AI TOOLS RADAR
Submit
All models / XIAOMI
xiaomi logo
xiaomi

Xiaomi: MiMo-V2.5

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,050,000 tokens
Maximum output
131,072 tokens
Architecture
text+image+audio+video->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Cache read
$0.0028
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95

Reasoning

Reasoning required
No
Default parameters
No
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"xiaomi/mimo-v2.5","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textaudioimagevideo
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Available providers

5 providers

Checked: September 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

GMICloud

fp8
Context
1.1M
Maximum output
945K
Input
$0.119
Output
$0.238
Cache read
$0.00255
Cache write
Not provided

DeepInfra

fp8
Context
262K
Maximum output
131K
Input
$0.13
Output
$0.65
Cache read
$0.026
Cache write
Not provided

Xiaomi

fp8
Context
1.0M
Maximum output
131K
Input
$0.14
Output
$0.28
Cache read
$0.0028
Cache write
Not provided

StreamLake

Not provided
Context
1M
Maximum output
128K
Input
$0.168
Output
$0.336
Cache read
$0.00336
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
131K
Input
$0.168
Output
$0.336
Cache read
$0.0034
Cache write
Not provided
xiaomi

4 models

All models
xiaomi logoxiaomi

Xiaomi: MiMo-V2.6-Pro-UltraSpeed

MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...

Context
1.0M
Input
text · image · video · audio
Output
text
Input: $4.35Output: $8.7per 1M tokens
View model details →
xiaomi logoxiaomi

Xiaomi: MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

Context
1.0M
Input
text · image · video · audio
Output
text
Input: $0.14Output: $0.28per 1M tokens
View model details →
xiaomi logoxiaomi

Xiaomi: MiMo-V2.6-Pro

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...

Context
1.0M
Input
text · image · video · audio
Output
text
Input: $0.435Output: $0.87per 1M tokens
View model details →
xiaomi logoxiaomi

Xiaomi: MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

Context
1.1M
Input
text
Output
text
Input: $0.435Output: $0.87per 1M tokens
View model details →