MiMo-V2.5-Pro

Xiaomi chatreasoningtool_use Long

API ID: xiaomi/mimo-v2.5-pro-20260422

Input Price
$1.00
/1M tokens
Output Price
$3.00
/1M tokens
Cached Input
$0.20
Save 80%

About 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....

💰
Price Ranking
#1040 lowest price among 1240 Chat models

Model Specifications

Context Length
1.1M
Max Output
16k
Release Date
2026-04-22
Capabilities
chat reasoning tool_use
Input Modalities
text
Output Modalities
text

Best For

  • Complex reasoning, math problems, multi-step logic
  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)
  • Simple Q&A (cheaper models available)

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$1.35
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$42.00
/month
1000 tickets/day, ~800 tokens each
Data Analysis Pipeline
$58.50
/month
500 analyses/day, ~2k tokens each

Xiaomi Model Lineup

Compare all models from Xiaomi to find the best fit

Model Input Output Context Capabilities
MiMo-V2.5-Pro Current $1.00 $3.00 1.1M chat reasoning tool_use
MiMo-V2.5 $0.14 $0.28 1.1M audio chat reasoning

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Relace Relace Search
Input: $1.00
Output: $3.00
Context: 256k
Amazon Nova Pro 1.0
Input: $0.80
Output: $3.20
Context: 300k
Nous Research Hermes 4 405B
Input: $1.00
Output: $3.00
Context: 131k
Alibaba Qwen Qwen VL Max
Input: $0.80
Output: $3.20
Context: 131k

🚀 Quick Start

Get started with MiMo-V2.5-Pro API

OpenAI-compatible SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="xiaomi/mimo-v2.5-pro-20260422",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)