# Xiaomi MiMo API Open Platform

> Xiaomi MiMo API Open Platform provides high-performance inference services for Xiaomi's AI models, compatible with OpenAI and Anthropic API formats.

This platform offers comprehensive API documentation, integration guides, and detailed update logs for Xiaomi-related AI models. It is designed to empower developers to build and deploy next-generation intelligent applications and agents with ease.



--- DOCUMENT: First API Call ---
URL: https://platform.xiaomimimo.com/static/docs/quick-start/first-api-call.md

# First API Call

## Supported API Types

Xiaomi MiMo API Open Platform is compatible with OpenAI API and Anthropic API formats. You can use existing SDKs to access model inference services.

## Preparation Before Calling

### Log in to Xiaomi MiMo API Open Platform

Currently, the platform only provides personal account login. You need to use a Xiaomi account to log in. If you already have a Xiaomi account, you can log in directly. If you don't have a Xiaomi account, you can visit the [Console](https://platform.xiaomimimo.com/#/console/usage) to register, or register in advance at [id.mi.com](https://id.mi.com/).

### Get API Key

Create an API Key in [Console-API Keys](https://platform.xiaomimimo.com/#/console/api-keys). Please keep your API Key safe to avoid leakage that may result in quota theft. It is recommended to configure the API Key in environment variables.

## Quick Integration Examples

You can copy the following API example code and replace the API Key value to quickly make calls.

The following system prompts are HIGHTLY recommended, please choose from English and Chinese version.

> Chinese version
>
> ```json
> 你是MiMo（中文名称也是MiMo），是小米公司研发的AI智能助手。
> 今天的日期：{date} {week}，你的知识截止日期是2024年12月。
> ```

> English version
>
> ```json
> You are MiMo, an AI assistant developed by Xiaomi.
> Today's date: {date} {week}. Your knowledge cutoff date is December 2024.
> ```

### Python SDK Examples

#### OpenAI API Format Example

Install the OpenAI Python SDK by running the following command:

```shell
# If the run fails, you can replace pip with pip3 and run again
pip install -U openai
```

Call the API:

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5-pro",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "please introduce yourself"
        }
    ],
    max_completion_tokens=1024,
    temperature=1.0,
    top_p=0.95,
    stream=False,
    stop=None,
    frequency_penalty=0,
    presence_penalty=0
)

print(completion.model_dump_json())
```

#### Anthropic API Format Example

Install the Anthropic Python SDK by running the following command:

```shell
# If the run fails, you can replace pip with pip3 and run again
pip install -U anthropic
```

Call the API:

```python
import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/anthropic"
)

message = client.messages.create(
    model="mimo-v2.5-pro",
    max_tokens=1024,
    system="You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "please introduce yourself"
                }
            ]
        }
    ],
    top_p=0.95,
    stream=False,
    temperature=1.0,
    stop_sequences=None
)

print(message.content)
```

### Curl Examples

#### OpenAI API Format Example

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "please introduce yourself"
        }
    ],
    "max_completion_tokens": 1024,
    "temperature": 1.0,
    "top_p": 0.95,
    "stream": false,
    "stop": null,
    "frequency_penalty": 0,
    "presence_penalty": 0
}'
```

#### Anthropic API Format Example

```bash
curl --location --request POST 'https://api.xiaomimimo.com/anthropic/v1/messages' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "max_tokens": 1024,
    "system": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "please introduce yourself"
                }
            ]
        }
    ],
    "top_p": 0.95,
    "stream": false,
    "temperature": 1.0,
    "stop_sequences": null
}'
```

### Make Multi-turn Tool Calls in Thinking Mode

During the multi-turn tool calls process in thinking mode, the model returns a `reasoning_content` field alongside `tool_calls`. To continue the conversation, it is recommended to keep all previous `reasoning_content` in the `messages` array for each subsequent request to achieve the best performance.

The requested example is as follows:

