MiniMax M2.7

Provider: MiniMax CN

Input price
$0.21
/ 1M tokens
Output price
$0.84
/ 1M tokens
Cache price
$0.042
/ 1M tokens (read)
Context
197K tokens
Max output 177K tokens

Overview

MiniMax M2.7 is a mid-tier model configured for autonomous task execution with a 196k context window and built-in thinking capabilities.

Strengths

  • Input cost of $0.21 per million tokens
  • Output cost of $0.84 per million tokens
  • Cached input drops to $0.042 per million
  • Supports function-calling and strict JSON mode

Best use cases

  • Autonomous agent workflows requiring reasoning steps
  • Structured data extraction via JSON mode
  • Real-world productivity automation pipelines

Pricing position

Priced slightly below older sibling M2.5 at $0.295/$1.20, but substantially more expensive on output than Ministral 3 at $0.20/$0.20.

Caveats

Context window of 196k is smaller than newer siblings like M3.1 Flash reaching 1M tokens.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
177K tokens
Listed on OpenRouter
2026-03-18
Tracked since
2026-05-09
Last updated
2026-11-10

Features

Function callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.06
1M (small app) 1 0.5 $0.63
10M (mid scale) 10 5 $6.30
100M (large) 100 50 $63.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from MiniMax

Similar-priced models

Source: OpenRouter API (minimax/minimax-m2.7)