Skip to content

MiniMax · Chat

MiniMax M1

MiniMax 🇨🇳ChatOpen weights. One of its sources says the weights are publicly available.

Newer version: MiniMax M2. We compared release dates and version names in our catalogue.

From Aiml API's listing:
MiniMax-M1 is a powerful reasoning model with a 1M token context window, delivering strong performance on complex tasks.
llminfo IQ
≈ 117
Maker's price
$0.85 blended / 1M
Max context
1M
Listings
7

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).

llminfo IQ ≈ 117, ranked among chat models. From 44 benchmarks. Little data behind it, so treat it as a rough estimate.How llminfo IQ is computedPoor value (44.8). Costs more per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 16 Jun 2025Maker HQ: CN (source)
All rankings: #555 on OpenRouter this monthSources: LMArena data, Models.dev data, AI/ML API data, llminfo researchPrimary data from LMArena from Models.dev: name, weights availability from AI/ML API: primary mode, description from llminfo research: release date

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 2 of the 8 peers that say either way have open weights.

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 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured output

Listings

 MiniMaxminimax-m1Source: GenAI Prices dataNot published by the provider$0.40$2.20
 302aiMiniMax-M1Sources: 302.ai data, Models.dev data1M$0.132$1.254
 Flowdotminimax/minimax-m1Source: FlowDot data1M$0.40$2.20
 OpenRouterminimax/minimax-m1Source: GenAI Prices dataNot published by the provider$0.30$1.65
 OpenRouterminimax-m1:extended · extendedSource: GenAI Prices dataNot published by the provider$0.55$2.20
 QiniuMiniMax-M1Sources: Models.dev data, Qiniu AI data, Qiniu AI Model Plaza Pricing1M

1 listing without a price is hidden.

Benchmarks

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

Human preference

Coding

Instruction following

Math

Reasoning

Other

Data credits: LMArena, CC BY 4.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Around the web

  • game theory — minimax search and alpha-beta
    interpret the outcome as a score by the following rule: win for crosses = 1, …interpret the outcome as a score by the following rule: win for crosses = 1, win for noughts = − 1, draw = 0. Max plays crosses and Min plays noughts. The complete game tree is huge, but here is a su…

    math.kth.se

  • Minimax search and alpha-beta pruning
    Alpha-Beta Pruning *) fun minimax(n: node, d: int, min: int, max: int): int = if …Alpha-Beta Pruning *) fun minimax(n: node, d: int, min: int, max: int): int = if leaf(n) or depth=0 return evaluate(n) if n is a max node v := min for each child of n v' := minimax (child,d-1, v,max …

    cs.cornell.edu

  • The Minimax Algorithm.
    In a trivial example like the one above, minimax is useful because it is a …In a trivial example like the one above, minimax is useful because it is a reasonable expectation that the computer's opponent can figure out what its best options are; in more complex games, however…

    cs.stanford.edu

  • MiniMax
    MiniMax MiniMax has independently developed a series of multimodal foundation models with powerful code and …MiniMax MiniMax has independently developed a series of multimodal foundation models with powerful code and Agent capabilities, as well as ultra-long context processing

    minimax.io

  • MiniMax - About Us | MiniMax
    MiniMax Models LLM LLM MiniMax M3 MiniMax M2.7 MiniMax M2.5 VIDEO VIDEO MiniMax H3 SPEECH …MiniMax Models LLM LLM MiniMax M3 MiniMax M2.7 MiniMax M2.5 VIDEO VIDEO MiniMax H3 SPEECH & MUSIC SPEECH & MUSIC MiniMax Speech 2.8 MiniMax Music 3.0 Product MiniMax Code MiniMax Design Audio Talkie …

    minimax.io

  • Minimax in Python: Learn How to Lose the Game of Nim – Real Python
    problems, in particular for bigger trees. In Python, function calls have some overhead, and the …problems, in particular for bigger trees. In Python, function calls have some overhead, and the call stack is limited. You’ll see how to counter some of these issues later . But a non-recursive imple…

    realpython.com

  • Implementing the Minimax Algorithm for AI in Python | DataCamp
    What is the Minimax Algorithm? Minimax is usually a decision-making algorithm for two-player games (like …What is the Minimax Algorithm? Minimax is usually a decision-making algorithm for two-player games (like chess, tic-tac-toe, or checkers). It allows computers to plan several moves while assuming you…

    datacamp.com

  • - MiniMax News | MiniMax
    MiniMax Models LLM LLM MiniMax M3 MiniMax M2.7 MiniMax M2.5 VIDEO VIDEO MiniMax H3 SPEECH …MiniMax Models LLM LLM MiniMax M3 MiniMax M2.7 MiniMax M2.5 VIDEO VIDEO MiniMax H3 SPEECH & MUSIC SPEECH & MUSIC MiniMax Speech 2.8 MiniMax Music 3.0 Product MiniMax Code MiniMax Design Audio Talkie …

    minimax.io

  • Minimax: exercises and theory
    Minimax (sometimes MinMax or MM) is a decision rule used in decision theory, game theory, …Minimax (sometimes MinMax or MM) is a decision rule used in decision theory, game theory, statistics and philosophy for minimizing the possible loss for a worst case (maximum loss) scenario. Original…

    codingame.com

  • MiniMax M2.7 - Model Self-Improvement, Driving ...
    MiniMax M2.7 - Model Self-Improvement, Driving ... MiniMax M2.7 Large Language Model, with enhanced capabilities …MiniMax M2.7 - Model Self-Improvement, Driving ... MiniMax M2.7 Large Language Model, with enhanced capabilities for building complex Agents. Delivers industry-leading coding and reasoning abilities …

    minimax.io

Also known as: minimax-m1, minimax-m1:extended, minimax/m1, minimax/minimax-m1

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