# sllm

11 Hacker News commenters recommended sllm and 15 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months.

**Verdict:** Splits one GPU node among developers for a flat monthly fee, with fixed-speed unlimited tokens. Critics say the unlimited claim is capped by rate limits and the business model does not add up.

## Why people recommend it

- Flat price for unlimited use (2 comments): "I kinda like the idea of paying $5/m for unlimited usage at the specified speed." ([source](https://news.ycombinator.com/item?id=47641259)) "this looks attractive to me for $5/m running unlimited at 20t/s-25t/s" ([source](https://news.ycombinator.com/item?id=47643668))
- Good idea, shared-cost concept (3 comments): "I like the idea, I just wouldn't want my subscription to suddenly be on hold because a peer decided to stop theirs." ([source](https://news.ycombinator.com/item?id=47648009)) "This is an excellent idea, but I worry about fairness during resource contention." ([source](https://news.ycombinator.com/item?id=47641080)) "Also mobile version is a bit broken, but good idea and good luck!" ([source](https://news.ycombinator.com/item?id=47642963))

## What people warn about

- Business model doesn't add up (3 comments): "$40/mo for deepseek r1 seems steep compared to a pro sub on open ai /claude unless you run 24x7" ([source](https://news.ycombinator.com/item?id=47641180)) "It fundamentally doesn't make sense as a business model." ([source](https://news.ycombinator.com/item?id=47642143)) "Isn't this a bad deal? Or is there an error in my math?" ([source](https://news.ycombinator.com/item?id=47643623))
- Rate limits make unlimited claim hollow (2 comments): "Seems like they have a rate limit so it is kinda the same as normal subs" ([source](https://news.ycombinator.com/item?id=47647182)) ""Unlimited tokens" is doing a lot of heavy lifting here." ([source](https://news.ycombinator.com/item?id=47648617))
- Half-baked, rushed launch (2 comments): "a less that half baked (5% baked?) implementation and you wasted goodwill by posting it before it was ready" ([source](https://news.ycombinator.com/item?id=47647420)) "This is a single afternoon vibe-coded project by all indications." ([source](https://news.ycombinator.com/item?id=47669871))
- Capacity too small for many users (2 comments): "The node peaks at ~3,000 tok/s total. So at full capacity they can really only serve" ([source](https://news.ycombinator.com/item?id=47642955)) "cache ejection during contention qill degrade everyones service." ([source](https://news.ycombinator.com/item?id=47643310))

## Alternatives hackers recommend

- [Cerebras Inference](https://hackerapproved.com/p/cerebras.md): 109 recommend
- [Groq API](https://hackerapproved.com/p/groq.md): 58 recommend
- [Tinfoil](https://hackerapproved.com/p/tinfoil.md): 21 recommend
- [Darkbloom](https://hackerapproved.com/p/darkbloom.md): 19 recommend
- [Synthetic](https://hackerapproved.com/p/synthetic.md): 18 recommend

## Where to get it

- [Visit the official site](https://sllm.cloud/)

## Cite as

Hacker Approved, "sllm", https://hackerapproved.com/p/sllm/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).