Model comparison
MiniMax M2.1 vs MiniMax M2-her
Compare MiniMax M2.1 and MiniMax M2-her: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
Minimax
MiniMax M2.1
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated par
Minimax
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
| Metric | MiniMax M2.1 | MiniMax M2-her |
|---|---|---|
| Provider | Minimax | Minimax |
| Context window | 204,800 | 65,536 |
| Input $/Mtok | $0.300 | $0.300 |
| Output $/Mtok | $1.20 | $1.20 |
| Modalities | text | text |
| License | open-weights | closed |
Quick take
On input price, MiniMax M2.1 is cheaper at $0.300/Mtok. For context window, MiniMax M2.1 leads with 204,800 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.