xiaomiChat

Xiaomi: MiMo-V2-Omni

xiaomi/mimo-v2-omni

262KContext Window

66KMax Output

Supported Protocols:reasoninginclude_reasoningmax_tokenstemperaturetop_pstopfrequency_penaltypresence_penaltyresponse_formattoolstool_choice

Online

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step planning, tool use, and code execution - making it well-suited for complex real-world tasks that span modalities, 256K context window.

Capabilities

👁 Vision🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & Reasoningmodels.reasoning

Technical Specs

Input Modality

Text、Audio、Image、Video

Output Modality

Text

Arch

—

Default Temperature

Default Top_P

0.95

Pricing

Pay per use, no monthly fees

Input Token< ¥0.001/1K Token

Output Token< ¥0.001/1K Token

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

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

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