MiniMax M2

minimax/minimax-m2

A chat model with a 205K-token context window, at $0.315 per million input tokens and $1.26 per million output tokens.

Details

Maker: minimax
Kind: Chat
Context window: 205,000 tokens
Max output: 205,000 tokens
Input: $0.315 per million tokens
Cached input: $0.0315 per million tokens, 90% off
Cache write: $0.39375 per million tokens
Output: $1.26 per million tokens
Capabilities: Reasoning, tool use
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2025-10-27
Newer model: minimax/minimax-m3Released later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model