MiniMax-M2.7

MiniMaxMCP Tool CallReasoning
minimax/MiniMax-M2.7Open Weights

Open MiniMax flagship for coding agents, office automation, and complex environments

Benchmark Pricing$0.30 / 1M in$1.20 / 1M out$0.06 cache read
Context: 204,800 tokens•Max Output: 131,072 tokens•Released: 2026-03-18

TECHNICAL SPECIFICATIONS

Context Window204,800204.8K tokens
Max Output131,072131.1K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ MiniMax-M2.7 natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 204,800 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedresolved
79.9
SWE-Bench Proresolve rate
56.2
Terminal-Benchsuccess rate
51.1

API CALL INVOCATION EXAMPLE

// Example: Calling MiniMax-M2.7 via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MINIMAX_API_KEY,
});

const response = await client.chat.completions.create({
  model: "minimax/MiniMax-M2.7",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

15 providers
MiniMax (minimax.io)MiniMax-M2.7
$0.30 / $1.20$0.06 cache
OpenCode Gominimax-m2.7
$0.30 / $1.20$0.06 cache
Charm Hyperminimax-m2.7
$0.48 / $1.85$0.24 cache
MoarkMiniMax-M2.7
$0.29 / $1.20
CrossModelminimax/minimax-m2.7
$0.33 / $1.32$0.07 cache
Novita AIminimax/minimax-m2.7
$0.30 / $1.20$0.06 cache
302.AIMiniMax-M2.7
$0.30 / $1.20
Tempr Gatewayminimax/MiniMax-M2.7-highspeed
$0.60 / $2.40$0.06 cache
Aurikominimax-m2-7
$0.30 / $1.20$0.06 cache
AbacusMiniMaxAI/MiniMax-M2.7
$0.30 / $1.20
OpenCodeminimax-m2.7
$0.30 / $1.20$0.06 cache
UnoRouterminimax-m2.7:free
$0.00 / $0.00
Eden AIminimax/MiniMax-M2.7
$0.30 / $1.20$0.06 cache
Ofoxminimax/minimax-m2.7
$0.30 / $1.20$0.06 cache
GMI CloudMiniMaxAI/MiniMax-M2.7
$0.30 / $1.20$0.06 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.06 / 1M tokens, saving up to 80% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES

View MiniMax HubHugging Face Weights

More Models by MiniMax

Alternative and family models from the same lab

View all MiniMax models →
MiniMax-M3
minimax/MiniMax-M3•MiniMax
1M ctx

MiniMax multimodal model for long-context coding, perception, and agent planning

512K out maxVisionSWE-Bench Verified: 80.5 resolved
In: $0.30 • Out: $1.20
MiniMax
MiniMax Text 01 (MiniMax)
minimax/MiniMax-Text-01•MiniMax
1M ctx

MiniMax model for chat, coding, office work, and agentic tasks

131.1K out max
In: $0.20 • Out: $1.10
MiniMax
MiniMax M1 80K
minimax/minimax-m1-80k•MiniMax
1M ctx

Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget

80K out max
In: $0.61 • Out: $2.42
MiniMax