Skip to content
ModelCap

MiniMax M2

All-versions archive #119Arena #200Restricted license

MiniMax·minimax/minimax-m2

MiniMax M2 is a language model published by MiniMax. 3 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 205K tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · All-versions archive
48.1#119
Measured · 70% support · score interval 48.1–56.9
Market Gravity
35.2
Secondary market signal

Superseded by MiniMax M3. It no longer holds a current-board position; its all-versions archive rank is #119.

Input
$0.255
per 1M tokens
Output
$1.02
per 1M tokens
Context
205K
tokens
Providers
3
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Minimaxfp8Cheapest$0.255$1.02205Kfp8—
Google$0.30$1.20197K—100.0%
Novitafp8$0.30$1.20205Kfp8—

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
novita
live
$0.30$1.20205K1259 ms65.3 tok/stools
featherless-ai
live
——————

Reported evaluation leads (4)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
cais/hle
hle
—12.5
Unpinned
not published
Reported
Quarantined
harborframework/terminal-bench-2.0
terminalbench_2
—30
Unpinned
not published
Reported
Quarantined
SWE-bench/SWE-bench_Verified
swe_bench_%_resolved
—69.4
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
—82
Unpinned
not published
Reported
Quarantined

Other versions (5)

ModelCap Index · All-versions archive

Methodology
48.1
Measured · 3 public benchmark observations across 3 boards
All-versions archive
#119
Public rank basis
Measured (measured)
Index support
69.5% · strong
Index interval
48.1–56.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · minimax/minimax/minimax-m2/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata MiniMaxAI/MiniMax-M2@757303d492a50514c312788b5247a4f696a4c6a3 (not the evaluation revision)
Direct benchmark observations
3
Breadth-adjusted BES point estimate
52.5
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
52.5
Evidence status
confirmed · 79% mass
General preference
52.6
Coding
52.2
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
70%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
6.2
Liquidity (providers × uptime)
90.3
Open reach (HF downloads)
—
Surface (context / tools / modalities)
73.5
Freshness
33.4
  • · OpenRouter popularity #209
  • · 3 live providers
  • · Catalogue: context 204800, reasoning, tools
  • · First seen 2025-10-23

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
85.7
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
92.5
Deployability
96.2
Evaluation provenance
64.2

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
35.2
OpenRouter weekly popularity
#209 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#200 of 385
Rating
1346.0
95% confidence interval
1338–1354
Votes
7K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
6.2

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
90.3

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
33.4

Time since first public availability, on a six-month half-life.

Specification

Context window
205K tokens
Max output
131K tokens
Inputs
Text
Outputs
Text
Tokenizer
Other
Cached input tokens
Not offered
First seen on OpenRouter
23 Oct 2025

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Restricted license. Downloadable weights use a model-specific or use-restricted license. Review the linked license before use, redistribution, or commercial deployment.

Access
Restricted license
Licence
modified-mit
Pinned revision
757303d492a5
Parameters
228.7B
Architecture
MiniMaxM2ForCausalLM
Model type
minimax_m2
Hugging Face downloads (30d)
127K
Downloads (all time)
2.4M
Likes
2K
Repository
MiniMaxAI/MiniMax-M2
Repository updated
23 Dec 2025, 08:37 UTC