模型定价企业
500+ AI 模型 API，一次搞定，就在 CometAPI
模型 API
开发者
快速入门文档API 仪表板
公司
关于我们企业
资源
AI 模型博客更新日志支持
服务条款隐私政策
© 2026 CometAPI · All rights reserved
Home/Models/Xiaomi/mimo-v2-pro
X

mimo-v2-pro

输入:$0.8/M
输出:$2.4/M
MiMo-V2-Pro 是 Xiaomi 的旗舰基础模型，拥有超过 1T 的总参数量和 1M 的上下文长度，并针对智能体场景进行了深度优化。它对 OpenClaw 等通用智能体框架具有很强的适配性。在标准 PinchBench 和 ClawBench 基准测试中，它跻身全球第一梯队，感知性能接近 Opus 4.6。MiMo-V2-Pro 旨在作为智能体系统的大脑，协调复杂工作流，推动生产工程任务，并可靠地交付结果。
新
商用
Playground
概览
功能亮点
定价
API

Xiaomi MiMo-V2-Pro 的技术规格

项目Xiaomi MiMo-V2-Pro
提供方Xiaomi
模型 IDmimo-v2-pro
模型系列MiMo-V2
模型类型代理式基础模型 / 推理模型
主要输入文本
主要输出文本
上下文窗口最多 1,000,000 个 token
总参数量超过 1 万亿
有效参数420 亿
架构混合注意力 MoE
发布时间窗口2026 年 3 月
基准信号Artificial Analysis Intelligence Index：全球第 #8；PinchBench：全球第 #3

什么是 Xiaomi MiMo-V2-Pro？

Xiaomi MiMo-V2-Pro 是 Xiaomi 面向真实世界代理式工作的 MiMo 系列旗舰模型。Xiaomi 将其描述为支撑代理系统的模型，能够编排复杂工作流、处理生产级工程任务，并在长时间、多步骤的作业中保持可靠运行。

Xiaomi MiMo-V2-Pro 的主要特性

  • 以代理为先的设计： 面向工作流、工具调用和任务执行构建，而非仅限于聊天式回答。
  • 超长上下文： 支持最多 100 万 token，适用于超大代码库、长文档和延展的任务轨迹。
  • 大规模 MoE： 总参数超过 1T，有效参数 42B，并配合混合注意力以提升效率。
  • 强大的编码能力： Xiaomi 称其在内部评测中的编码性能超过 Claude 4.6 Sonnet。
  • 可靠的工具调用： Xiaomi 强调在代理脚手架中的工具调用稳定性与准确性有所提升。
  • 框架友好： Xiaomi 表示该模型正与 OpenClaw、OpenCode、KiloCode、Blackbox 和 Cline 等代理框架配合使用。

Xiaomi MiMo-V2-Pro 的基准表现

Xiaomi 在 2026 年 3 月发布的材料中，将 MiMo-V2-Pro 列为 Artificial Analysis Intelligence Index 全球第 #8，PinchBench 平均任务完成率全球第 #3。Xiaomi 还报告其 ClawEval 得分为 61.5，称之在该基准上接近 Claude Opus 4.6，且领先于 GPT-5.2。

Xiaomi MiMo-V2-Pro 对比 MiMo-V2-Flash 与 MiMo-V2-Omni

模型最适用于关键差异
MiMo-V2-Flash快速、高效的文本推理为效率调优的较小 MoE 模型；总参数 309B / 有效参数 15B
MiMo-V2-Pro深度代理式推理与长工作流具备 100 万 token 上下文与 1T+ 参数的旗舰文本代理模型
MiMo-V2-Omni多模态理解与执行为多模态代理任务统一文本、视觉与语音

何时使用 Xiaomi MiMo-V2-Pro

当你需要长上下文推理、多步骤代理编排、代码密集的工作流或类生产环境的任务执行时，使用 MiMo-V2-Pro。与 MiMo-V2-Flash 相比，当深度比速度更重要时它更合适；与 MiMo-V2-Omni 相比，当你的工作负载以文本为先而非多模态时它更合适。

限制

MiMo-V2-Pro 定位为以文本为先的代理模型，因此原生多模态工作更适合由 MiMo-V2-Omni 处理。与任何以基准为导向的模型一样，实际结果仍取决于提示设计、工具质量以及代理如何接入你的技术栈。

常见问题

What makes Xiaomi MiMo-V2-Pro API different from MiMo-V2-Flash?

MiMo-V2-Pro is Xiaomi’s flagship agentic model for deeper workflows, while MiMo-V2-Flash is the efficiency-focused sibling. Xiaomi says Pro is built for real-world agent tasks, with over 1 trillion total parameters, 42 billion active parameters, and a 1 million-token context window.

How large is the Xiaomi MiMo-V2-Pro API context window?

Xiaomi says MiMo-V2-Pro supports up to 1 million tokens of context. That is the key spec to know if you need to keep huge codebases, long documents, or extended task histories in one run.

Can Xiaomi MiMo-V2-Pro API handle coding and multi-step agent workflows?

