wrangler or even #general-help -- those folks might be able to provide more help in debugging this.

carter•10/21/25, 8:56 PM

Curious about the current state of this - is there any way to use CLIP models on CF?
workers-ai

carter•10/21/25, 9:09 PM

^ or if anyone has found any workarounds for hosting multimodal retrieval apps on CF

Ashkan•10/21/25, 10:03 PM

is it possible to deposit 100$ for only AI use? I mean pre-deposit and at max 100$ as I have for AI cost.

Laurence•10/22/25, 9:35 AM

Hello, I'm having an issue with @cf/deepgram/flux. Whenever I try to use it I get an error "Argument of type '"@cf/deepgram/flux"' is not assignable to parameter of type 'keyof AiModels'.". Yet I'm able to run other models without issue.

LLaurence Hello, I'm having an issue with @cf/deepgram/flux. Whenever I try to use it I g...

Kevin•10/22/25, 9:47 AM

do you have the latest version of wrangler?

Laurence•10/22/25, 9:48 AM

Yes.

Laurence•10/22/25, 9:55 AM

When the error occurred I updated my cloudflare/ai using "npm install @Cloudflare/ai@latest" but the error is still there.

Kevin•10/22/25, 10:17 AM

Seems like the list has not been updated in a while https://github.com/cloudflare/ai/blob/main/types/workerd.d.ts#L3924

GitHub

ai/types/workerd.d.ts at main · cloudflare/ai

Contribute to cloudflare/ai development by creating an account on GitHub.

KKevin Seems like the list has not been updated in a while https://github.com/cloudflar...

Laurence•10/22/25, 10:20 AM

I'll try using it like this, not ideal but maybe it will work.

James•10/22/25, 12:49 PM

Types for workers AI feel mostly abandoned at this point sadly. I’ve raised it again and again, both publicly and privately, and there’s never any real conclusion:

- https://github.com/cloudflare/workerd/issues/5080
- https://github.com/cloudflare/workerd/issues/2418
- https://github.com/cloudflare/workerd/issues/2181

If you want good DX, with a maintained platform, sdk, and reliable inference, I’d personally recommend using vercel’s ai sdk and OpenAI directly at this point unfortunately.

JJames Types for workers AI feel mostly abandoned at this point sadly. I’ve raised it a...

Laurence•10/22/25, 1:24 PM

Thanks, I'll check it them out. I've currently been using fal.ai but it doesn't have all the models that I'm looking for.

LLaurence I'll try using it like this, not ideal but maybe it will work.

Laurence•10/22/25, 8:56 PM

So, the method that I used above works but it's kind of finicky. The response is kind of inconsistent at it throws a lot of internal errors. So, I'm currently using the direct WebSocket connection according to Deepgram's website https://developers.deepgram.com/docs/flux/quickstart (works well). I'll try Cloudflare's implementation later.

Getting Started with Flux | Deepgram's Docs

Flux is the first conversational speech recognition model built specifically for voice agents. Unlike traditional STT that just transcribes words, Flux understands conversational flow and automatically handles turn-taking.

JJames Types for workers AI feel mostly abandoned at this point sadly. I’ve raised it a...

carter•10/23/25, 3:19 AM

Wow, that's really unfortunate. No indication that they'll work to improve workers AI? I'm a bit new to CF's inference, but what do you mean by (not) "reliable inference"? Is the latency all over?

samjs•10/23/25, 3:10 PM

Hey @James , @carter and others. Apologies for the slow progress here, and I understand and share the frustration.

We are absolutely working on fixing these issues, and we hope to have an update soon. We've got a little backed up on some work here, but should be getting around to it soon. To give you an idea of the kinds of things we've been working on:

- Improved platform stability and performance: we've recently rolled out a lot of "invisible" changes to make the platform more stable to things like high load and more consistently return successful responses. While there will still be occasions that people will see 3040 errors due to limited capacity, these should be much less often than before
- For the gpt-oss models, we've been waiting for some vLLM changes to land before pushing out more updates. In hindsight we shouldn't have let ourselves be blocked on this, and we're working to address this by seeing if we can build this ourselves internally. That's going to bring streaming, chat/completions support, and support for async requests. Along with a number of bug fixes.
- Support for realtime audio models like deepgram/flux, and websocket support for those.

On the DX front -- all the feedback that gets shared here/in GitHub is absolutely heard internally. e.g. you have @Kevin and I both core member of the Workers AI team checking this regularly.

Ssamjs Hey @James , @carter and others. Apologies for the slow progress here, and I un...

James•10/23/25, 3:33 PM

Thanks Sam, excited for updates. I'd love to see DX around types with model releases a clear focus, so that models aren't added to the platform with an immediately negative DX. Other platforms have types available with great DX on day one or two, especially for platforms they advertise as a "partner", but some models on Cloudflare end up weeks, or even months out of date, if not missing entirely.

samjs•10/23/25, 3:37 PM

Agreed. We have a process and tooling problem we need to fix here. On the former, as you say we've been way to slow to update types along with model releases. And on the latter, currently updating types is a somewhat manual process for us (which obviously feeds into the former).

samjs•10/23/25, 3:38 PM

Kevin and I have been discussing a bunch how we want to improve it. We'll get better

James•10/23/25, 3:40 PM

Great to hear. Let me know if there's anything I can do to help here!

carter•10/23/25, 3:41 PM

Thanks for the updates Sam! Appreciate the communication.

JJames Great to hear. Let me know if there's anything I can do to help here!

samjs•10/23/25, 3:46 PM

Thanks James! Will share with you updated types for feedback when we have them

! Tᐯ-GᗩᗰE.ᗪEᐯ•10/24/25, 10:46 AM

How can I send to a model with mcp server?

