Model Releases
Inference is becoming the largest compute market and energy consumer in AI. Pearl turns inference CapEx of hyperscalers into a profit center…
Inference is becoming the largest compute market and energy consumer in AI. Pearl turns inference CapEx of hyperscalers into a profit center: every LLM token produced by GPUs can simultaneously genera
Inference is becoming the largest compute market and energy consumer in AI. Pearl turns inference CapEx of hyperscalers into a profit center: every LLM token produced by GPUs can simultaneously generate ¶PRL in parallel. That means users get 2-for-1 economics: useful inference today, and Pearl coins that discount future compute. We’re excited to partner with Together AI to launch the first 2-for-1 inference endpoint offering SoTA LLMs at discounted price, and securing the Pearl network in parallel. Introducing Gemma-4-31B-it-Pearl on Together AI, Pearl Research Labs’ instruction-tuned checkpoint of Gemma 4 31B powered by @prlnet Proof of Useful Work protocol. AI natives can now use this Pearl model as a serverless inference endpoint on Together AI, at a 25%+ discounted pric…
Source: Together AI (X) | 2026-05-15