Standard
The chat runs on Standard.
A GPU node in our network answers, and the same work also mines PRL. Our pool briefly checks a small slice of intermediate model values in memory, then discards them.
Mining and your dataAsk anything. We keep nothing.
A chat on open models. Your prompts and answers are never stored and never used for training.
Free to try: 50,000 tokens a day after you sign in.
The first request after a quiet period can take a few minutes.
- Summarise this lease in three lines.
- Two-year term, starting 1 March.Renews each year unless cancelled.Either side can leave on 60 days’ notice.
Privacy
What private means here.
-
No prompt logs
We do not log or store prompt or completion content.
-
No training
No training on prompts or completions, ever.
-
History stays in your browser
Saved only if you turn saving on, and encrypted. We do not receive a copy of your history.
-
Only request metadata
Such as time, model, token counts and status, for billing and reliability.
Tiers
Where your request runs.
Two tiers, both zero retention. They differ in mining and in which GPUs answer.
Private
Never mined. Vetted nodes only.
Ours, or those of operators we have approved.
Talk to us about PrivateModels
Open models in the chat.
-
1 dot = 1B parameters
Llama 3.1 8B Instruct
Meta · 8B parameters
Quick answers, summaries and rewrites.
- Context
- 32K tokens
- Longest answer
- 8K tokens
- Licence
- Llama 3.1 Community License
-
Need another model? Ask us.
Tell us which open model you need, and for what.
Ask for a model
Teams
Private deployment for teams.
Dedicated GPUs, your own routing rules, no mining on your traffic. Talk to us.