AI Observatory / Model Radar Minimax / minimax/minimax-m2.1

MiniMax: MiniMax M2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

196,608 Context
196,608 Max output
$0.29 / 1M Prompt price
2025-12-23 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider Minimax Input modalities text
Output modalities text Prompt price $0.29 / 1M
Completion price $0.95 / 1M Request price N/A
Context length 196,608 Max completion tokens 196,608
Supported parameters frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Best for minimax/minimax-m2.1

MiniMax: MiniMax M2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

Coding workflows High-volume usage tool-capable low-cost
03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.