Decentralized AI: Permissionless LLM Inference on POKT Network
Daniel Olshansky, Ramiro Rodriguez Colmeiro, Bowen Li
TL;DR
The paper proposes Decentralized AI Inference (DecAI) on the POKT Network, leveraging its established DePIN RPC backbone and Relay Mining metering to create a permissionless, verifiable marketplace for LLM inference. It formalizes a four-way stakeholder model (Sources, Suppliers, Gateways, Applications) and outlines data- and service-flow primitives that enable open-source models to be monetized without deploying end-user software, while preserving privacy and censorship resistance relative to centralized providers. By decoupling infrastructure from product layers and integrating with Web3 data/storage, compute, and inference networks, DecAI aims to democratize access to mid-to-low-end inference capabilities, reduce downtime, and foster a broader ecosystem of open-source AI researchers and small-to-mid-sized applications. The work identifies concrete future directions—tokenomics, TEEs, verification, and adversarial safeguards—to mature a robust, scalable, and secure decentralized AI stack capable of competing with centralized inference services.
Abstract
POKT Network's decentralized Remote Procedure Call (RPC) infrastructure, surpassing 740 billion requests since launching on MainNet in 2020, is well-positioned to extend into providing AI inference services with minimal design or implementation modifications. This litepaper illustrates how the network's open-source and permissionless design aligns incentives among model researchers, hardware operators, API providers and users whom we term model Sources, Suppliers, Gateways and Applications respectively. Through its Relay Mining algorithm, POKT creates a transparent marketplace where costs and earnings directly reflect cryptographically verified usage. This decentralized framework offers large model AI researchers a new avenue to disseminate their work and generate revenue without the complexities of maintaining infrastructure or building end-user products. Supply scales naturally with demand, as evidenced in recent years and the protocol's free market dynamics. POKT Gateways facilitate network growth, evolution, adoption, and quality by acting as application-facing load balancers, providing value-added features without managing LLM nodes directly. This vertically decoupled network, battle tested over several years, is set up to accelerate the adoption, operation, innovation and financialization of open-source models. It is the first mature permissionless network whose quality of service competes with centralized entities set up to provide application grade inference.