For GPU clouds
Serve AI as you do today. The same computation also earns network rewards through our pool.
Two ways to work with us
Serve your own traffic on Pearl's mining-enabled vLLM serving engine, and the same computation earns PRL through our pool. No rerouting, no reselling. One integration, 1% pool fee. We set it up with you.
Your traffic · PRL through our pool
Also take inference jobs from our API on idle capacity and earn USD per token on top.
Our traffic · USD per token + PRL
Start with one GPU from the miner portal today (pool only or with our demand), or talk to us and we set it up with you.
vLLM with Pearl's miner and our node software, on your GPU host.
It connects out to our network; no open ports, no inbound access.
You choose which GPUs join and when they leave.
Measured on NVIDIA H100 SXM; H200 runs the same software. Running other GPUs? Tell us about your fleet.
Pick a GPU and a load. Ranges come from our measured H100 SXM runs and today's Pearl network difficulty.
8 × H100 SXM (80 GB)
Tokens served
4.58B–14.9Btokens / day
137B–448B tokens per 30 days
USD from our API jobs (at the partner rate)
60.4–181USD / day
1,811–5,428 USD per 30 days
Depends on demand we route to you. Payouts begin at launch.
PRL from the same work
9.38–32.4PRL / day
281–973 PRL per 30 days
Estimate. Your results depend on load and network difficulty.
Throughput and mining rates are measured on an H100 SXM under three request shapes, three runs each, warm-up discarded. With mining on, a Pearl GPU serves about three quarters (73–78%) of the tokens per second of a standard vLLM server on the same card. H100 NVL and H200 figures are scaled from the H100 SXM measurement. Under steady traffic it mines about half as fast as when it runs warm-up batches alone. PRL is the expected value at today's network difficulty and block reward; rewards arrive per block, so a single day can be higher or lower. Full method: docs.
Earned on jobs from our API, in USD or stablecoins.
The pool splits each block's reward by the work each GPU submitted; 1% pool fee.
You set the payout address, for example your Pearl Safe Vault.
Payouts begin at launch. Schedules and minimums are in your partner agreement.
With Pearl's own verification code before it counts.
Known prompts check that a GPU runs the model it claims.
A new GPU takes our customers' requests only after we approve it.
Our node software never logs or stores prompts or answers. The pool briefly checks a small slice of intermediate model values from mined requests in memory, then discards them.
Compute privacy policyToday
AI GPUs earn only from customers.
With Pearl Safe
The same work also earns PRL.
Tell us about your fleet. We reply within one business day.