Skip to content

MiniMax M2.1

MiniMax M2.1 is MiniMax's second-generation model, focused on coding accuracy, tool use, instruction following, and long-horizon planning. It supports a context window of 204.8K tokens and a max output of 131.1K tokens per request.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'minimax/minimax-m2.1',
  prompt: 'Why is the sky blue?'
})
OverviewPlaygroundAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

Frequently Asked Questions

  • What specific programming tasks improved from M2 to MiniMax M2.1?

    Refactoring accuracy, feature scaffolding structure, bug-fix precision, and automated code-review adherence all improved. The gains show most on multi-file tasks that require sustained instruction fidelity.

  • Does MiniMax M2.1 support Interleaved Thinking?

    Yes. The 2.1 generation introduced this capability, letting the model alternate between reasoning and action during complex instruction sequences.

  • How does MiniMax M2.1 handle a five-step tool-call chain?

    MiniMax M2.1 executes steps sequentially without reordering or omission. M2 occasionally dropped or shuffled later steps in long chains.

  • What is the migration path from M2?

    Swap the model identifier to minimax/minimax-m2.1 in your API calls. The request and response formats are unchanged.

  • Is MiniMax M2.1 appropriate for a CI bot that reviews every pull request?

    Yes, it's a fit. Automated review is asynchronous, so the baseline inference rate carries no penalty. MiniMax M2.1's improved instruction adherence means review criteria apply consistently across every PR.

  • When should I look past the 2.1 generation entirely?

    When your workflow benefits from the plan-then-code architecture that M2.5 introduced, or the multi-agent coordination in M2.7. Those later generations address different design patterns.