MiMo-V2-Flash is Xiaomi's lightweight language model with a 262K token context window, positioned as an earlier generation model before the MiMo-V2.5 and V2.6 lineups.
- Strengths
- Offers efficient inference with a substantial context window for its generation, making it suitable for applications where speed and memory usage matter.
- Best for
- Workloads that require fast responses and reasonable context handling but do not need the extended 1M token window or parameter scale of newer MiMo models.
- Limitations
- The 262K context window is significantly smaller than MiMo-V2.5 and later releases, and earlier model generations typically show reduced performance on complex reasoning and specialized tasks compared to their successors.
Input / 1M
$0.1
Output / 1M
$0.3
Cached input / 1M
$0.01
Context window
262K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.1 | $0.3 | $0.01 | Imported from OpenRouter | openrouter.ai |