Skip to content

MiniMax · Chat

MiniMax M2

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 is an advanced large language model with 1M token context for extended reasoning and generation.
llminfo IQ
118.9
Maker's price
$0.525 blended / 1M
Max context
1M
Listings
30

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-M2llminfo IQ 118.9, ranked among chat models. From 111 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 95.4, 95% interval 88–103. From 9 benchmark families across 7 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (57.8). Cheaper per task than its benchmark results predict. From 3 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksReleased 22 Oct 2025Maker HQ: CN (source)
All rankings: #483 on OpenRouter this month #563 on NanoGPT recentlySources: LMArena data, AWS Bedrock Runtime data, LiteLLM data, Models.dev data, AI/ML API data, Hugging FacePrimary data from LMArena from AWS Bedrock Runtime: name 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:instructtoolsreasoning

Advantages and trade-offs

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

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 6 maker's prices; 1 official partner's price; 3 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingBatch API

Listings

 MiniMaxMiniMax-M2Sources: GenAI Prices data, LiteLLM data, Models.dev data200K$0.30cache read $0.03$1.20cache write $0.375
 Aihubmixcoding-minimax-m2-free · coding, freeSource: AIHubMix data docs205K$0.00$0.00
 NanoGPTminimax/minimax-m2Sources: Models.dev data, NanoGPT200K$0.17cache read $0.085$1.53
 Llmgatewayminimax-m2Source: LLMGateway data197K$0.20cache read $0.03$1.00
 Llmgateway Providersminimax/minimax-m2Source: Models.dev data197K$0.20cache read $0.03$1.00
 Flowdotminimax/minimax-m2Source: FlowDot data197K$0.255$1.00
 OpenRouterminimax/minimax-m2Source: GenAI Prices dataNot published by the provider$0.255cache read $0.03$1.00
 Amazon Web Servicesminimax.minimax-m2Sources: AWS Bedrock Runtime data, LiteLLM data, Models.dev data1M$0.30batch $0.15$1.20batch $0.60
 Googlevertex_ai/minimaxai/minimax-m2-maas · maasSource: LiteLLM data197K$0.30cache read $0.03$1.20
 Eden AIInference by MiniMaxminimax/MiniMax-M2Source: Models.dev data205K$0.30$1.20
Show all 27 listings

Showing 10 of 27: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Cortecs AI, Fireworks AI, Gmicloud, Hugging Face, Merge Gateway, Minimax Cn, Novita AI, Ofox, Openroute Cn, Qiniu, Requesty, 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.

Human preference

Coding

Arena ELOSource: LMArena data · Nov 2026
LiveCodeBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.
SciCodeSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.

Agentic

BrowseCompSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.
BrowseComp-zhSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.
Tau-benchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.
Tau2 TelecomSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.

Reasoning

Instruction following

General

AA-IndexSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.
IFSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it.

Knowledge

Science

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

Other

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

Data credits: Data by LLM Stats · LMArena, CC BY 4.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · 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 · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

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

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