$5 free credits when you sign up Claim now
Wan 2.2 Animate now available Test it!
Video Upscaling models now available Test it!
Z-Anime image model Test it!

About Us

One API. A decentralized GPU network. Run image, video, audio, and text models without managing infrastructure, and at a fraction of traditional cloud cost.

Mission

AI compute should be priced like a utility, not a luxury.

A handful of cloud providers own the GPUs that modern AI runs on — and they set the price. We took a different route: we route inference through a global network of idle consumer GPUs. The result is the same open-source models, running faster, for 10–20× less.

Abstract visualisation of deAPI’s decentralized GPU compute network.

The problem

The bottleneck isn’t models. It’s GPUs.

Open-source models are now competitive with closed ones. Running them isn’t.
GPU capacity is expensive, concentrated in a few hyperscalers, and wrapped in lock-in.
Most teams either overpay or never ship.

Meanwhile, hundreds of thousands of high-end GPUs sit idle in gaming PCs every night.

High-end consumer GPUs sitting idle in gaming PCs.

The solution

One API. A decentralized GPU network.

deAPI aggregates idle consumer GPUs into a single inference layer and exposes it through one consistent API. We handle GPU orchestration, execution, and scaling — you call an endpoint. Built on the GamerHash network (live since 2017), it turns underused gaming hardware into production compute.

Already on the OpenAI SDK? deAPI ships an OpenAI-compatible endpoint at oai.deapi.ai/v1 — change base_url and api_key, keep your code.

deAPI exposes a decentralized GPU network through one consistent API.

Team

Patryk Pusch — CEO at deAPI, the decentralized GPU network for AI inference

Patryk Pusch

CEO

14+ years in tech, 8+ building AI-focused platforms. Previously launched GamerHash — a distributed GPU network — scaling it from crypto mining to AI compute. At deAPI he owns the full product lifecycle, from vision and roadmap to user satisfaction.

in/patryk-pusch
Sławomir Olszyński — CTO at deAPI, the decentralized GPU network for AI inference

Sławomir Olszyński

CTO

20+ years in software engineering and infrastructure. Leads deAPI’s technical strategy. Also CEO at codelabs.rocks (30+ developers) and has led the team behind SocialTalent.com for 13+ years — trusted by IBM, Siemens, Cisco, Nokia across 60 countries.

in/solszynski
Alex Strześniewski — COO at deAPI, the decentralized GPU network for AI inference

Alex Strześniewski

COO

10+ years scaling fintech and distributed infrastructure. Founder & CEO of AngelBlock and former COO of the CoinDeal exchange, with advisory work at GamerHash and Aleph Zero. Based in the SF Bay Area, he runs deAPI’s operations and growth.

in/alexstrzesniewski
Dawid Wenderski — Software Developer at deAPI, the decentralized GPU network for AI inference

Dawid Wenderski

Software Developer

15+ years of experience building applications across multiple platforms. Previously developed the GamerHash Miner desktop client (C#/WPF) and GamerHash mobile app (Dart/Flutter). At deAPI, responsible for the GamerHash AI desktop client (worker) and contributing to the AI Python server for inferences.

Adam Iglewski — Senior Developer at deAPI, the decentralized GPU network for AI inference

Adam Iglewski

Senior Developer

20+ years of software engineering in PHP, JavaScript, C++, Python, Laravel, Vue.js. Previously, architected GamerHash mining system handling thousands miners connected to GamerHash api. At deAPI, core full-stack contributor working across backend, frontend, and infrastructure. Verification and research of new open source models, quantization and parameter tuning.

Patryk Augustyn — Back-end Developer at deAPI, the decentralized GPU network for AI inference

Patryk Augustyn

Back-end Developer

10+ years in software development (PHP, Laravel, Docker, Vue.js). Former CTO of a global CPA affiliate network (850k+ publishers, 154 countries) and backend developer at GamerHash. At deAPI, built the entire client dashboard from scratch in Livewire/Laravel. Focuses on backend infrastructure, security, and performance.

Career in deAPI

Ship AI without the infrastructure bill.

Point your SDK at deAPI and run open-source models on a decentralized GPU network.