MiniMax-M3

MiniMaxMCP Tool CallReasoning
minimax/MiniMax-M3Open Weights

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

Benchmark Pricing$0.30 / 1M in$1.20 / 1M out$0.06 cache read
Context: 1,048,576 tokens•Max Output: 512,000 tokens•Released: 2026-06-01

TECHNICAL SPECIFICATIONS

Context Window1,048,5761M tokens
Max Output512,000512K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
TextVisionVideo
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ MiniMax-M3 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 1,048,576 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedresolved
80.5
SWE-Bench Proresolve rate
59
Terminal-Benchsuccess rate
66
BrowseCompaccuracy
83.52
MCP Atlassuccess rate
74.2
OSWorld-Verifiedsuccess rate
70.06

API CALL INVOCATION EXAMPLE

// Example: Calling MiniMax-M3 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-M3",
  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-M3
$0.30 / $1.20$0.06 cache
Cortecsminimax-m3
$0.30 / $1.20$0.06 cache
ClinePasscline-pass/minimax-m3
$0.30 / $1.20$0.06 cache
Fireworks AIaccounts/fireworks/models/minimax-m3
$0.30 / $1.20$0.06 cache
Volcengine Ark Coding Planminimax-m3
$0.00 / $0.00$0.00 cache
Vultrminimax-m3
$0.20 / $0.90
OpenCode Gominimax-m3
$0.30 / $1.20$0.06 cache
Jalapeno CloudMiniMax-M3
$0.30 / $1.20$0.06 cache
Charm Hyperminimax-m3
$0.33 / $1.31$0.06 cache
CrossModelminimax/minimax-m3
$0.33 / $1.32$0.07 cache
Novita AIminimax/minimax-m3
$0.30 / $1.20$0.06 cache
Synthetichf:MiniMaxAI/MiniMax-M3
$0.60 / $1.20$0.60 cache
302.AIMiniMax-M3
$0.72 / $2.88$0.14 cache
IteraComputeminimax/minimax-m3
$0.30 / $1.19$0.05 cache
CoreWeaveMiniMaxAI/MiniMax-M3
$0.23 / $0.96$0.05 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.