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/meta/llama-4-scout-17b-16e-instruct \
  -X POST \
  -H "Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN" \
  -d '{ "messages": [{ "role": "system", "content": "You are a friendly assistant" }, { "role": "user", "content": "Why is pizza so good" }]}'

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/meta/llama-4-scout-17b-16e-instruct \
  -X POST \
  -H "Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN" \
  -d '{ "messages": [{ "role": "system", "content": "You are a friendly assistant" }, { "role": "user", "content": "Why is pizza so good" }]}'

!! Tᐯ-GᗩᗰE.ᗪEᐯ How can I send to a model with mcp server? ```curl https://api.cloudflare.com/cl...

! Tᐯ-GᗩᗰE.ᗪEᐯ•10/24/25, 10:47 AM

my server: https://mcp.exa.ai/mcp

Razmjoo•10/25/25, 12:34 PM

Hi guys, any active incidents here? I am getting 408 error on @cf/openai/gpt-oss-120b, status 408;

{
  "error": {
    "code": "invalid_prompt",
    "message": "AiError: AiError: Request timeout (a613c7db-647c-4c07-ba94-a5702bc99d52)"
  }
}

{
  "error": {
    "code": "invalid_prompt",
    "message": "AiError: AiError: Request timeout (a613c7db-647c-4c07-ba94-a5702bc99d52)"
  }
}

Razmjoo•10/25/25, 12:42 PM

@sunbuhui do I click on general support or bug report? unsure which team is it?

Razmjoo•10/25/25, 12:46 PM

@sunbuhui could you please point it out;

Razmjoo•10/25/25, 12:48 PM

done

Razmjoo•10/25/25, 1:00 PM

Seriously, dude? @sunbuhui You're trying to scam people for their wallets in the Cloudflare channel full of security experts during debugging an error?

Razmjoo•10/25/25, 1:01 PM

@samjs would you please advise, and also ban the scammer user?

RRazmjoo Seriously, dude? @sunbuhui You're trying to scam people for their wallets in th...

zegevlier•10/25/25, 1:03 PM

Thank you for the report, I have banned the user. For the next time, you can ping the green role (community champions) for moderation issues like this

zegevlier•10/25/25, 1:04 PM

And just to confirm, yes, this is a scam. Cloudflare will never ask you to join another discord server for support

Razmjoo•10/25/25, 1:04 PM

he did zero efford; asked directly for 'wallet info' what an impatent scammer

samjs•10/25/25, 2:45 PM

Hey @Razmjoo , thanks for reporting! And thank you Zegevlier for jumping on it.

With respect to the timeouts: I'm not seeing any indications of an outage. I can see the spike in inference times that would have caused the timeouts, but there's no correlation with location/server or anything like that to suggest there's a bug. And no other accounts were experiencing any spikes. Were the inputs particularly long? E.g. using reasoning high as well?

Razmjoo•10/25/25, 6:32 PM

@samjs input were a bit long (maybe around 50,60 kb) but the reasoning was default;

Razmjoo•10/25/25, 6:33 PM

i mean total message (system + user + json schema) were in total around 50-60kb

Razmjoo•10/25/25, 7:10 PM

I have reduced them to 19kb but still the same issue.

Iñaki Fuentes•10/27/25, 8:31 AM

Hey team, anyone know what’s going on here? Looks like the counters reset and show 10k neurons available

but I’m still getting an API error.

Is this expected or is something borked? Lmk if you’ve seen this too.

  "error": {
        "message": "4006: you have used up your daily free allocation of 10,000 neurons, please upgrade to Cloudflare's Workers Paid plan if you would like to continue usage.",
        "stage": "pipeline",
        "code": "internal_error"
    },

    "timestamp": "2025-10-27T08:26:51.928Z"

  "error": {
        "message": "4006: you have used up your daily free allocation of 10,000 neurons, please upgrade to Cloudflare's Workers Paid plan if you would like to continue usage.",
        "stage": "pipeline",
        "code": "internal_error"
    },

    "timestamp": "2025-10-27T08:26:51.928Z"

IIñaki Fuentes Hey team, anyone know what’s going on here? Looks like the counters reset and sh...

Iñaki Fuentes•10/27/25, 9:04 AM

To pay is always a solution, solved...

MichaelC•10/27/25, 12:26 PM

Are there changes ongoing with the llama 4 model? The latency has gone through the roof for about a week now and it is very unstable. Can see some data here as well https://delay.chaika.me/ai/@cf/meta/llama-4-scout-17b-16e-instruct.

ItsAsheer•10/28/25, 7:19 AM

Hi, so I've been trying to connect LiteLLM (LLM proxy) to Cloudflare and when i try to send a message i get an error (check below), doing this with other services doesnt give me this error so i believe its Cloudflare.

Error code: 400 - {'success': False, 'errors': [{'code': 7000, 'message': 'No route for that URI'}], 'messages': [], 'result': None}

Error code: 400 - {'success': False, 'errors': [{'code': 7000, 'message': 'No route for that URI'}], 'messages': [], 'result': None}

Base Url: https ://api.cloudflare.com/client/v4/accounts/{my account id}/ai/v1

(the space between https and :// is on purpose to not format it like a link)

si.kiskre.•10/28/25, 9:12 AM

worker paid vs. free
isn't 300000 per month equals to 10000 per day ??

zegevlier•10/28/25, 12:12 PM

Pretty much, yea. The difference is that with the 300k/month, you can (I think) use all of them up in a single day, then nothing for the rest of the month. With 10k/day, you cannot use any more than those 10k that day

I'm getting the error:`AiError: 3040: Capacity temporarily exceeded, please try again.` This appears

Similar Threads

Similar Threads

Similar Threads