MiniMax M2 (MiniMax-M2) is a chat model from minimax with a 200K-token context window; open-weight; capabilities tools, reasoning; input text; output text.
200KContext
8.2KMax output
$0.3$ / 1M in
28.3Intelligence
96.733tok / s
Pricing
Input
$0.3 / 1M tokens
Output
$1.2 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.
Benchmarks
Intelligence index
28.3
Math
78.3
Cited from a public third-party leaderboard — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-24.
Performance
Throughput
96.733 tokens/s
Latency (TTFT)
1.169 s
Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-07-22.