I’m looking for access to Claude and other models before I build against something like open router.

CCodingCoop | Co-Founder Nullshot I’m looking for access to Claude and other models before I build against somethi...

I

Isaac McFadyen•9/28/25, 10:02 AM

Workers AI is Cloudflare-run models only, which does not include Claude.

C

CodingCoop | Co-Founder NullshotOP•9/28/25, 1:00 PM

Am I getting confused with gateway?

C

CodingCoop | Co-Founder NullshotOP•9/28/25, 1:04 PM

Sorry I did https://blog.cloudflare.com/ai-gateway-aug-2025-refresh/

The Cloudflare Blog

AI Gateway now gives you access to your favorite AI models, dynamic...

AI Gateway simplifies AI app development with unified billing, secure key storage, and dynamic routing. Gain observability and control over costs, API keys, and traffic, connecting to major AI providers through a single endpoint.

Z

zsueo•9/28/25, 5:47 PM

out of curiosity does workers-ai use durable objects with web-gpu internally? or is it an entirely custom cloudflare product?

Zzsueo out of curiosity does workers-ai use durable objects with web-gpu internally? or...

I

Isaac McFadyen•9/28/25, 5:50 PM

A mix of custom and off-the-shelf engines, no WebGPU. It's been blogged about here: https://blog.cloudflare.com/how-cloudflare-runs-more-ai-models-on-fewer-gpus/

I

Isaac McFadyen•9/28/25, 5:51 PM

See specifically this section: https://blog.cloudflare.com/how-cloudflare-runs-more-ai-models-on-fewer-gpus/#how-omni-runs-multiple-models-for-workers-ai

AI models can run in a variety of inference engines or backends: vLLM, Python, and now our very own inference engine, Infire.

Z

zsueo•9/28/25, 5:53 PM

ah cool thanks!

A

Ashkan•9/29/25, 4:31 PM

I encountered this error:

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

I put setName everywhere in the codebase to fix it but no success. do u have any idea to temporary resolve it until major updates come?

AAshkan Hello, when I want to poll batch request I encounter this error: `Error: 3030: 1...

K

Kevin•9/29/25, 5:06 PM

Hey can you share an example payload you’re sending for polling the batch request

KKevin Hey can you share an example payload you’re sending for polling the batch reques...

A

Ashkan•9/29/25, 10:17 PM

I've had that error almost days ago(I can't remember the payload) but the problem was related to JSON format of the

payload

payload

payload

payload and I could resolve the error. although the error resolved and no more exceptions were thrown but when I was checking status of the batch job it was showing

invalid parameters

invalid parameters

invalid parameters

invalid parameters. so I decided to suspend my works around the batch processing until stable version of that is announced.

AAshkan I've had that error almost days ago(I can't remember the payload) but the proble...

A

Ashkan•9/29/25, 10:22 PM

this is the part of the code I was using for batch process:

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

A

Ashkan•9/29/25, 10:24 PM

it should be noted

input

input

input

input of type

Array

Array

Array

Array worked but I wasn't able to run it when

input

input

input

input was of type

string

string

string

string (openai compatible JSON format)

D

displayname•9/29/25, 10:44 PM

Hey, could we please get some eyes on workers-and-pages-helpOpenAI Completions compatibility for gpt-oss models?
Sorry I didn't know where to open the thread

A

ajgeiss0702•9/30/25, 1:23 AM

just got an error i havent seen before with

gpt-oss-20b

gpt-oss-20b

gpt-oss-20b

gpt-oss-20b

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

account id:

f55b85c8a963663b11036975203c63c0

f55b85c8a963663b11036975203c63c0

f55b85c8a963663b11036975203c63c0

f55b85c8a963663b11036975203c63c0
(there is no stack trace above)

Z

Zetax•10/1/25, 6:29 AM

I wish the types would work for this

Wanted to try out a model and the response type for it is completely broken.

Bildschirmfoto_2025-10-01_um_08.28.55.png

J

James•10/2/25, 6:34 PM

Workers AI types need a lot of love, yeah.
- https://github.com/cloudflare/workerd/issues/2181
- https://github.com/cloudflare/workerd/issues/2418
- https://github.com/cloudflare/workerd/issues/5080

N

Nova Sven Cat•10/3/25, 7:14 PM

I'm using workers AI with the free plan and it still works even when I reached the quota, what is happening?

N

Nova Sven Cat•10/3/25, 8:00 PM

Daily usage (resets at 00:00 UTC) - Neurons used today: 32.48k/10k

N

Nova Sven Cat•10/3/25, 8:28 PM

You have exceeded the Neuron limit of 10,000 for this today. Upgrade your plan

NNova Sven Cat > You have exceeded the Neuron limit of 10,000 for this today. Upgrade your plan

Z

Zetax•10/3/25, 9:58 PM

why would you report that though

N

Nova Sven Cat•10/3/25, 9:58 PM

i have no idea why it's still working so i thought it was a bug

Z

Zetax•10/3/25, 9:58 PM

Maybe it's intentional, some overage to not discourage customers

Z

Zetax•10/3/25, 9:59 PM

Not sure

Z

Zetax•10/3/25, 9:59 PM

Although 3x seems a bit much lol

N

Nova Sven Cat•10/3/25, 9:59 PM

yeah im using the ai for an irc bot lmao

ZZetax Maybe it's intentional, some overage to not discourage customers

N

Nova Sven Cat•10/3/25, 10:02 PM

from the docs it says any future reqs will error if I reach that neuron quota :P

All limits reset daily at 00:00 UTC. If you exceed any one of the above limits, further operations will fail with an error.

