Skip to content

MiniMax · Chat

MiniMax M2.1

MiniMax 🇨🇳ChatOpen weights. One of its sources says the weights are publicly available.The maker currently plans to deprecate it within the next 180 days (30 Mar 2027). Plans can change.
From Aiml API's listing:
MiniMax-M2.1 is an updated Minimax model with a 200K context window optimized for conversational and reasoning tasks.
llminfo IQ
122.3
Maker's price
$0.525 blended / 1M
Max context
1M
Listings
38

Evidence and sources

International API storefront (minimax.io) is Singapore-based; principal operating entity 上海稀宇科技有限公司 (Shanghai).

🤗 MiniMaxAI/MiniMax-M2.1llminfo IQ 122.3, ranked among chat models. From 97 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 96.5, 95% interval 91–102. From 10 benchmark families across 7 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (45.1). Costs more per task than its benchmark results predict. From 23 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (59 ±13). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 45,251 output tokens per task at default effort.How the Yap score worksReleased 20 Dec 2025Maker HQ: CN (source)
All rankings: #450 on OpenRouter this month #565 on NanoGPT recentlySources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data, AI/ML API data, Hugging FacePrimary data from AWS Bedrock Runtime from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode, description from Hugging Face: release date
Tags from its sources:instructtoolsreasoningopen-sourcemoelong-contextvision

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 1 of the 9 peers that say either way has open weights.

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 30 Mar 2027, within the next 180 days.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt cachingBatch API

Listings

 MiniMaxminimax/MiniMax-M2.1Sources: LiteLLM data, Models.dev data1M$0.30cache read $0.03$1.20cache write $0.375
 Aihubmixcoding-minimax-m2.1-free · coding, freeSource: AIHubMix data docs205K$0.00$0.00
 Llmgatewayminimax-m2.1Source: LLMGateway data205K$0.27$1.10
 Llmgateway Providersminimax/minimax-m2.1Source: Models.dev data197K$0.27$1.10
 MeganovaMiniMaxAI/MiniMax-M2.1Sources: MegaNova data, Models.dev data197K$0.28$1.20
 Flowdotminimax/minimax-m2.1Source: FlowDot data197K$0.29$0.95
 OpenRouterminimax/minimax-m2.1Source: GenAI Prices dataNot published by the provider$0.29cache read $0.03$0.95
 MoarkMiniMax-M2.1Source: Models.dev data205K$0.29$1.20
 Amazon Web Servicesminimax.minimax-m2.1Sources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data196K$0.30batch $0.15$1.20batch $0.60
 302aiminimax/minimax-m2.1Sources: 302.ai data, Models.dev data205K$0.30$1.20
Show all 35 listings

Showing 10 of 35: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Cortecs AI, Eden AI, Eurouter, Fireworks AI, Gmicloud, Hugging Face, Jiekou, Kilo, Merge Gateway, Minimax Cn, NanoGPT, Novita AI, Ofox, Openroute Cn, Poe, Qiniu, Tokenmix, Vercel, Zenmux.

3 listings without a price are hidden.

Included in plans

MiniMax M Plan GoMiniMaxSubscription$22/moPlan page
MiniMax M Plan ExploreMiniMaxSubscription$55/moPlan page
MiniMax M Plan BuildMiniMaxSubscription$132/moPlan page

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Coding

SciCodeSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-Perf7 related benchmarks · 7 results
SWE-Perf
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-bench Multilingual
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-bench Verified
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Show 1 more resultHide 1 result
SWE-Review
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWT-BenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
VIBESource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Agentic

OpenHandsSource: OpenHands Index data

Human preference

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Reasoning

Math

ValsSource: Vals AI

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

Instruction following

IFBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Knowledge

Long context

Other

Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
MiniMaxAI/MiniMax-M2.1: reasoning-enabled

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · OpenEvals/leaderboard-data, MIT (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · OpenHands Index (All Hands AI), Apache-2.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Also known as: bedrock/ap-northeast-1/minimax.minimax-m2.1, bedrock/ap-south-1/minimax.minimax-m2.1, bedrock/ap-southeast-2/minimax.minimax-m2.1, bedrock/ap-southeast-3/minimax.minimax-m2.1, bedrock/eu-central-1/minimax.minimax-m2.1, bedrock/eu-north-1/minimax.minimax-m2.1, bedrock/eu-south-1/minimax.minimax-m2.1, bedrock/eu-west-1/minimax.minimax-m2.1, bedrock/eu-west-2/minimax.minimax-m2.1, bedrock/sa-east-1/minimax.minimax-m2.1, bedrock/us-east-1/minimax.minimax-m2.1, bedrock/us-east-2/minimax.minimax-m2.1, bedrock/us-west-2/minimax.minimax-m2.1, bedrock_mantle/ap-northeast-1/minimax.minimax-m2.1, bedrock_mantle/ap-south-1/minimax.minimax-m2.1, bedrock_mantle/ap-southeast-2/minimax.minimax-m2.1, bedrock_mantle/ap-southeast-3/minimax.minimax-m2.1, bedrock_mantle/eu-central-1/minimax.minimax-m2.1, bedrock_mantle/eu-north-1/minimax.minimax-m2.1, bedrock_mantle/eu-south-1/minimax.minimax-m2.1, bedrock_mantle/eu-west-1/minimax.minimax-m2.1, bedrock_mantle/eu-west-2/minimax.minimax-m2.1, bedrock_mantle/minimax.minimax-m2.1, bedrock_mantle/sa-east-1/minimax.minimax-m2.1, cc-minimax-m2.1, coding-minimax-m2.1, coding-minimax-m2.1-free, fireworks_ai/accounts/fireworks/models/minimax-m2p1, fireworks_ai/minimax-m2p1, gmi/minimaxai/minimax-m2.1, minimax-m2.1, minimax-m2.1-free, minimax-m2.1-highspeed, minimax-m2p1, minimax.minimax-m2.1, minimax/m2-1, minimax/m2-1-highspeed, minimax/minimax-m2.1, minimax/minimax-m2.1-highspeed, minimaxai/minimax-m2.1, novita/minimax-m2.1, novita/minimax/minimax-m2.1, sophnet/minimax-m2.1

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works