ZeroGPU
ZeroGPU builds distributed inference infrastructure that orchestrates specialized nano models across a fleet of edge devices to reduce AI costs.
At a Glance
- AI startups
- Enterprise developers
- Compliance and security teams
AI Tools by ZeroGPU
(1)
ZeroGPU
Edge AI Inference API Platform
Discussions
No discussions yet
Be the first to start a discussion about ZeroGPU
Latest News
Products & Services
A distributed network for AI inference that routes tasks to device-optimized small language models.
An API layer that allows developers to drop ZeroGPU into their existing AI stacks with minimal changes.
Market Position
Differentiates from centralized providers like OpenAI by offering a decentralized, edge-powered compute layer specifically for specialized tasks at significantly lower costs.
Leadership
Founders
Maddy Arvapally
Founder and CEO at ZeroGPU. Previously Lead Blockchain Engineer at Replay (2022-2024), Software Architect at B20 Labs, and Senior Backend Engineer at GoPro (2016-2020). Also worked at Walmart eCommerce and Knightscope.
Nishitha Tanukunuri
Co-founder. Previously Software Engineer at AI20 Labs. Expert in AI architecture, system design, and full-stack development.
Executive Team
Maddy Arvapally
Founder and CEO
Veteran software engineer with over a decade of experience in backend and data engineering at major tech firms.
Nishitha Tanukunuri
Co-founder
System architect focused on building distributed AI infrastructure.
Founding Story
ZeroGPU was founded to combat the high cost and latency of using frontier-scale LLMs for routine, structured tasks that can be handled by smaller, more efficient models.
Business Model
Revenue Model
The company generates revenue through usage-based API fees for AI inference calls routed through its distributed network.
Pricing Tiers
Cost is calculated based on tokens used. Example: $0.02 per 1M input tokens for specialized SLMs.
Target Markets
- AI startups
- Enterprise developers
- Compliance and security teams
- Document intelligence
- Adtech intent classification
- PII redaction
- Security alert triage
- Agent tool planning
- Various AI agents and document processing startups