A

Anon•10/4/25, 1:41 AM

Hey! I'm a software dev. I'm interested in building a RAG system and would like to hear y'all opinions on this platform when it comes to Workers AI and Vectorize. Thanks :3

A

Ashkan•10/5/25, 12:02 AM

Hey, how can I have message history such that ai model will have a message history and depend on this history will answer. for example.

User: sum of 2 + 2? -> Model: the answer is 4 -> User:now multiply the result by 2

User: sum of 2 + 2? -> Model: the answer is 4 -> User:now multiply the result by 2

User: sum of 2 + 2? -> Model: the answer is 4 -> User:now multiply the result by 2

User: sum of 2 + 2? -> Model: the answer is 4 -> User:now multiply the result by 2 at last user user input, ai model should have a history of messages and know what the

result

result

result

result is.

AAshkan Hey, how can I have message history such that ai model will have a message histo...

I

Isaac McFadyen•10/5/25, 12:07 AM

That is possible but Workers AI will not do that for you. You need to store the messages somewhere (or have the client re-send the full history) and then send the full conversation with each Workers AI request.

IIsaac McFadyen That is possible but Workers AI will not do that for you. You need to store the ...

A

Ashkan•10/5/25, 12:11 AM

thanks for reply, this approach may result in exponential

token_input

token_input

token_input

token_input and exponential cost

AAshkan thanks for reply, this approach may result in exponential `token_input` and expo...

I

Isaac McFadyen•10/5/25, 12:13 AM

That is just how LLMs work and how every provider does it, not just Workers AI. OpenAI, Gemini, Claude, etc all need to see the past history in order to act on it. If a message isn't in the context then it will not be seen by the model.

IIsaac McFadyen That is just how LLMs work and how every provider does it, not just Workers AI. ...

A

Ashkan•10/5/25, 12:14 AM

ok, I will try it. thanks for help

AAshkan Hey, how can I have message history such that ai model will have a message histo...

A

Anon•10/5/25, 2:16 AM

Use Durable Obejcts to store the history

A

Anon•10/5/25, 2:17 AM

At least that's what's recommended you could really store them anywhere

C

Comrade Nalaxone•10/5/25, 4:44 PM

For god sake can you all please update the docs to match the portal this drives me nuts every single time:

https://developers.cloudflare.com/workers-ai/get-started/rest-api/#1-get-api-token-and-account-id

Cloudflare Docs

REST API

Use the Cloudflare Workers AI REST API to deploy a large language model (LLM).

C

Comrade Nalaxone•10/5/25, 4:44 PM

Too big of a company for that to happen

L

LordSilver•10/6/25, 9:21 PM

what is the default model being used?

LLordSilver what is the default model being used?

I

Isaac McFadyen•10/6/25, 9:32 PM

There is no default, you pick whatever model on Workers AI you want to use yourself.

IIsaac McFadyen There is no default, you pick whatever model on Workers AI you want to use yours...

L

LordSilver•10/6/25, 9:37 PM

but i didn't pick anything

I

Isaac McFadyen•10/6/25, 9:38 PM

If you're using Workers AI you must have? Are you using another product of some sort?

L

LordSilver•10/6/25, 9:38 PM

ok it uses llama by default

IIsaac McFadyen If you're using Workers AI you must have? Are you using another product of some ...

L

LordSilver•10/6/25, 9:38 PM

i use Workes AI and i don't specify any model

LLordSilver i use Workes AI and i don't specify any model

I

Isaac McFadyen•10/6/25, 9:39 PM

You must be using a product that uses Workers AI and picks the model for you, there are no default models in Workers AI. I saw in #workers-and-pages-discussions that you're using Stagehand, correct? I expect that picks llama-3.3 for you.

L

LordSilver•10/6/25, 9:40 PM

mmm ok

S

sodepr•10/9/25, 6:15 AM

Hi,

Does Cloudflare support legacy endpoints (

/completions

/completions

/completions

/completions,

/chat/completions

/chat/completions

/chat/completions

/chat/completions) for new models (Eg: gpt-oss-20b)?

The document said that:

Workers AI supports OpenAI compatible endpoints for text generation (/v1/chat/completions)

Workers AI supports OpenAI compatible endpoints for text generation (/v1/chat/completions)

Workers AI supports OpenAI compatible endpoints for text generation (/v1/chat/completions)

Workers AI supports OpenAI compatible endpoints for text generation (/v1/chat/completions)

But I cannot use any new model.

A

Ashkan•10/9/25, 9:49 AM

doesn't

runWithTools

runWithTools

runWithTools

runWithTools support

gateway

gateway

gateway

gateway configuration?

Ssodepr Hi, Does Cloudflare support legacy endpoints (`/completions`, `/chat/completion...

K

Kevin•10/9/25, 9:52 AM

Use responses endpoint.

KKevin Use responses endpoint.

S

sodepr•10/9/25, 2:46 PM

Applications hasn't support new endpoint yet.

Ssodepr Applications hasn't support new endpoint yet.

K

Kevin•10/9/25, 2:51 PM

at least ai gateway does support it ai-gateway I have not tried workers ai directly

H

Hew•10/9/25, 7:27 PM

@sodepr The Cloudflare blog said in August that completions support was "coming soon" to the gpt-oss models. I haven't seen any update from them since, though. It would certainly be nice to have because, as you've pointed out, not everything supports the responses endpoint yet.

I’m looking for access to Claude and other models before I build against something like open router.

Similar Threads

Similar Threads

Similar Threads