prices synced 2026-09-22
X

MiMo-V2.6-Flash

Xiaomi · Multimodal · Released Sep 2026

Compare

MiMo-V2.6-Flash is a text language model from Xiaomi built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, supporting a 1M token context window.

Strengths
The sparse MoE design reduces computational overhead while the hybrid attention mechanism handles long-range dependencies efficiently across the extended context window.
Best for
Processing long-form text and maintaining context over extended sequences where a smaller per-token parameter footprint is acceptable.
Limitations
As a text-only model, it does not handle images, video, or multimodal inputs; for those use cases or higher throughput demands, MiMo-V2.5-Pro or MiMo-V2.6-Pro-UltraSpeed may be more suitable.

Input / 1M

$0.14

Output / 1M

$0.28

Cached input / 1M

$0.0028

Context window

1.05M

Price history

Price per 1M tokens over timeOutput $0.28; Input $0.14 as of Sep 2026.$0$0.1$0.2$0.3Output on 22 Sep 2026: $0.28Out $0.28Input on 22 Sep 2026: $0.14In $0.14Sep 2026

Snapshots

Effective Input Output Cached in Note Source
22 Sep 2026 $0.14 $0.28 $0.0028 Imported from OpenRouter openrouter.ai

More from Xiaomi

Report a problem