Hormouz AIHormouzSign in

Xiaomi: MiMo-V2.5: AI model

MiMo-V2.5 is Xiaomi's omnimodal model. Text, image, audio and video in, with a 1M-token context. Served from inside Iran through Hormouz.

Context window:
1,050,000 tokens
Input:
$0.14/1M tokens
Output:
$0.28/1M tokens
Type:
text, audio, image, video
  • Vision
  • Tools
  • Streaming
  • Long context
Good for:Popular for Marketing & SEO · #9Ranks are based on global usage data

Thinking levels:

MiMo-V2.5 is a natively omnimodal model from Xiaomi that accepts text, image, audio and video inputs and returns text. It is tuned for agentic work and aims to deliver strong multimodal perception at a lower inference cost than larger siblings.

Its 1M-token context window can hold complete documents, long conversations and rich task context in a single pass, which makes it a good fit for agent frameworks that need both perception and reasoning.

Through Hormouz, MiMo-V2.5 is served behind an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged. Pricing is usage-based: $0.105 per million input tokens and $0.28 per million output tokens, with no fixed monthly fee.

Hormouz provides stable access to MiMo-V2.5 from inside Iran, with no foreign credit card or circumvention tooling required.

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...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorXiaomi
TypeText, Audio, Image, Video
Context window1,050,000 tokens
Pricing$0.14/M in · $0.28/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

56.8
Coding Index
Better than 65% of models we compared
15.8
Agentic Index
Better than 43% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
84.9%
HLE
Humanity's Last Exam
27.2%
IFBench
Instruction-following
67.1%
AA-LCR
Long-context reasoning
73%
CritPt
Research-level physics reasoning
3.7%
AA Omniscience
Broad factual knowledge accuracy
16.8%
Non-Hallucination
Rate of avoiding fabricated answers
68.1%

Coding

SciCode
Python for scientific computing
43.9%
Terminal-Bench Hard
Agentic coding & terminal use
41.7%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
90.6%
GDPval
Economically valuable tasks
25.2%

Source: Artificial Analysis

3D
Top 28%
1,225Elo
Win rate: 50.8%Avg time: 133s
ASCII Art
Top 59%
1,154Elo
Win rate: 45.4%Avg time: 153s
Code
Top 22%
1,265Elo
Win rate: 53.6%Avg time: 206s
Data Viz
Top 22%
1,258Elo
Win rate: 53.7%Avg time: 156s
Game Dev
Top 23%
1,257Elo
Win rate: 52.6%Avg time: 244s
SVG
Top 35%
1,177Elo
Win rate: 50.5%Avg time: 89.8s
UI Component
Top 26%
1,262Elo
Win rate: 53.8%Avg time: 155s
Website
Top 20%
1,272Elo
Win rate: 53.8%Avg time: 232s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="xiaomi/mimo-v2.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "xiaomi/mimo-v2.5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Xiaomi: MiMo-V2.5 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Xiaomi: MiMo-V2.5 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

What is MiMo-V2.5 and what is it good for?
MiMo-V2.5 is Xiaomi's omnimodal model that reads text, image, audio and video and writes text, tuned for agentic use.
What is the context window of MiMo-V2.5?
It supports up to a 1M-token context window, which suits very long documents and extended multimodal conversations.
How much does MiMo-V2.5 cost?
Pricing is usage-based: $0.105 per million input tokens and $0.28 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access MiMo-V2.5 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to MiMo-V2.5 from inside Iran, with no foreign credit card required.
Is MiMo-V2.5 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.

Updated 2026-10-13