November 3, 2026 · Together AIDeprecation

MiniMax-M3 deprecated for new post-training resources, use MiniMax-M3.1-Flash

Together AI platform
MiniMax-M3
MiniMax-M3.1-Flash
AI and machine learning

MiniMaxAI/MiniMax-M3 is no longer available for new post-training model resources. Use MiniMaxAI/MiniMax-M3.1-Flash instead. Existing MiniMax M3 model resources keep running, and their checkpoints stay available for download. See Supported models.

Read the Together AI changelog

Oct 23, 2026
MiniMax-M3.1-Flash available for LoRA post-training with 262,144 context
Oct 22, 2026
MiniMax-M3.1-Flash on serverless with 1,048,576-token context window
Nov 3, 2026
MiniMax M3.1 Flash adapters can be deployed on dedicated model inference
Sep 14, 2026
MiniMax-H3 available on serverless at $0.1391/sec at 2k

All Together AI platform changes

Related updates