Xiaomi
xiaomi/mimo-v2.6-flash-20260921Hugging Face ↗
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
OpenRouter share of tokens, by day.
Xiaomi: MiMo-V2.6-Flash holds 2.08% today, up from 0.72% at the start of the visible window.
Xiaomi: MiMo-V2.6-Flash's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-11-10, Xiaomi: MiMo-V2.6-Flash holds 2.1% of OpenRouter token share, down 4.02pp over 30 days. Source: OpenRouter (openrouter.ai/rankings), as of 2026-11-10. tidelines.ai
Median dollars spent on one Xiaomi: MiMo-V2.6-Flash session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Kilo Code | $0.0002 | $0.011 | $0.036 | $0.217 |
| Hermes Agent | $0.0011 | $0.0035 | $0.028 | $0.161 |
| Claude Code | $0.0024 | $0.0047 | $0.027 | $0.174 |
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Xiaomi: MiMo-V2.6-Flash is served by 8 tracked endpoints on OpenRouter. The cheapest output price is $0.22 per million tokens from GMICloud, and the most expensive is $0.35 from Venice. The largest context window offered is 1050k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| GMICloud | $0.11 | $0.22 | 1050k | 100.00% |
| Darkbloom | $0.100 | $0.28 | 1049k | 100.00% |
| Cohere | $0.14 | $0.28 | 1049k | 96.67% |
| DeepInfra | $0.14 | $0.28 | 1049k | 100.00% |
| Xiaomi | $0.14 | $0.28 | 1049k | 100.00% |
| Tenstorrent | $0.17 | $0.33 | 1049k | 100.00% |
| Makora | $0.17 | $0.33 | 1049k | 100.00% |
| Venice | $0.17 | $0.35 | 1000k | 100.00% |