ModelBench
MiniMax logo
Models/MiniMax

MiniMax-M2

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Source-linked minimax Open weights Released 2025-10-27
API data Report
Input modalitiesT
Output modalitiesT
Input price$0.3/1M tokens
Output price$1.2/1M tokens
Context window196.608K
Max output128K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Creator
MiniMax
Model family
minimax
Knowledge cutoff
Not documented
License
Not documented
Release date
2025-10-27
Model ID
minimax/MiniMax-M2
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering MiniMax-M2
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
MiniMax Token Plan (minimax.io) MiniMax-M2 196.608K Not listed Not listed - ReasoningTools Docs
MiniMax Token Plan (minimaxi.com) MiniMax-M2 196.608K Not listed Not listed - ReasoningTools Docs
LLM Gateway minimax-m2 196.608K $0.2 $1 $0.03 ReasoningTools Docs
OpenRouter minimax/minimax-m2 204.8K $0.255 $1.02 - ReasoningToolsJSON Docs
Hugging Face MiniMaxAI/MiniMax-M2 204.8K $0.3 $1.2 - ReasoningTools Docs
NovitaAI minimax/minimax-m2 204.8K $0.3 $1.2 $0.03 ReasoningTools Docs
Merge Gateway minimax/minimax-m2 204.8K $0.3 $1.2 $0.03 ReasoningTools Docs
MiniMax (minimaxi.com) MiniMax-M2 196.608K $0.3 $1.2 - ReasoningTools Docs
MiniMax (minimax.io) MiniMax-M2 196.608K $0.3 $1.2 - ReasoningTools Docs
Cortecs minimax-m2 400K $0.39 $1.57 - ReasoningTools Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
SWE-Bench Verified - Unversioned - resolvedTop 8 reported models
Claude Fable 5
95.0
Claude Opus 4.8
88.6
Claude Sonnet 5
85.2
DeepSeek V4 Pro
80.6
Qwen3.7 Max
80.4
Kimi K2.6
80.2
DeepSeek V4 Flash
79.0
MiniMax-M2
69.4
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/minimax/MiniMax-M2
curl
curl "https://www.modelbench.lol/api/v1/models/minimax/MiniMax-M2"