# Glossary **Inference API**\ OpenAI-compatible API for running generative AI inference (text, vision, image, embeddings) at . **GPU Instances**\ Virtual machines equipped with GPUs for compute-intensive tasks such as machine learning and AI workloads. **Object Storage**\ A scalable storage solution for storing and retrieving large amounts of unstructured data, such as datasets and model outputs. **SSH Keys**\ Cryptographic keys used to securely access and manage instances via SSH (Secure Shell). **API Key**\ A unique identifier used to authenticate requests to the API, ensuring secure access to resources. **Tier**\ Different levels of service or pricing plans available to users, often based on resource limits or features. **Referral**\ A program that rewards users for inviting others to use the platform. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.nebulablock.com/glossary.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.