MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.
Back to Models
53.4%$0$0/ M tokens$0$0/ M tokensRead:00/ M tokensWrite:-/ M tokens262.14K1.97s85.6tps
Providers
Route requests across multiple providers. Copy a provider slug to set your preference.
ProviderCache Hit RateContext
XiaomiSunset
xiaomi
Uptime
24hoursDirect request success rate on AI Gateway and per-provider.
Mar 30, 11:24
Xiaomi100.00%
Throughput
24hoursP50 throughput on live AI Gateway traffic, in tokens per second (TPS).
Mar 30, 11:00
Xiaomi85.6 tps
Latency
24hoursP50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.
Mar 30, 11:00
Xiaomi1.97s
Activity
Token volume and request traffic to this model over time.
Token Consumption
Mar 30
Xiaomi670.1K
Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis
Artificial AnalysisNo benchmark data is available for this model.
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All
Token Ranking
No app usage is available for this period.
Related Models
More models from Xiaomi