Nebius Batch Inference — Synthetic Data Generation

Run large-scale async LLM jobs at 50% cost, no rate-limit impact. Ideal for generating synthetic training datasets, annotation, evaluation sets, or any offline bulk inference.

Prerequisites

pip install openai
export NEBIUS_API_KEY="your-key"

API base: https://api.tokenfactory.nebius.com/v1/

Limits & pricing