Sign up now! New useSign up now! New users get $20 in free creditsDeepSeek V3.1
MiniMax-M2.1 API
CODELLM

MiniMax-M2.1 API

All You Need To Know About MiniMax-M2.1 API

Overview

Model Provider:MiniMax-M2.1
Model Type:CODE
State:Ready

Key Specs

Quantization:FP8
Parameters:229B
Context:192k
Pricing:$0.27 input / $1.08 output
Try Model API
Quick Start
Reserve Dedicated Endpoint

Introduction

Today, we’re releasing MiniMax-M2.1 to the open-source community—and the MiniMax-M2.1 API marks more than a routine model update. It represents a meaningful step toward democratizing top-tier agentic intelligence.

MiniMax-M2.1 was designed to challenge the assumption that high-performance agents must remain closed and inaccessible. Optimized for robustness across coding, tool use, instruction following, and long-horizon planning, the MiniMax-M2.1 API enables developers to tackle everything from multilingual software automation to complex, multi-step enterprise workflows.

With full transparency, fine-grained control, and open accessibility, the MiniMax-M2.1 API empowers builders to create the next generation of autonomous applications—without compromising trust or flexibility. We believe true intelligence should be within reach, and M2.1 is our commitment to that future, now placed directly in your hands.

MiniMax-M2.1 API Usage

Model

Endpoint

minimax/minimax-m2.1


        1
        curl -X POST https://inference.canopywave.io/v1 \
      
        2
          -H "Content-Type: application/json" \
      
        3
          -H "Authorization: Bearer $CANOPYWAVE_API_KEY" \
      
        4
          -d '{
      
        5
            "model": "minimax/minimax-m2.1",
      
        6
            "messages": [
      
        7
              {"role": "system", "content": "You are a helpful assistant."},
      
        8
              {"role": "user", "content": "please tell me a story."}
      
        9
            ]
      
        10
          }'
Contact us