ToolsThe story, in brief
Show HN: sllm – Split a GPU node with other developers, unlimited tokens
$14k/month. That's what running DeepSeek V3 costs solo. This startup splits the bill among developers for $5/mo.
The KeyNews take
Why it matters
A new service democratizes access to expensive large language models by enabling cost-sharing among developers, potentially disrupting how AI infrastructure is consumed by smaller teams and individual developers.
The key facts
5 to knowDeepSeek V3 requires 8×H100 GPUs at $14k/month
Pricing starts at $5/month for shared access
Most developers only need 15-25 tokens per second
OpenAI-compatible API
Private traffic with no logging
Go to the source
Hacker Newssllm.cloud
Publisher excerpt: Running DeepSeek V3 (685B) requires 8×H100 GPUs which is about $14k/month. Most developers only need 15-25 tok/s. sllm lets you join a cohort of developers sharing a dedicated node. You reserve a spot with your card, and nobody is charged until the cohort fills. Prices start at $5/mo for smaller…