MiniMax M2-her

Provider: MiniMax CN

No longer listed on OpenRouter since 2026-11-05. The figures below are the last recorded values.
Input price
$0.30
/ 1M tokens
Output price
$1.20
/ 1M tokens
Cache price
$0.03
/ 1M tokens (read)
Context
66K tokens
Max output 2K tokens

Overview

MiniMax M2-her is a mid-tier model from Chinese provider MiniMax, positioned with a competitive input price but a more constrained context window compared to its higher-end siblings. It targets general-purpose language tasks that operate within a moderate context length, offering a specific benefit for cached interactions.

Strengths

  • Offers a moderate 65,536 token context window, suitable for many common tasks.
  • Features a very low cache read price of $0.03 per million tokens, benefiting repetitive queries.
  • Provides a competitive input token price of $0.3 per million tokens, matching several peer models.

Best use cases

  • General text generation or summarization tasks requiring moderate document lengths.
  • Chatbot applications where conversational history fits within its 65,536 token context.
  • Information extraction from documents up to its context limit.
  • Applications with high rates of repeated queries that can leverage its low cache read price.

Pricing position

With an input price of $0.3/M tokens, M2-her is more expensive than most of its MiniMax siblings, such as M2.5 ($0.15/M) or M2 ($0.255/M), though it matches peers like Gemini 2.5 Flash and Grok 3 Mini. Its output price of $1.2/M tokens is among the highest within MiniMax and significantly higher than Grok 3 Mini ($0.5/M) or Codestral 2508 ($0.9/M), but more economical than Gemini 2.5 Flash ($2.5/M).

Caveats

The specific capabilities of MiniMax M2-her are unknown, making it difficult to assess its performance for tasks requiring advanced reasoning or multimodal input. Its 65,536 token context window is notably smaller than MiniMax M2.5 (204,800 tokens) or MiniMax-01 (1,000,192 tokens), which also offer lower input prices. For use cases not benefiting from its unique caching feature or requiring larger contexts, other MiniMax models may offer better value.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
2K tokens
Tracked since
2026-05-09
Last updated
2026-11-05

Features

No information available

Price history

  • 2026-11-05 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.09
1M (small app) 1 0.5 $0.90
10M (mid scale) 10 5 $9.00
100M (large) 100 50 $90.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from MiniMax

Similar-priced models

Source: OpenRouter API