Yes. Xiaomi positions MiMo-V2-Pro as a model for production engineering tasks, complex workflows, and agent scaffolds. The company also says its coding ability surpasses Claude 4.6 Sonnet in internal evaluations.

When should I use Xiaomi MiMo-V2-Pro API instead of MiMo-V2-Omni?

Use MiMo-V2-Pro when your workload is text-first and centered on reasoning, code, or tool orchestration. Use MiMo-V2-Omni when you need native multimodal understanding across text, vision, and speech.

How does Xiaomi MiMo-V2-Pro API compare with Claude Opus 4.6 and GPT-5.2?

Xiaomi reports MiMo-V2-Pro at 61.5 on ClawEval, compared with 66.3 for Claude Opus 4.6 and 50.0 for GPT-5.2 on the same chart. Xiaomi also says Pro is close to Opus 4.6 on general agent performance and ranks #8 globally on the Artificial Analysis Intelligence Index.

What are the known limitations of Xiaomi MiMo-V2-Pro API?

MiMo-V2-Pro is optimized for agentic text workflows, so it is not the family member to choose for native multimodal input. For image, video, or speech-heavy jobs, Xiaomi’s MiMo-V2-Omni is the better match.

How do I integrate Xiaomi MiMo-V2-Pro API with an OpenAI-compatible client?

OpenClaw documents the Xiaomi provider as OpenAI-compatible, which means you can use an OpenAI-style client with Xiaomi’s base URL and model ID. In practice, that makes it straightforward to swap in mimo-v2-pro as the model name while keeping your existing chat-completions flow.

Is Xiaomi MiMo-V2-Pro API suitable for long document analysis?

Yes. The 1 million-token context window makes MiMo-V2-Pro a strong fit for very long source documents, support tickets, policy packs, or repository-scale analysis where smaller-context models would truncate too early.

mimo-v2-pro 的定价

查看 mimo-v2-pro 的竞争性定价，满足不同预算与使用需求，灵活方案确保随需求扩展。
Comet 价格 (USD / M Tokens)官方定价 (USD / M Tokens)折扣
输入:$0.8/M
输出:$2.4/M
输入:$1/M
输出:$3/M
-20%

mimo-v2-pro 的示例代码与 API

获取完整示例代码与 API 资源，简化 mimo-v2-pro 的集成流程，我们提供逐步指导，助你发挥模型潜能。
POST
/v1/chat/completions
POST
/v1/messages
Python
JavaScript
Curl
from openai import OpenAI
import os

# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"

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

stream = client.chat.completions.create(
    model="mimo-v2-pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain the Monty Hall problem step by step."},
    ],
    stream=True,
    extra_body={"thinking": {"type": "enabled"}},
)

thinking = False
for chunk in stream:
    delta = chunk.choices[0].delta
    reasoning = (delta.model_extra or {}).get("reasoning_content")
    if reasoning:
        if not thinking:
            print("<thinking>")
            thinking = True
        print(reasoning, end="", flush=True)
    elif thinking and delta.content:
        print("
</thinking>
")
        thinking = False
        print(delta.content, end="", flush=True)
    elif delta.content:
        print(delta.content, end="", flush=True)

Python Code Example

from openai import OpenAI
import os

# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"

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

stream = client.chat.completions.create(
    model="mimo-v2-pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain the Monty Hall problem step by step."},
    ],
    stream=True,
    extra_body={"thinking": {"type": "enabled"}},
)

thinking = False
for chunk in stream:
    delta = chunk.choices[0].delta
    reasoning = (delta.model_extra or {}).get("reasoning_content")
    if reasoning:
        if not thinking:
            print("<thinking>")
            thinking = True
        print(reasoning, end="", flush=True)
    elif thinking and delta.content:
        print("\n</thinking>\n")
        thinking = False
        print(delta.content, end="", flush=True)
    elif delta.content:
        print(delta.content, end="", flush=True)

JavaScript Code Example

import OpenAI from "openai";

// Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
const api_key = process.env.COMETAPI_KEY || "<YOUR_COMETAPI_KEY>";

const client = new OpenAI({ apiKey: api_key, baseURL: "https://api.cometapi.com/v1" });

const stream = await client.chat.completions.create({
  model: "mimo-v2-pro",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain the Monty Hall problem step by step." },
  ],
  stream: true,
  thinking: { type: "enabled" },
});

let thinking = false;
for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta ?? {};
  const reasoning = delta.reasoning_content;
  if (reasoning) {
    if (!thinking) { process.stdout.write("<thinking>\n"); thinking = true; }
    process.stdout.write(reasoning);
  } else if (thinking && delta.content) {
    process.stdout.write("\n</thinking>\n\n");
    thinking = false;
    process.stdout.write(delta.content);
  } else if (delta.content) {
    process.stdout.write(delta.content);
  }
}

Curl Code Example

# Get your CometAPI key from https://api.cometapi.com/console/token
# Export it as: export COMETAPI_KEY="your-key-here"

curl https://api.cometapi.com/v1/chat/completions \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain the Monty Hall problem step by step."}
    ],
    "stream": true,
    "thinking": {"type": "enabled"}
  }'