Skip to content
LLMs
Xiaomi logo

Xiaomi: MiMo-V2.5

by Xiaomi

Xiaomi: MiMo-V2.5 is a large language model from Xiaomi. It costs $0.140 per million input tokens and $0.280 per million output tokens. Its context window is 1.1M tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weightsaudio inputimage inputvideo input
Input / 1M tokens
$0.140
Output / 1M tokens
$0.280
Cached input / 1M
$0.0028

On repeated prefixes

Context window
1.1M

tokens

Who serves it cheapest

5 hosts serve MiMo-V2.5. Same weights, same API - the price difference is pure margin and routing.

Providers serving Xiaomi: MiMo-V2.5, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GMICloudCheapestfp8$0.119$0.2381.1M-74.8%
DeepInfrafp8$0.133$0.266262K-98.9%
Xiaomifp8$0.140$0.2801.0M-97.6%
StreamLake$0.168$0.3361M-90.7%
Novitafp8$0.168$0.3361.0M-94.4%

The spread between GMICloud and Novita is 1.4× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
22.3
Coding index
56.8
Agentic index
17.4

About MiMo-V2.5

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...

Specifications

Xiaomi: MiMo-V2.5 specifications
Model IDxiaomi/mimo-v2.5
ProviderXiaomi
Context window1.1M tokens
Max output131K tokens
Input modalitiestext, audio, image, video
Output modalitiestext
Knowledge cutoff-
Open weightsYes - XiaomiMiMo/MiMo-V2.5
ReleasedApril 22, 2026

Cheaper alternatives

Models that cost less than MiMo-V2.5 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Xiaomi: MiMo-V2.5 cost?

$0.140 per million input tokens and $0.280 per million output tokens. Cached input reads cost $0.0028 per million tokens.

What is the context window of Xiaomi: MiMo-V2.5?

1.1M tokens, with up to 131K tokens of output per request.

Which provider serves Xiaomi: MiMo-V2.5 cheapest?

GMICloud at $0.119 per million input tokens - 1.4× cheaper than Novita, the most expensive of the 5 hosts serving it.