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)→
More from Infra
- HBM demand shifts: low-stack inference plans shelved, Rubin to go 12-high only — BenBajarin · 2026-10-26
- CircuitHub unveils The Grid, a factory-scale robot making PCBs in the US twice as fast as Shenzhen — garrytan · 2026-10-26
- Ubicloud publishes "Fixing Tool-Call Accuracy in vLLM" — petrusenko_max · 2026-10-26
- Meta approves nonvoting Class C shares as 2026 capex guidance hits $135B–$145B — thione · 2026-10-26
- Unsloth Ships MiniMax-M3.1-Flash Quants: 2-bit Retains 91.5% Accuracy, Runs in 150GB RAM — danielhanchen · 2026-10-26
- Engineer with thousands of fabricated devices pours cold water on photonic crystal modulator yields — jwt0625 · 2026-10-26