MiMo V2.5 is Xiaomi's language model with a 1.1M context window and up to 131K output tokens, available from 5 providers, starting at $0.14 / 1M input and $0.28 / 1M output. Xiaomi's native omnimodal LLM delivering Pro-level agentic performance at reduced inference cost, with strong multimodal perception across image and video inputs.
Specifications
Canonical IDxiaomi-mimo-2-5
TypeLanguage
StatusDeprecating
CreatorXiaomiXiaomi
Providers
Context Window1.1M tokens
Max Output131K tokens
Input ModalitiesAudioImagePDFTextVideo
Output ModalitiesText
Reasoning Effortsdefault
Parameters311B
HuggingFace Likes359
HuggingFace Downloads (30d)255,837
HuggingFace Downloads (all-time)655,255
Release Date · 6 months ago
Deprecation Date

Capabilities

Input5/5
Text✓
Image✓
Audio✓
Video✓
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
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
DeepInfra logo
DeepInfra
deepinfra/XiaomiMiMo/MiMo-V2.5
$0.4$2.00$0.08
Hugging Face logo
Hugging Face
novita:xiaomimimo/mimo-v2.5
$0.168$0.336N/A
Novita logo
Novita
novita/xiaomimimo/mimo-v2.5
$0.168$0.336$0.0034
OpenRouter logo
OpenRouter
xiaomi/mimo-v2.5
$0.14$0.28$0.0028
Vercel AI Gateway logo
Vercel AI Gateway
xiaomi/mimo-v2.5
$0.14$0.28$0.0028

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host MiMo V2.5, ranked by cheapest on-demand price. The model needs about 746 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
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hr
g4-standard-384GCP8× nvidia-rtx-pro-6000768 GB$36.00/hr
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hr
7 more instances can run MiMo V2.5
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MiMo V2.6 Pro1.1M$0.435$0.870Available
MiMo V2.6 Flash1.1M$0.140$0.280Available
MiMo V2.6 Pro UltraSpeed1.0M$4.35$8.70Available
MiMo V2.5 Pro UltraSpeed1.0M——Available
MiMo V2.51.1M$0.140$0.280Current
MiMo V2.5 Pro1.1M$0.435$0.870Deprecating
MiMo V2 Pro1.0M$1.10$3.30Deprecated
MiMo V2 Omni262K$0.440$2.20Deprecated
MiMo V2 Flash262K$0.110$0.330Deprecated
MiMo V2 Flash Reasoning————Available
MiMo V2.5 424B————Available

Model IDs

deepinfra/XiaomiMiMo/MiMo-V2.5
mimo-v2-5-tts
novita/xiaomimimo/mimo-v2.5
openrouter/xiaomi/mimo-v2.5
xiaomi-mimo-2-5
xiaomi/mimo-v2.5
xiaomimimo/mimo-v2.5
XiaomiMiMo/MiMo-V2.5