MiniMax M3.1 Flash lands on Together AI with 1M context and low pricing

MiniMax M3.1 Flash is available through the Together AI API at $0.15 input and $0.60 output per million tokens, with 1M context and adjustable reasoning effort. Engineers can test a low-cost agentic coding and computer-use model today.

• mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
• speculative decoding — A speed trick where a small model drafts several tokens ahead and the big model verifies them in one pass, often doubling generation speed.

• postTogether Post-Training opens flexible RL and SFT on open models
• articleReflection's Beam open-weight model launches on Together AI
• postTogether Link routes your coding harness to open models by task

• postMiniMax M3.1 Flash: cheaper, faster agentic coding model, weights Oct 23MiniMax (official)
• postMiniMax opens M3.1 Flash weights for coding and agentsMiniMax (official)
• articleMiniMax M3.1 Flash now available on AI Gateway for freeZachary Chen

Checking sign-in…

Loading comments…