Introduction

ZeroGPU is the compute efficiency layer for AI inference. It runs repeatable, high-volume AI tasks on specialized small and nano language models across an edge-powered network - so the same workloads run faster and cheaper than on centralized GPUs. Send a request to one OpenAI-compatible endpoint; ZeroGPU picks the right small or nano model and runs it on the right compute. Frontier models for reasoning. ZeroGPU for repeatable execution - classification, extraction, moderation, summarization, routing - at the scale AI demands.

Make your first call

Find your API key in the ZeroGPU dashboard.

The x-project-id header is optional. Send it only to scope a request to a specific project.

curl --location 'https://api.zerogpu.ai/v1/responses' \
  --header 'content-type: application/json' \
  --header 'x-api-key: YOUR_API_KEY' \
  --data '{
  "input": "Technology has quietly reshaped the rhythm of everyday life, weaving itself into routines so seamlessly that it often goes unnoticed. From the moment a smartphone alarm wakes someone in the morning to the final glance at a glowing screen before sleep, digital systems guide communication, navigation, work, and entertainment. This transformation did not happen overnight. It emerged through decades of incremental innovation, each new tool building upon the last, until the modern world became deeply interconnected.One of the most significant changes has been the speed at which information travels.",
  "model": "zlm-v1-iab-classify-edge"
}'

Already using the OpenAI SDK? Point it at ZeroGPU:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.zerogpu.ai/v1",
    api_key="unused",  # ZeroGPU authenticates via the header below
    default_headers={
        "x-api-key": "YOUR_API_KEY",
    },
)

resp = client.responses.create(
    model="zlm-v1-iab-classify-edge",
    input="Technology has quietly reshaped the rhythm of everyday life, weaving itself into routines so seamlessly that it often goes unnoticed. From the moment a smartphone alarm wakes someone in the morning to the final glance at a glowing screen before sleep, digital systems guide communication, navigation, work, and entertainment. This transformation did not happen overnight. It emerged through decades of incremental innovation, each new tool building upon the last, until the modern world became deeply interconnected.One of the most significant changes has been the speed at which information travels.",
)

🎉 Either call returns the same classification result:

{
  "audience": [
    { "name": "Technology & Computing", "score": 0.8194953318627214 },
    { "name": "Consumer Electronics", "score": 0.7730970665427267 },
    { "name": "IT and Internet Support", "score": 0.6476231908025892 }
  ],
  "content": {
    "iab_1_0": [
      { "name": "Technology & Computing", "score": 0.8130967783784443 },
      { "name": "Automotive", "score": 0.6588144281246334 }
    ],
    "iab_2_2": [
      { "name": "Technology & Computing", "score": 0.8130967783784443 },
      { "name": "Wearable Technology", "score": 0.7080836335415118 },
      { "name": "Auto Infotainment Technologies", "score": 0.6588144281246334 }
    ]
  }
}

What you can run

Text classification

Text generation

Open Weight

What you get

Lower cost and latency

Specialized small and nano models on distributed compute. ~10x faster and 50%+ cheaper on production tasks.

One OpenAI-compatible API

POST /v1/responses; integrate with minimal code changes.

Built for production

Token usage, latency, and volume per request, with project isolation for dev, staging, and production.

How it works

Create a project

One organization, multiple projects. Each gets its own API key and dashboard.

Send requests

POST to /v1/responses with your key and model. Response comes back as structured JSON.

Monitor everything

Token usage, request volume, latency, error rates: all visible in the dashboard. Debug individual requests in Logs.

Workload analysis → Model selection → Edge orchestration. ZeroGPU classifies each task, picks the fastest viable model, and routes it to the right compute. See How ZeroGPU works for the full picture.

Go deeper

Quickstart

How ZeroGPU works

Model Catalog

API Reference

Be an Edge Provider

Contribute compute from your idle devices to the ZeroGPU edge network and help power distributed AI inference.

Get Started

Models

Guides

Edge Providers

Make your first call

What you can run

Text classification

Text generation

Open Weight

What you get

Lower cost and latency

One OpenAI-compatible API

Built for production

How it works

Go deeper

Quickstart

How ZeroGPU works

Model Catalog

API Reference

Be an Edge Provider

​Make your first call

​What you can run

Text classification

Text generation

Open Weight

​What you get

Lower cost and latency

One OpenAI-compatible API

Built for production

​How it works

​Go deeper

Quickstart

How ZeroGPU works

Model Catalog

API Reference

Be an Edge Provider

Make your first call

What you can run

What you get

How it works

Go deeper