MiniMax: MiniMax M2-her
by MiniMaxMiniMax: MiniMax M2-her is a large language model from MiniMax. It costs $0.300 per million input tokens and $1.20 per million output tokens. Its context window is 66K tokens.
- Input / 1M tokens
- $0.300
- Output / 1M tokens
- $1.20
- Cached input / 1M
- $0.030
- Context window
- 66K
On repeated prefixes
tokens
Who serves it cheapest
1 hosts serve MiniMax M2-her. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| MinimaxCheapest | $0.300 | $1.20 | 66K | - | 100.0% |
About MiniMax M2-her
MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...
Specifications
| Model ID | minimax/minimax-m2-her |
|---|---|
| Provider | MiniMax |
| Context window | 66K tokens |
| Max output | 2K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | No |
| Released | January 23, 2026 |
Cheaper alternatives
Models that cost less than MiniMax M2-her while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does MiniMax: MiniMax M2-her cost?
$0.300 per million input tokens and $1.20 per million output tokens. Cached input reads cost $0.030 per million tokens.
What is the context window of MiniMax: MiniMax M2-her?
66K tokens, with up to 2K tokens of output per request.
Confirm against the source: MiniMax official pricing.