Hormouz AIHormouzSign in

Xiaomi: MiMo-V2.5-Pro: AI model

MiMo-V2.5-Pro is Xiaomi's flagship agentic model with a 1M-token context, built for complex software engineering and long-horizon tasks, via Hormouz.

Context window:
1,050,000 tokens
Input:
$0.43/1M tokens
Output:
$0.87/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context

Thinking levels:

MiMo-V2.5-Pro is Xiaomi's flagship model, aimed at general agentic capability, complex software engineering and long-horizon tasks that can span many tool calls. It is designed to work through problems that would otherwise take human experts a long time.

With a context window of up to 1M tokens, it fits naturally into agent frameworks that keep large amounts of state, code and history in context across a single run.

Through Hormouz, MiMo-V2.5-Pro 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: $0.435 per million input tokens and $0.87 per million output tokens, with no fixed monthly fee.

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

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....

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-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorXiaomi
TypeText
Context window1,050,000 tokens
Pricing$0.43/M in · $0.87/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

26
Intelligence Index
Better than 51% of models we compared
60.2
Coding Index
Better than 70% of models we compared
21.3
Agentic Index
Better than 52% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
86.6%
HLE
Humanity's Last Exam
35.7%
IFBench
Instruction-following
79.9%
AA-LCR
Long-context reasoning
79.7%
CritPt
Research-level physics reasoning
4%
AA Omniscience
Broad factual knowledge accuracy
22.4%
Non-Hallucination
Rate of avoiding fabricated answers
75.3%

Coding

SciCode
Python for scientific computing
50.6%
Terminal-Bench Hard
Agentic coding & terminal use
43.2%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
94.2%
GDPval
Economically valuable tasks
31.2%

Source: Artificial Analysis

3D
Top 23%
1,254Elo
Win rate: 54.2%Avg time: 215s
ASCII Art
Top 50%
1,163Elo
Win rate: 46%Avg time: 130s
Code
Top 19%
1,272Elo
Win rate: 51.9%Avg time: 309s
Data Viz
Top 21%
1,266Elo
Win rate: 50.5%Avg time: 252s
Game Dev
Top 21%
1,272Elo
Win rate: 53.4%Avg time: 329s
SVG
Top 34%
1,178Elo
Win rate: 48.1%Avg time: 126s
UI Component
Top 26%
1,254Elo
Win rate: 50.9%Avg time: 279s
Website
Top 18%
1,275Elo
Win rate: 51.2%Avg time: 340s

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-pro",
    "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-pro",
    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-pro",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Xiaomi: MiMo-V2.5-Pro 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-Pro 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-Pro and what is it good for?
MiMo-V2.5-Pro is Xiaomi's flagship agentic model for software engineering and long, multi-step tasks.
What is the context window of MiMo-V2.5-Pro?
It supports up to a 1M-token context window, well suited to large codebases and long agent runs.
How much does MiMo-V2.5-Pro cost?
Pricing is usage-based: $0.435 per million input tokens and $0.87 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access MiMo-V2.5-Pro from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to MiMo-V2.5-Pro from inside Iran, with no foreign credit card required.
Is MiMo-V2.5-Pro 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