MMiniMax · Released Jan 23, 2026
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...
- Released
- Jan 23 2026
- Context window
- 66K 2K out
- Input / 1M tokens
- $0.30
- Output / 1M tokens
- $1.20
Where to run it
4 providers compared
Cheapest: Minimax, Kilo Gateway, Ofox at $0.30 / $1.20 per 1M input / output tokens — 1% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Minimaxno tool calling | $0.30 | $1.20 | $0.03 | 66K | 2K | 93.2%24h | Cheapest |
| Kilo Gatewayno tool calling | $0.30 | $1.20 | $0.03 | 66K | 2K | — | Cheapest |
| Ofox | $0.30 | $1.20 | — | 66K | 2K | — | Cheapest |
| NanoGPTno tool calling | $0.30 | $1.21 | $0.15 | 66K | 2K | — | +1% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated MiniMax M2-her. Scores appear here automatically once it does.
Specs
Details
- Model ID
minimax/minimax-m2-her- Developer
- MiniMax
- Release date
- Jan 23, 2026 ·
- Context window
- 65,536 tokens
- Max output
- 2,048 tokens
- API price
- $0.30 / $1.20 per 1M input / output tokens
- Providers
- 4
- Input types
- text
- Reasoning
- No
- Tool calling
- No
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.