# ZeroGPU

## Docs

- [Responses](https://docs.zerogpu.ai/api-reference/endpoint/responses.md): Send input to an AI model and receive a response.
- [API Reference](https://docs.zerogpu.ai/api-reference/introduction.md): ZeroGPU Responses API documentation.
- [Distributed Inference](https://docs.zerogpu.ai/concepts/distributed-inference.md): Run AI on idle devices at the edge instead of GPU data centers.
- [Geo-Aware Routing](https://docs.zerogpu.ai/concepts/geo-aware-routing.md): Every request goes to the nearest capable device. Fallback to cloud if needed.
- [Nano Language Models](https://docs.zerogpu.ai/concepts/nano-language-models.md): Sub-1B parameter models that run on CPUs and cost a fraction of LLMs.
- [Batch requests](https://docs.zerogpu.ai/cookbook/batch-requests.md): Send multiple API requests efficiently with parallelism and error handling.
- [Runnable demos](https://docs.zerogpu.ai/cookbook/demos.md): Clone and run full apps that use the ZeroGPU API.
- [IAB content classification](https://docs.zerogpu.ai/cookbook/iab-classification.md): Classify content into IAB categories with the classification model.
- [Cookbook](https://docs.zerogpu.ai/cookbook/index.md): Ready-to-use recipes for common ZeroGPU API tasks.
- [Summarize text](https://docs.zerogpu.ai/cookbook/summarize-text.md): Use the summarization model to shorten long content.
- [FAQ](https://docs.zerogpu.ai/faq.md): Quick answers to common questions.
- [Introduction](https://docs.zerogpu.ai/index.md): Run AI model inference through an API — without managing GPU infrastructure.
- [API Keys](https://docs.zerogpu.ai/platform/api-keys.md): Create, rotate, revoke. Keys are shown once — copy immediately.
- [Authentication](https://docs.zerogpu.ai/platform/authentication.md): Two headers on every request. That's it.
- [Billing](https://docs.zerogpu.ai/platform/billing.md): Pay as you go, credit balance, auto recharge, and billing history.
- [Dashboard](https://docs.zerogpu.ai/platform/dashboard.md): Your API key, project ID, and a ready-to-copy code snippet — all in one place.
- [Logs](https://docs.zerogpu.ai/platform/logs.md): Every API request, searchable: model, status, latency, timestamp.
- [Organizations & Projects](https://docs.zerogpu.ai/platform/organizations-and-projects.md): Separate dev from production. Give each team its own keys and logs.
- [Security](https://docs.zerogpu.ai/platform/security.md): Five rules for keeping your API credentials safe.
- [Usage Analytics](https://docs.zerogpu.ai/platform/usage-analytics.md): See exactly how your API is being used: tokens, latency, volume.
- [Quickstart](https://docs.zerogpu.ai/quickstart.md): First API call in under 5 minutes.
- [Connect AI tools](https://docs.zerogpu.ai/resources/ai-and-mcp.md): Connect Claude Code or Cursor to ZeroGPU docs via MCP for live, queryable access to documentation.
- [Go](https://docs.zerogpu.ai/sdks/go.md): Integrate ZeroGPU into your Go application.
- [JavaScript](https://docs.zerogpu.ai/sdks/javascript.md): Integrate ZeroGPU into your JavaScript or Node.js application.
- [Python](https://docs.zerogpu.ai/sdks/python.md): Integrate ZeroGPU into your Python application.
- [Ruby](https://docs.zerogpu.ai/sdks/ruby.md): Integrate ZeroGPU into your Ruby application.
- [Rust](https://docs.zerogpu.ai/sdks/rust.md): Integrate ZeroGPU into your Rust application.

## Optional

- [Website](https://zerogpu.ai)
- [GitHub](https://github.com/zerogpu)
- [Join Waitlist](https://zerogpu.ai)
- [llms.txt](https://zerogpu.mintlify.app/llms.txt)
- [llms-full.txt](https://zerogpu.mintlify.app/llms-full.txt)


Built with [Mintlify](https://mintlify.com).