Yes, you can see the same "hosted" ones on there, but when you look at the models endpoint, there are much less options at the "workers-ai/*" namespace. Is that intentional?
james2doyle [3 hidden]5 mins ago
To better clarify, I don’t see "workers-ai/@cf/google/gemma-4-26b-a4b-it" in the /models enpoint in gateway.ai.cloudflare.com but it does seem to exist as a hosted model. Same with "workers-ai/@cf/nvidia/nemotron-3-120b-a12b" which I would expect to see
samjs [3 hidden]5 mins ago
Hey James.
Thanks for the feedback, and good catch. Looks like that endpoint is pulling from a slightly out of date data source. The docs/dashboard currently are the best resources for the full catalog, but we'll update that API to match.
whereistejas [3 hidden]5 mins ago
This actually looks very useful. Cloudflare seems to be brining together a great set of tools. Not to mention, D2 is literally the only sqlite-as-a-service solution out there whose reliability is great and free tier limits are generous.
rs_rs_rs_rs_rs [3 hidden]5 mins ago
Yeah but the 10GB limit for D1 is crazy, can you really start building on that? Other than toy projects?
eis [3 hidden]5 mins ago
D1 reliability has been bad in our experience. We've had queries hanging on their internal network layer for several seconds, sometimes double digits over extended periods (on the order of weeks). Recently I've seen a few times plain network exceptions - again, these are internal between their worker and the D1 hosts. And many of the hung queries wouldn't even show up under traces in their observability dashboard so unless you have your own timeout detection you wouldn't even know things are not working. It was hard to get someone on their side to take a look and actually acknowledge and understand the problem.
But even without network issues that have plagued it I would hesitate to build anything for production on it because it can't even do transactions and the product manager for D1 openly stated they wont implement them [0]. Your only way to ensure data consistency is to use a Durable Object which comes with its own costs and tradeoffs.
The basic idea of D1 is great. I just don't trust the implementation.
For a hobby project it's a neat product for sure.
mikeocool [3 hidden]5 mins ago
Agreed -- except that all of their docs and marketing pitches it for use cases like "per-user, per-tenant or per-entity databases" -- which would be SO great.
But in practice, it's basically impossible to use that way in conjunctions with workers, since you have to bind every database you want to use to the worker and binding a new database requires redeploying the worker.
BoorishBears [3 hidden]5 mins ago
> For those who don’t use Workers, we’ll be releasing REST API support in the coming weeks, so you can access the full model catalog from any environment.
Cloudflare seems to be building for lock-in and I don't love it. I especially don't understand how you build an OpenRouter and only have bindings for your custom runtime at launch.
switz [3 hidden]5 mins ago
Workers runtime is open source and permissively licensed fwiw
* D1, but agreed. I wish Cloudflare would offer a built-in D1-R2 backups system though! (Can be done with custom code in a worker, but wish it was first-party)
datadrivenangel [3 hidden]5 mins ago
Good to see their purchase of Replicate paying off!
bm-rf [3 hidden]5 mins ago
Not seeing any pricing info on the models[1] page. Wonder how much of a lift this is over paying providers directly. Perhaps Cloudflare is doing this at cost? Also interesting that zero data retention is not on by default, and is not supported with all providers[2]. Finally, would be great if this could return OpenAI AND Anthropic style completions.
We'll be adding prices to the docs and the model catalog in the dashboard shortly.
In short: currently the pricing matches whatever the provider charges. You can buy unified billing credits [1] which charges a small processing fee.
> Finally, would be great if this could return OpenAI AND Anthropic style completions.
Agreed! This will be coming shortly. Currently we'll match the provider themselves, but we plan to make it possible to specify an API format when using LLMs.
Thanks, I don't see pricing for foundation models however, such as GPT-5.4
ashleypeacock [3 hidden]5 mins ago
It’s at-cost pricing I believe, no mark up
ramesh31 [3 hidden]5 mins ago
Big, could be a viable Bedrock alternative. Probably better uptime than Anthropic or AWS, too.
Jack5500 [3 hidden]5 mins ago
Sadly no mention on regions.
pjmlp [3 hidden]5 mins ago
It will work great in Spain! /s
pprotas [3 hidden]5 mins ago
Can't wait for the free tier!
yoavm [3 hidden]5 mins ago
Workers AI had a free tier since it launched, I think? See the pricing page I linked to above.
indigodaddy [3 hidden]5 mins ago
So looks like the AI Platform free tier will have access to the open models only perhaps? And the 10,000 neuron thing? I don't see any mention of frontier models in the url you linked in the other comment ( https://news.ycombinator.com/item?id=47792538#47793142 )
throwpoaster [3 hidden]5 mins ago
Anthropic gonna acquire Cloudflare for stock. Solves their infrastructure problems in one shot.
kylehotchkiss [3 hidden]5 mins ago
No way! Cloudflare will buy anthropic when the economy begins self-correcting. Looking forward to Workers AI getting all those H100s to run more Qwens
neya [3 hidden]5 mins ago
I'm not ready to for another rug pull, so please no :( I really enjoy Cloudflare's CDN.
6thbit [3 hidden]5 mins ago
don’t attach to a single AI provider when you can attach to cloudflare as your single AI gateway provider!
rant aside, they are greatly positioned network wise to offer this service, i wonder about their princing and potential markup on top of token usage?
i presume they wont let you “manage all your AI spend in one place” for free.
koolba [3 hidden]5 mins ago
> i presume they wont let you “manage all your AI spend in one place” for free.
