Together AI launches serverless inference endpoint for Gemma-4-31B-it-Pearl
Together AI launched a serverless inference endpoint for the Gemma-4-31B-it-Pearl model through a partnership with Pearl Research Labs. The endpoint runs at together.ai/models/gemma-4-31b-it-pearl on the Pearl Network’s Proof of Useful Work protocol and provides discounts exceeding 25 percent funded by cryptocurrency emissions. The 31B-parameter dense multimodal model supports 256K context length, configurable reasoning modes, native function calling, OCR parsing, and more than 140 languages.
#735Dan Fu@REALDANFUThis is pretty cool - LLM inference that generates @prlnet coins during the forward pass, so you can subsidize inference cost. Excited to see how this changes inference tokenomics!
Omri Weinstein@WeinsteinOmriA milestone for Pearl Research Labs: our first major enterprise partnership is live with Together AI. @togethercompute’s inference platform is an ideal demonstration of @prlnet's value proposition — One of the world’s most advanced hyperscalers running AI workloads on Pearl’s 2-for-1 Cuda kernels, turning inference into ¶PRL coins, and reducing consumer LLM price per token. Excited for what we’ll build together.
#1027Simran Arora@SIMRAN_S_ARORA
Together AI@togethercomputeIntroducing 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 pricing.
Blog: https://www.together.ai/blog/together-ai-partners-with-pearl-research-labs
Model endpoints: https://www.together.ai/models/gemma-4-31b-it-pearl#
Simran Arora@simran_s_aroraAI compute and inference are increasingly $$$. How can we change the unit economics of AI to improve accessibility? It's been fun working with @prlnet to release the first model endpoint that simultaneously generates tokens **and** a digital asset that can subsidize inference! 🪙 Check it out, links below 🚀
#1581Vipul Ved Prakash@VIPULVEDThe first inference endpoint with @prlnet support, discounted by 25%, is live!
The endpoint generates @prlnet emissions to offset cost, and we’ll be discounting it further (and launching more endpoints) as Pearl spot prices change.
Together AI@togethercomputeIntroducing 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 pricing.