---
id: "minimax/minimax-m1"
also: ["minimax/minimax-m1"]
card_usd_per_m: "0.4 in, 2.2 out, at minimax"
cheapest_list_usd_per_m: "0.4 in, 2.2 out, at minimax on openrouter"
cheapest_effective_usd_per_m: "0.3999 in, 2.1996 out, at minimax on openrouter"
context: 1000000
max_output: 40000
input: ["text"]
output: ["text"]
released: "2025-06-17"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 2
gateways: "openrouter (2)"
no_training: 2
trains: 0
retains_prompts: 1
---
# MiniMax: MiniMax M1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...