modelgrep
X

Xiaomi: MiMo-V2-Flash

xiaomi/mimo-v2-flash

77th smartest of 179Cheaper than 83% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
30.3
77th of 179
Design Elo
1211
Website
Speed
92
74th fastest
Latency
614ms
first token
Input price
$0.100
51st cheapest
Context
262K
66K max out

How it compares

Smarter than57%
of all ranked models
Faster than75%
of all ranked models
Cheaper than83%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis54th percentile
Intelligence Index
30.3
Coding Index
25.8
Agentic Index
47.3
GPQA Diamond
66%
Humanity's Last Exam
8%
SciCode
26%
Tau²-Bench (agentic)
84%
Design Arena · Elo16,330 tournaments
Website
1211
codecategories
1207
Game Dev
1200
UI Component
1199
3D
1196
Data Viz
1176
svg
1086
asciiart
1061

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Xiaomifp8$0.100$0.300100%

Specifications

Context window262K
Max output66K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.010/M
ModeratedNo

MiMo-V2-Flash FAQ

How much does MiMo-V2-Flash cost?

MiMo-V2-Flash costs $0.100 per million input tokens and $0.300 per million output tokens via OpenRouter, making it 51st cheapest of 298 paid models.

How smart is MiMo-V2-Flash?

MiMo-V2-Flash scores 30.3 on the Artificial Analysis Intelligence Index, ranking 77th of 179 benchmarked models, with a GPQA Diamond score of 66%.

How fast is MiMo-V2-Flash?

MiMo-V2-Flash generates around 92 tokens per second with 614ms time-to-first-token (p50), the 74th fastest tracked model.

What is MiMo-V2-Flash's context window?

MiMo-V2-Flash supports a 262K-token context window and can output up to 66K tokens. It accepts text input.

Compare head-to-head