MiniMax M2.1 is a large language model with a 204K token context window, released as part of MiniMax's M2 generation lineup.
- Strengths
- The model handles extended contexts efficiently and sits between the earlier M2 coding-focused tier and the later M2.5 productivity model.
- Best for
- General-purpose text generation and tasks that benefit from longer context windows without requiring multimodal capabilities.
- Limitations
- It is superseded by later releases in the M2 generation (M2.5 and M2.7) that offer improved performance; for multimodal work, the M3 generation is required.
Input / 1M
$0.3
Output / 1M
$1.20
Cached input / 1M
$0.03
Context window
204K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in increased 3.4% out increased 26.3%
- 1y
- in increased 3.4% out increased 26.3%
- Since launch
- in increased 3.4% out increased 26.3%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 2 Jul 2026 | $0.3 | $1.20 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.29 | $0.95 | $0.03 | Imported from OpenRouter | openrouter.ai |