sllm
Ranked 7 of 12 LLM inference APIs by recommenders
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.
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.
26 people gave an opinion
- recommend it
- 11
- criticize it
- 15
- approval share
- 42%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 11 people recommend itNeeds 10 or more, met.
- 0.7 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Flat price for unlimited use
“I kinda like the idea of paying $5/m for unlimited usage at the specified speed.”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “this looks attractive to me for $5/m running unlimited at 20t/s-25t/s”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” Good idea, shared-cost concept
“I like the idea, I just wouldn't want my subscription to suddenly be on hold because a peer decided to stop theirs.”
Comment from 5 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “This is an excellent idea, but I worry about fairness during resource contention.”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “Also mobile version is a bit broken, but good idea and good luck!”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens”
What people warn about
Each mark is one comment
Business model doesn't add up
“$40/mo for deepseek r1 seems steep compared to a pro sub on open ai /claude unless you run 24x7”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “It fundamentally doesn't make sense as a business model.”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “Isn't this a bad deal? Or is there an error in my math?”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” Rate limits make unlimited claim hollow
“Seems like they have a rate limit so it is kinda the same as normal subs”
Comment from 5 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “"Unlimited tokens" is doing a lot of heavy lifting here.”
Comment from 5 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” Half-baked, rushed launch
“a less that half baked (5% baked?) implementation and you wasted goodwill by posting it before it was ready”
Comment from 5 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “This is a single afternoon vibe-coded project by all indications.”
Comment from 7 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” Capacity too small for many users
“The node peaks at ~3,000 tok/s total. So at full capacity they can really only serve”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens” “cache ejection during contention qill degrade everyones service.”
Comment from 4 Apr 2026 in “Show HN: sllm – Split a GPU node with other developers, unlimited tokens”
Other LLM inference APIs people recommend
The four most recommended other LLM inference APIs, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Cerebras Inference | 109 | 51 | 68% | 13 | — | Approved |
| Groq API | 58 | 23 | 72% | 12 | — | Approved |
| Tinfoil | 21 | 10 | 68% | 10 | — | Approved |
| Darkbloom | 19 | 39 | 33% | 1 | — | — |
| sllmThis page | 11 | 15 | 42% | 1 | — | — |
What people said
28 of the 32 comments that mention it, newest first. Each links to the original comment.
“The site was showing that 4 out of 6 had a sign up of 464 out of 465, so numbers were deceiving.”
“support@sllm.cloud is bouncing.”
“this was a scam just to get email addresses”
“Apparently, the earlier pricing was better for us as customers”
“If you want predictable cost and guaranteed throughput on one model, that's us.”
“This is a single afternoon vibe-coded project by all indications.”
“Being capped to the rate would make your openclaw run slowly, but still be able to work 24x7.”
“"Unlimited tokens" is doing a lot of heavy lifting here.”
“I like the idea, I just wouldn't want my subscription to suddenly be on hold because a peer decided to stop theirs.”
“a less that half baked (5% baked?) implementation and you wasted goodwill by posting it before it was ready”
“otherwise it looks like a less flexible API compared to what chutes.ai or openrouter.ai providing”
“Seems like they have a rate limit so it is kinda the same as normal subs”
“this looks attractive to me for $5/m running unlimited at 20t/s-25t/s”
“Isn't this a bad deal? Or is there an error in my math?”
“The absolute lack of any kind of legal information makes this website criminal.”
“it works like a Kickstarter/group coupon model and creates a guaranteed win-win for the users”
“cache ejection during contention qill degrade everyones service.”
“Also mobile version is a bit broken, but good idea and good luck!”
“The node peaks at ~3,000 tok/s total. So at full capacity they can really only serve”
“It fundamentally doesn't make sense as a business model.”
“But in practise it means sitting and staring for minutes at nothing happening with a "thinking" until something finally happens.”
“I kinda like the idea of paying $5/m for unlimited usage at the specified speed.”
“This is the most "Prompted ourselves a Shadcn UI" page I've seen in a while lol”
“$40/mo for deepseek r1 seems steep compared to a pro sub on open ai /claude unless you run 24x7”
“This is an excellent idea, but I worry about fairness during resource contention.”
“25 t/s is barely usable. Maybe for a background runner”
“Is this not a more restricted version of OpenRouter?”
“It seems crazy to me that the "Join" button does not have a price on it”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.