Models/MiniMax/MiniMax M2.1

MiniMax M2.1

Name: MiniMax M2.1 API access
Brand: MiniMax

MiniMax · Open weights · Released Dec 23, 2025 · minimax/minimax-m2.1

Compare Estimate cost

205K contextToolsReasoningStructured outputPrompt cachingOpen weights

Available from 3 providersUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Novita	$0.30	$1.20	$0.03	205K	fp8	1.9s	89 tok/s	99.6%
Minimaxminimax/fp81ST PARTY	$0.30	$1.20	$0.03	205K	fp8	1.6s	95 tok/s	99.3%
Minimaxminimax/highspeed1ST PARTY	$0.30	$2.40	$0.03	205K	fp8	—	—	100.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago

Pricing variants · USD / MTok in / out

STANDARD

$0.30 / $1.20

per MTok in / out

CACHE READ $0.03

About

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...

Specifications

Context window204,800

Max output131,072

Modalities intext

Modalities outtext

LicenseOpen weights

ReleasedDec 23, 2025

TokenizerOther

WeightsHugging Face ↗

Open weights

Hugging FaceMiniMaxAI/MiniMax-M2.1 ↗

Downloads27.4K

Likes1.4K

Licenseother

safetensors

MiniMax M3$0.23 / $0.96 MiniMax M2.7$0.24 / $0.96 MiniMax M2.5$0.27 / $0.95 MiniMax M2-her$0.30 / $1.20

Embed badge

[![MiniMax M2.1](https://modelindex.ai/badge/minimax/minimax-m2.1)](https://modelindex.ai/models/minimax/minimax-m2.1)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

Hugging Face4 minutes ago

COMMUNITY

ModelIndex benchmarks44 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.