LaunchDevelopersOctober 19, 2026

Together launches Post-Training for custom SFT and RL models

Read original source →together.ai

Together Post-Training lets developers post-train open models like Qwen, GLM and Kimi with SFT or RL while keeping the training loop in their own Python code. B200 capacity is $9/GPU-hour for the first eight weeks, down from $11.

How this story unfolded

11 days · 1 report · 8 community posts · from Oct 19

  1. Oct 19
  2. Oct 20
  3. Oct 22
  4. Oct 26
  5. Oct 28
  6. Oct 30

More stories today

Open the live feed