MiniMax

MiniMax-M2.7 — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCEMiniMax
Input Cost
$0.30/1M
Output Cost
$1.2/1M
Context Window
205K
Max Output
131K
Accepts
text

MiniMax-M2.7 by MiniMax demonstrates competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.

General Benchmarks

AA Intelligence Index
23.236th of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)

Coding Benchmarks

Design Arena ELO
121936th of 120

Human preference ELO for building things — websites, UI, games, charts, SVG

Design Arena (via OpenRouter)
AA Coding Index
52.641st of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)
Website Arena ELO
125733rd of 108

Human preference ELO for building a working web page from a brief

Design Arena (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
16.840th of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)
GPQA Diamond
84.3%39th of 140

Graduate-level science Q&A by domain experts

Papers
τ²-Bench Airline
71.1%45th of 93

Multi-turn service agent making tool calls under strict policy constraints

OpenRouter (measured)

Cost Benchmarks

Input Cost
$0.30204th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$1.2209th of 413

Cost per 1M output tokens

OpenRouter API
Cached Input Cost
$0.0649th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API

Context Benchmarks

Context Length
205K177th of 451

Maximum context window size

OpenRouter API

Available from 43 providers

The same model costs different amounts depending on who serves it. You can bring your own key for 6 of these — connect it here.

ProviderInput / 1MOutput / 1MCached inContextYour key
Kenari$0$0205K
MiniMax Token Plan (minimaxi.com)$0$0$0205K
MiniMax Token Plan (minimax.io)$0$0$0205K
Nvidia$0$0205K
SCNet Token Plan$0$0$0205K
UnoRouter$0$0205K
DevPass (LLM Gateway)$0.08$0.32$0.017205K
EmpirioLabs AI$0.15$0.6$0.03200K
Deep Infra$0.25$1$0.05197KSupported
Pioneer$0.279$1.2$0.279205K
302.AI$0.3$1.2205K
Abacus$0.3$1.2205K
AIHubMix$0.3$1.2$0.06205K
Alibaba (China)$0.3$1.2$0.06205K
Auriko$0.3$1.2205K
Eden AI$0.3$1.2$0.06205K
FastRouter$0.3$1.2205K
FrogBot$0.3$1.2$0.06192K
GMI Cloud$0.3$1.2$0.06197K
Hugging Face$0.3$1.2$0.06205KSupported
Kilo Gateway$0.3$1.2$0.06205K
LLM Gateway$0.3$1.2$0.06200K
Merge Gateway$0.3$1.2$0.06205K
MiniMax (minimaxi.com)$0.3$1.2$0.06205K
MiniMax (minimax.io)$0.3$1.2$0.06205KSupported
NovitaAI$0.3$1.2$0.06205K
Ofox$0.3$1.2$0.06205K
OpenCode Go$0.3$1.2$0.06205K
OpenCode Zen$0.3$1.2$0.06205K
OpenRouter$0.3$1.2$0.06205KSupported
OrcaRouter$0.3$1.2$0.06205K
Requesty$0.3$1.2$0.06200K
Together AI$0.3$1.2$0.06203KSupported
Vercel AI Gateway$0.3$1.2$0.06205KSupported
Vultr$0.3$1.2205K
ZenMux$0.3055$1.2219205K
NanoGPT$0.315$1.26$0.1575205K
CrossModel$0.33$1.32$0.066205K
Venice AI$0.375$1.5$0.06875198K
Charm Hyper$0.396$1.464$0.198262K
SCX.ai$0.48$1.79$0.05197K
Cortecs$0.668$2.674197K
Ollama Cloud197K

MiniMax-M2.7 — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

MiniMax-M2.7 — Frequently Asked Questions

How much does MiniMax-M2.7 cost?

MiniMax-M2.7 costs $0.30 per 1M input tokens and $1.2 per 1M output tokens. This makes it one of the more affordable models.

What is the context window of MiniMax-M2.7?

MiniMax-M2.7 has a context window of 205K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created MiniMax-M2.7?

MiniMax-M2.7 was created by MiniMax. It is classified as a open source model in our catalogue.

Is MiniMax-M2.7 open source?

Yes, MiniMax-M2.7 is an open-source model. The model weights are publicly available for download and self-hosting.