---
id: "minimax/minimax-m2.5"
also: ["minimax/minimax-m2.5-20260211", "MiniMaxAI/MiniMax-M2.5", "hf/MiniMaxAI/MiniMax-M2.5", "requesty/minimax/minimax-m2.5", "vercel/minimax/minimax-m2.5"]
card_usd_per_m: "0.3 in, 1.2 out, at minimax/fp8"
cheapest_list_usd_per_m: "0.22 in, 0.9 out, at inceptron/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.0452 in, 1.1991 out, at siliconflow/fp8 on openrouter"
context: 200000
max_output: 58982
input: ["text"]
output: ["text"]
released: "2026-02-12"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 29
gateways: "openrouter (12), requesty (10), vercel (5), hf (2)"
no_training: 25
trains: 0
retains_prompts: 4
---
# MiniMax: MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. It is capable of handling the entire development process of various complex systems. It covers full-stack projects across multiple platforms including Web, Android, iOS, Windows, and Mac, encompassing server-side APIs, functional logic, and databases.