We're among the first platforms in the world to offer M3 access. It's rolling out in phases - join the waitlist to get it first.
When you hand a task to Kimchi Coding, the orchestrator classifies and delegates. Planning phases go to the planner. File reads go to the explorer. But the actual work - arguably the most important part - goes to the builder.
It's where most of the tokens are spent and where model quality has the most impact. M3 replaces MiniMax M2.7 as the default builder, and it outperforms the previous model by a meaningful margin.
Benchmarked on real GitHub issues - ahead of GPT-5.5 and Gemini 3.1 Pro on the same test.
MiniMax Sparse Attention (MSA) makes long context fast - 1/20th the per-token compute of M2.7 at 1M length.
Builder subagents finish each /ferment step dramatically faster, and the gains compound across parallel agents.
Kimchi's orchestrator sends the heaviest work - writing the actual code - to the builder. M3 replaces M2.7 there.
M3 is rolling out in phases via the waitlist. Drop your email and we'll let you know the moment it goes live.