Together AI Enables Custom Post-Training for MiniMax M3.1 Flash

Together AI has added MiniMax M3.1 Flash (256K context) to its Post-Training platform, letting developers fine-tune the model with LoRA via SFT on their own data or train it with custom reward functions and environments using RL.

2026-10-26 ~ 2026-10-27 · 2 related posts

• Together AI adds MiniMax M3.1 Flash post-training with SFT and RL support — togethercompute · 2026-10-26
• MiniMax M3.1 Flash lands on Together AI with LoRA post-training for SFT and RL — MiniMax_AI · 2026-10-27