Of course they will. In return they get to control who they’re routing requests to. I wouldn’t be surprised if this turns I to the LLM equivalent of “paying for order flow”.
6thbit [3 hidden]5 mins ago
i got shivers thinking about a future ai dynamic pricing and automatic gateway choosing the cheapest provider available
nhecker [3 hidden]5 mins ago
Openrouter already does this, unless I've misunderstood the premise.
nubg [3 hidden]5 mins ago
shivers? as in it frightens you? i believe there is no way around tokens being prices like gasoline at the gas station - it changes every hour. Any other system means you are either over- or underspending.
ernsheong [3 hidden]5 mins ago
What is Cloudflare trying to be? Everything everywhere all at once?
charcircuit [3 hidden]5 mins ago
They want to be an edge networking platform. Anything that would be useful doing on an edge node close to the end user is in scope.
PUSH_AX [3 hidden]5 mins ago
A CSP.
wahnfrieden [3 hidden]5 mins ago
No spending limit / no ability to set a budget, unlike Google or OpenAI. Be prepared for an eye-watering invoice if you have a bug or get hacked.
edit: Why downvote? It's correct, and it's a risk that competitors handle better, including for their CDN products (compared to Bunny CDN). Maybe you are just used to the risk and haven't felt the burn yourself yet. Or you have the mistaken notion that there is no price at which temporary downtime is worthwhile to avoid paying.
james2doyle [3 hidden]5 mins ago
I just added some credits to my account. You can set a daily $ spend limit as well as add credits without auto-refill
mbtrucks [3 hidden]5 mins ago
Can I set a hard cost limit ? Else I'm not interested, don't be like googles mess of billing.
james2doyle [3 hidden]5 mins ago
Seems like it. I just added some credits to my account. You can set a daily $ spend limit as well as add credits without auto-refill
mbtrucks [3 hidden]5 mins ago
Can I set a hard cost limit per day ? With no drift, else I'm not interested.
tln [3 hidden]5 mins ago
I think you should look at OpenRouter. It has budget controls
stult [3 hidden]5 mins ago
A few weeks ago, I ran into a bug with Cloudflare's DNS server not detecting when I updated the records with the registrar. The bug was 100% on their end, entirely unsolvable by me, yet they have made it literally impossible to contact them to file a bug report. Their standard user help workflow dead-ended by forcing me to talk to their absolutely useless AI help chatbot, which proceeded to regurgitate their FAQ (inaccurately, uselessly), then referred me to a phone number that was disconnected/not in service, then gave me an email address that auto-replied it was no longer in use, then just looped back to the FAQ. There was no way for me to even send them an email to let them know they have a major bug.
I immediately pulled all my sites off of Cloudflare and I will never use that godawful nightmare of a company for anything ever again. If they can't even host a generic help bot without screwing it up that badly, why would I ever use them for anything at all, never mind an AI platform?
allthetime [3 hidden]5 mins ago
What was the bug? I configure DNS for both public and private networks on cloudflare semi-frequently and always see changes in minutes or less.
Yes, you can see the same "hosted" ones on there, but when you look at the models endpoint, there are much less options at the "workers-ai/*" namespace. Is that intentional?
Thanks for the feedback, and good catch. Looks like that endpoint is pulling from a slightly out of date data source. The docs/dashboard currently are the best resources for the full catalog, but we'll update that API to match.
But even without network issues that have plagued it I would hesitate to build anything for production on it because it can't even do transactions and the product manager for D1 openly stated they wont implement them [0]. Your only way to ensure data consistency is to use a Durable Object which comes with its own costs and tradeoffs.
https://github.com/cloudflare/workers-sdk/issues/2733#issuec...
The basic idea of D1 is great. I just don't trust the implementation.
For a hobby project it's a neat product for sure.
But in practice, it's basically impossible to use that way in conjunctions with workers, since you have to bind every database you want to use to the worker and binding a new database requires redeploying the worker.
Cloudflare seems to be building for lock-in and I don't love it. I especially don't understand how you build an OpenRouter and only have bindings for your custom runtime at launch.
https://github.com/cloudflare/workerd
[1] https://developers.cloudflare.com/ai/models/
[2] https://developers.cloudflare.com/ai-gateway/features/unifie...
We'll be adding prices to the docs and the model catalog in the dashboard shortly.
In short: currently the pricing matches whatever the provider charges. You can buy unified billing credits [1] which charges a small processing fee.
> Finally, would be great if this could return OpenAI AND Anthropic style completions.
Agreed! This will be coming shortly. Currently we'll match the provider themselves, but we plan to make it possible to specify an API format when using LLMs.
[1]: https://developers.cloudflare.com/ai-gateway/features/unifie...
rant aside, they are greatly positioned network wise to offer this service, i wonder about their princing and potential markup on top of token usage?
i presume they wont let you “manage all your AI spend in one place” for free.
Of course they will. In return they get to control who they’re routing requests to. I wouldn’t be surprised if this turns I to the LLM equivalent of “paying for order flow”.
edit: Why downvote? It's correct, and it's a risk that competitors handle better, including for their CDN products (compared to Bunny CDN). Maybe you are just used to the risk and haven't felt the burn yourself yet. Or you have the mistaken notion that there is no price at which temporary downtime is worthwhile to avoid paying.
I immediately pulled all my sites off of Cloudflare and I will never use that godawful nightmare of a company for anything ever again. If they can't even host a generic help bot without screwing it up that badly, why would I ever use them for anything at all, never mind an AI platform?