Xiaomi
Xiaomi: MiMo-V2.5
xiaomi/mimo-v2.5-20260422Hugging Face ↗
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
Xiaomi: MiMo-V2.5 usage over time
OpenRouter share of tokens, by day.
Xiaomi: MiMo-V2.5 holds 3.17% today, up from 0.32% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
Xiaomi: MiMo-V2.5'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 2026-09-01, Xiaomi: MiMo-V2.5 holds 3.2% of OpenRouter token share, down 4.96pp over 30 days. Source: Tidelines (OpenRouter).
Cost per session
Median dollars spent on one Xiaomi: MiMo-V2.5 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 |
|---|---|---|---|---|
| Claude Code | $0.0033 | $0.0067 | $0.023 | $0.154 |
| Kilo Code | $0.0007 | $0.0067 | $0.018 | $0.098 |
| Hermes Agent | $0.0012 | $0.0042 | $0.017 | $0.094 |
Where to run it
Xiaomi: MiMo-V2.5 pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Xiaomi: MiMo-V2.5 is served by 5 tracked endpoints on OpenRouter. The cheapest output price is $0.24 per million tokens from GMICloud, and the most expensive is $0.65 from DeepInfra. The largest context window offered is 1050k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| GMICloud | $0.12 | $0.24 | 1050k | 72.51% |
| Xiaomi | $0.14 | $0.28 | 1049k | 90.41% |
| StreamLake | $0.17 | $0.34 | 1000k | 97.03% |
| Novita | $0.17 | $0.34 | 1049k | 95.34% |
| DeepInfra | $0.13 | $0.65 | 262k | 99.41% |