Xiaomi: MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship open model for advanced agentic workflows, complex software engineering, and long-horizon task execution. Built on a sparse Mixture-of-Experts architecture with 1.02T total parameters and 42B active parameters, it is optimized for autonomous coding agents, large codebase reasoning, tool use, and multi-step problem solving.

Why It Looks Great

• Flagship Xiaomi MiMo model for complex agentic and software engineering workloads
• Sparse Mixture-of-Experts architecture with 1.02T total parameters and 42B active parameters
• 1M-token context window for long prompts, large codebases, documents, and multi-turn workflows
• Strong fit for autonomous coding agents, long-horizon task execution, and tool-heavy workflows
• Competitive performance on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro
• Designed for token-efficient agent trajectories and extended multi-step execution
• Function calling and tool-use support for agentic application workflows
• Structured output support for JSON responses and schema-constrained generation
• Reasoning controls for tuning latency, quality, and cost per request

Key Features

• Architecture: Sparse Mixture-of-Experts
• Total Parameters: 1.02T
• Active Parameters: 42B
• Context Window: 1,048,576 tokens
• Max Input: 1,032,192 tokens
• Max Output: 16,384 tokens
• Input: Text
• Output: Text
• Vision: Not listed
• Function Calling: Supported
• Structured Outputs: Supported
• Thinking Mode: Supported
• Image Generation: Not listed
• Audio Input: Not listed
• Supported Parameters: frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p

Specifications

Pricing

How to Use

1. Write your prompt - describe the task, provide context, and specify the desired output format.
2. Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: xiaomi/mimo-v2.5-pro

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

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

print(response.choices[0].message.content)

cURL

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

Notes

• Model: xiaomi/mimo-v2.5-pro
• Provider: xiaomi
• Best suited for autonomous coding, complex software engineering, long-horizon reasoning, tool-heavy agent workflows, and large-context text tasks