M

MiniMax M2.1

Minimax
Vision
205K
Context
$94.80
Input /1M
$4.41
Output /1M
N/A
Max Output
Run API Call Open in Chat

MiniMax M2.1

Overview

Property Value
Model ID (Inference) minimax/minimax-m2.1
Provider MiniMax
Created December 23, 2025
Context Length 204,800 tokens
Knowledge Cutoff June 2025
Input Modalities Text
Output Modalities Text

Description

A lightweight, state-of-the-art language model with 10 billion activated parameters, optimized for coding, agentic workflows, and application development. The model delivers cleaner, more concise outputs and faster perceived response times compared to predecessors, with strong multilingual coding performance.

Key Capabilities

  • Tool use and function calling support
  • Multipart request support
  • BYOK (Bring Your Own Key) enabled
  • Reasoning support with <think> tags
  • Mandatory reasoning feature enabled

Pricing

Type Cost per Million Tokens
Input $0.30
Output $1.20

Supported Parameters

Parameter Description
Reasoning Enable/disable reasoning mode
Include Reasoning Include reasoning in response output
Max Tokens Maximum tokens to generate
Temperature Controls randomness (0-2)
Top-p Nucleus sampling parameter
Tools Function/tool definitions for tool use
Tool Choice Control tool selection behavior
Response Format Specify response format (JSON, etc.)

Performance

Usage Statistics (Latest Day)

Metric Value
Prompt Tokens 94.8M
Completion Tokens 4.41M
Reasoning Tokens 2.77M
Total Requests 7,732

API Usage Example

curl https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGMART_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2.1",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

From MiniMax Provider

Model Model ID Context Input $/M Output $/M Description
MiniMax M2 minimax/minimax-m2 197K $0.20 $1.00 Compact, high-efficiency LLM optimized for end-to-end coding and agentic workflows
MiniMax M1 minimax/minimax-m1 1M $0.40 $2.20 Large-scale, open-weight reasoning model designed for extended context and high-efficiency inference
MiniMax-01 minimax/minimax-01 1M $0.20 $1.10 Combines text generation and image understanding with 456B parameters and 4M token context

Providers

MiniMax (Primary Provider)

Property Value
Region Singapore (headquarters); US (datacenters)
Data Policy Training disabled; prompts retained; no publishing allowed
Terms minimax.io/platform/protocol

Resources

Last updated: December 23, 2025 *Source: LangMart *