Glossary

Inference API : OpenAI-compatible API for running generative AI inference (text, vision, image, embeddings) at https://inference.nebulablock.com/v1.

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.