FilterHN

LLMCap – A proxy that hard-stops LLM API calls when you hit a dollar cap

19 points

6 hours ago

| 13 comments

| HN

1 hour ago

[-]

I actually laughed, its a security issue, and it requires payment to avoid payment.

2 hours ago

[-]

Proxying == Logging suspicions

guard-sdk does the same locally https://guard-sdk.js.org

34 minutes ago

[-]

I wonder much time did the author actually spent vibe coding this. I bet 90% of the time were spent on subscription payment processing.

4 hours ago

[-]

Its basic function is something you could vibe code in a few minutes :-)

Not to mention the whole privacy issue.

1 hour ago

[-]

I think the fundamental problem with this project is that if I'm on a hard budget, I have a hard time justifying $19–49/month to keep to my budget.

37 minutes ago

[-]

This will fail product-market fit instantly. Nobody is paying $49/mo for a tiny script they can vibe and run locally.

4 hours ago

[-]

The pricing is very steep. I can see a market for this as an application with one time purchase but as a subscription?

3 hours ago

[-]

We self-host LiteLLM which allows to set the budget per day/week, and it's free.

30 minutes ago

[-]

bifrost

1 hour ago

[-]

Openrouter offers per API-key spending limits.

1 hour ago

[-]

Came here to say this. And you get access to lots of models!

1 hour ago

[-]

Here's a tool to install and manage these limit keys. Even has a GUI.

$ uvx capit serve

https://github.com/day50-dev/limit-model-spending

* Free to use

* Everything is stored local.

* Anthropic skills are included for easily extending it to additional tools or providers.

Please ask for features or file bugs. Thanks!

Btw, I'm terrible at marketing even when I'm giving stuff away.

1 hour ago

[-]

Is this a joke project?

1 hour ago

[-]

> The Service is provided "as is." We are not liable for downtime, data loss, or errors in token counting or cost calculation.

lmao

2 hours ago

[-]

LiteLLM already provides this feature, no need of another proxy

13 minutes ago

[-]

i did try litellm hosted locally for privacy.

it was so bugged, the mcp page broke its postgres, many openai compatible type generic providers but not knowing what works. discovered logging was truncated by default, too late. my fault for that last one.

moved off it after the trivy incident.