MiniMax M2.5

Provider: MiniMax CN

Input price
$0.29
/ 1M tokens
Output price
$1.20
/ 1M tokens
Cache price
$0.06
/ 1M tokens (read)
Context
198K tokens
Max output 33K tokens

Overview

MiniMax M2.5 is a reasoning-capable model built by MiniMax for complex productivity and coding tasks. It features a 200k context window and dedicated thinking capabilities.

Strengths

  • Supports native function-calling and JSON mode
  • Includes built-in thinking capability
  • Reaches 200k token context window
  • Outputs up to 58,982 tokens per request

Best use cases

  • Complex multi-step reasoning workflows
  • Structured data extraction tasks
  • Coding assistant integrations

Pricing position

Priced at $0.295 input and $1.20 output per million tokens, matching sibling MiniMax M3 and DeepSeek V4.1 Flash.

Caveats

Context window of 200k tokens is smaller than the 1M capacity found on M3.1 Flash and Qwen3.5 Plus.

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
33K tokens
Listed on OpenRouter
2026-02-12
Tracked since
2026-05-09
Last updated
2026-11-13

Features

Function callingJSON outputReasoning

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 $8.95
100M (large) 100 50 $89.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from MiniMax

Similar-priced models

Source: OpenRouter API (minimax/minimax-m2.5)