MiMo V2 Flash is Xiaomi's language model with a 262K context window and up to 32K output tokens, available from 3 providers, starting at $0.1 / 1M input and $0.3 / 1M output. A highly efficient MoE LLM from Xiaomi with 309B total parameters and only 15B active, designed for extreme inference speed with hybrid attention.
Specifications
Canonical IDxiaomi-mimo-2-flash
TypeLanguage
StatusDeprecated
CreatorXiaomiXiaomi
Providers
Context Window262K tokens
Max Output32K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters310B
HuggingFace Likes716
HuggingFace Downloads (30d)67,865
HuggingFace Downloads (all-time)728,735
Release Date · 7 months ago
Deprecation Date
Benchmarks
Intelligence Index
24.7
#129
Coding Index
49.8
#30
Math Index
67.7
#95
MMLU-Pro
0.7
#169
GPQA
0.7
#235
HLE
0.1
#183
LiveCodeBench
0.4
#168
IFBench
0.4
#235
Time to First Token
0.00s
#223
SciCode
0.3
#298
AIME 2025
0.7
#95
LCR
0.3
#212
TerminalBench Hard
0.3
#115
TAU2
0.8
#95
Output TPS
0.0
#487

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Novita logo
Novita
novita/xiaomimimo/mimo-v2-flash
$0.1$0.3$0.02
OpenRouter logo
OpenRouter
openrouter/xiaomi/mimo-v2-flash
$0.1$0.3$0.01
Vercel AI Gateway logo
Vercel AI Gateway
xiaomi/mimo-v2-flash
$0.1$0.3$0.01

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host MiMo V2 Flash, ranked by cheapest on-demand price. The model needs about 743 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NCC40ads_H100_v5AzureNVIDIA H100752 GB$6.98/hreastus2
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hrus-east-1
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hrwestus3
5 more instances can run MiMo V2 Flash
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MiMo V2.5 Pro1.1M$0.435$0.870Available
MiMo V2.51.1M$0.105$0.280Available
MiMo V2 Pro1.0M$1.00$3.00Deprecated
MiMo V2 Omni262KDeprecated
MiMo V2 Flash262K$0.100$0.300Current
MiMo V2.5 424BAvailable
MiMo V2 OmniAvailable
MiMo V2Available
MiMo V2 Flash ReasoningAvailable
MiMo V2 TTSAvailable
MiMo V2.5 TTSAvailable

Model IDs

mimo-v2-flash
mimo-v2-flash-reasoning
novita/xiaomimimo/mimo-v2-flash
openrouter/xiaomi/mimo-v2-flash
xiaomi-mimo-2-flash
xiaomi/mimo-v2-flash
xiaomimimo/mimo-v2-flash