Nebius Adds DeepSeek V4 Flash Supervised Fine-Tuning

Arindam_1729 · x · 2026-07-20

Nebius Token Factory says DeepSeek V4 Flash is now available for supervised fine-tuning on its platform.

Users can bring their own training data, run full-parameter SFT in a managed post-training workflow, and read data directly from existing object storage without migrating it. The pitch is essentially: more model choice, less infrastructure to maintain.

The screenshot shows a fine-tuning UI with DeepSeek-V4-Flash selected, supervised fine-tuning enabled, and pricing displayed at $5.00 per 1M tokens with an 8,192 context length.

Related event: Nebius Launches Managed SFT for DeepSeek V4 Flash(3 posts)→

Original post →

More from Infra

Infra channel →