MiniMax M2 is a 10B activated parameter model with a 196K token context window, designed for coding and agentic workflows.
- Strengths
- Handles coding tasks and multi-step reasoning efficiently with a large context window that enables processing of long documents and complex codebases.
- Best for
- Autonomous agents, code generation, and workflows that require sustained reasoning over extended inputs.
- Limitations
- Smaller activated parameter count may underperform on highly specialized domains or complex reasoning tasks compared to larger frontier models.
Input / 1M
$0.255
Output / 1M
$1.02
Cached input / 1M
—
Context window
204K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out increased 2.0%
- 90d
- in decreased 0.0% out increased 2.0%
- 1y
- in decreased 0.0% out increased 2.0%
- Since launch
- in decreased 0.0% out increased 2.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 24 Jul 2026 | $0.255 | $1.02 | — | Imported from OpenRouter | openrouter.ai |
| 23 Jul 2026 | $0.255 | $1.02 | — | Imported from OpenRouter | openrouter.ai |
| 19 Jul 2026 | $0.3 | $1.20 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 2 Jul 2026 | $0.255 | $1.02 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.255 | $1.00 | $0.03 | Imported from OpenRouter | openrouter.ai |