Nebius Token Factory

Training is excluded, but prompts and outputs may be stored by default unless zero-data-retention mode is enabled.

Plan Scope

Nebius Token Factory inference and fine-tuning; speculative decoding is enabled by default unless Zero Data Retention is selected.

Prompt Retention

By default API prompts and outputs may be stored for speculative decoding, with no public maximum period stated in the quick guide. Enabling ZDR prevents post-request storage.

Response Retention

Same default speculative-decoding storage and optional ZDR as prompts.

Ordinary Logging

Account, billing, usage, security, and service metadata is processed under the integrated terms and DPA; ZDR applies to content rather than eliminating all metadata.

Model Training

Nebius states customer data is never used to train AI models. Fine-tuning data is used only for the customer's requested training.

Product Improvement

Stored default content is used for speculative decoding to improve inference speed, not model training; ZDR opts out of that use.

Human Or Operator Access

Content is processed within Nebius infrastructure and may be stored under the default; the public guide does not promise zero operator access.

Subprocessors And Routing

Model hosting can occur in EU, Israel, or US locations shown per endpoint. Fine-tuning artifacts are stored centrally in the EU, and US processing relies on transfer mechanisms such as SCCs.

Deletion Controls

Users can enable ZDR in account settings to prevent storage after processing. Fine-tuning datasets, artifacts, and models follow separate customer resource controls.

Caveat

ZDR is opt-in and may reduce service level. Without it, input and output storage for speculative decoding has no stated maximum retention in the reviewed public guide.