About
sllm provides access to a range of large language models at the cheapest possible price, in the most configurably relevant way, all securely and privately hosted on dedicated GPU infrastructure. No markup beyond cost. No tracking. Just the models you need.
How it works
sllm organizes access around cohorts — small groups that share a subscription to a specific model. You join a cohort, get an API key, and split the cost with other members. Each cohort has a fixed number of slots and a commitment period. When a cohort fills up, a new one opens.
Privacy & security
All infrastructure runs on dedicated GPU providers. Prompts and responses are never logged. Traffic is routed through an isolated proxy layer with strict data separation between users. Your usage data stays yours.
FAQ
- What models are available?
- The home page lists every model with an open cohort. Available models change as new subscriptions are added.
- How does billing work?
- You pay upfront for the full commitment period when you join a cohort. The price shown is your monthly share of the subscription cost.
- Is my data private?
- Yes. Prompts and responses are never logged, and each user's traffic is isolated.
- What happens when a cohort fills up?
- A new cohort for the same model opens automatically. You can join any open cohort from the home page.