Input
$0.30
Output
$1.20
Context
64K
MiniMax M2-her costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input is billed at $0.03 per million, 90% less than fresh input.
Specifications
| Lab | MiniMax |
| Model id | minimax/minimax-m2-her |
| Input price | $0.30 per million tokens |
| Output price | $1.20 per million tokens |
| Cached input price | $0.03 per million tokens |
| Context window | 65,536 tokens (64K) |
| Maximum output | 2,048 tokens (2K) |
| Tool calling | no |
| Image input | no |
| Reasoning | no |
| First listed | 23 January 2026 |
MiniMax's other models
| Model | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| MiniMax M3.1 Flash | $0.15 | $0.60 | 1M | 19 October 2026 |
| MiniMax M3 | $0.30 | $1.20 | 1M | 31 May 2026 |
| MiniMax M2.7 | $0.30 | $1.20 | 200K | 18 March 2026 |
| MiniMax M2.5 | $0.30 | $1.20 | 200K | 12 February 2026 |
| MiniMax M2.1 | $0.30 | $1.20 | 200K | 23 December 2025 |
| MiniMax M2 | $0.255 | $1.02 | 200K | 23 October 2025 |
| MiniMax M1 | $0.55 | $2.20 | 1M | 17 June 2025 |
| MiniMax-01 | $0.20 | $1.10 | 1M | 15 January 2025 |
Where these numbers come from
Read from OpenRouter's listing of MiniMax M2-her every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.