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "messages": [
        {
            "role": "assistant",
            "content": "Hello! I am MiMo.",
            "reasoning_content": "Okay, the user just asked me to introduce myself. That is a pretty straightforward request, but I should think about why they are asking this."
        },
        {
            "role": "user",
            "content": "What is the weather like in Hebei?"
        }
    ],
    "model": "mimo-v2.5-pro",
    "max_completion_tokens": 1024,
    "temperature": 1.0,
    "stream": false,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "get_current_weather",
                "description": "Get the current weather in a given location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA"
                        },
                        "unit": {
                            "type": "string",
                            "enum": [
                                "celsius",
                                "fahrenheit"
                            ]
                        }
                    },
                    "required": [
                        "location"
                    ]
                }
            }
        }
    ],
    "tool_choice": "auto"
}'
```

## Check Usage Information

On the [Usage Information](https://platform.xiaomimimo.com/#/console/usage) page, you can view and export detailed data of your account's model Token usage and request counts by date.


--- DOCUMENT: Model Hyperparameters ---
URL: https://platform.xiaomimimo.com/static/docs/quick-start/model-hyperparameters.md

# Model Hyperparameters

`temperature` represents the sampling temperature. Higher values (such as 0.8) will make the output more random, while lower values (such as 0.2) will make the output more deterministic.

`top_p` represents the probability threshold for nucleus sampling, used to control the diversity of text generated by the model. The higher the value, the greater the diversity of the generated text. 

<div className='mdx-highlight'>

In thinking mode, the `mimo-v2.5-pro` and `mimo-v2.5` models do not support customizing the `temperature` parameter. Even if this parameter is passed in, it will be forcibly overridden and take effect with the model's recommended default value of `1.0`.

</div>

The default values and parameter ranges of `temperature` and `top_p` for different models are as follows:

<table>
<colgroup>
<col style="width: 244px" />
<col />
<col style="width: 225px" />
</colgroup>
<thead>
<tr>
<th>**Model Name**</th>
<th>**temperature**</th>
<th>**top_p**</th>
</tr>
</thead>
<tbody>
<tr>
<td>`mimo-v2.5-pro`<br />`mimo-v2-pro`</td>
<td><ul><li>Default value: 1.0</li><li>Range: [0, 1.5]</li></ul></td>
<td><ul><li>Default value: 0.95</li><li>Range: [0.01, 1.0]</li></ul></td>
</tr>
<tr>
<td>`mimo-v2.5`<br />`mimo-v2-omni`</td>
<td><ul><li>Default value: 1.0</li><li>Range: [0, 1.5]</li></ul></td>
<td><ul><li>Default value: 0.95</li><li>Range: [0.01, 1.0]</li></ul></td>
</tr>
<tr>
<td>`mimo-v2.5-tts`<br />`mimo-v2.5-tts-voicedesign`<br />`mimo-v2.5-tts-voiceclone`<br />`mimo-v2-tts`</td>
<td><ul><li>Default value: 0.6</li><li>Range: [0, 1.5]</li></ul></td>
<td><ul><li>Default value: 0.95</li><li>Range: [0.01, 1.0]</li></ul></td>
</tr>
<tr>
<td>`mimo-v2-flash`</td>
<td><ul><li>Default value: 0.3</li><li>Range: [0, 1.5]</li></ul></td>
<td><ul><li>Default value: 0.95</li><li>Range: [0.01, 1.0]</li></ul></td>
</tr>
</tbody>
</table>

We recommend that you set parameter values according to task type, and you can refer to the following recommended values.

The recommended values for the `mimo-v2-flash` model are as follows:

<table>
<colgroup>
<col style="width: 187px" />
<col style="width: 136px" />
<col />
</colgroup>
<thead>
<tr>
<th>**Task Type**</th>
<th>**temperature**</th>
<th>**top_p**</th>
</tr>
</thead>
<tbody>
<tr>
<td>Vibe Coding</td>
<td>0.3</td>
<td>0.95</td>
</tr>
<tr>
<td>Function Call</td>
<td>0.3</td>
<td>0.95</td>
</tr>
<tr>
<td>General Conversation</td>
<td>0.8</td>
<td>0.95</td>
</tr>
<tr>
<td>Creative Writing</td>
<td>0.8</td>
<td>0.95</td>
</tr>
<tr>
<td>WebDev</td>
<td>0.8</td>
<td>0.95</td>
</tr>
<tr>
<td>Mathematical Reasoning</td>
<td>1</td>
<td>0.95</td>
</tr>
</tbody>
</table>

The recommended values for the `temperature` and `top_p` parameters of the `mimo-v2.5-pro`, `mimo-v2.5`, `mimo-v2-pro`, and `mimo-v2-omni` models for the above tasks are 1 and 0.95, respectively.


--- DOCUMENT: Error Codes ---
URL: https://platform.xiaomimimo.com/static/docs/quick-start/error-codes.md

# Error Codes

When using API calls to the MiMo model, common error codes and solutions are as follows:

<table>
<colgroup>
<col />
<col style="width: 465px" />
<col style="width: 564px" />
</colgroup>
<thead>
<tr>
<th>**Error Code**</th>
<th>**Causes**</th>
<th>**Solutions**</th>
</tr>
</thead>
<tbody>
<tr>
<td>400 - Invalid Format</td>
<td>Invalid request format</td>
<td><ul><li>Check if the JSON format is correct</li><li>Check if all required parameters are included</li><li>Check if parameter values are within the valid range</li><li>Check if the message format meets the interface requirements</li><li>Check if the model exists</li><li>Check if the fields are entered correctly</li><li>Check multimodal file input for compliance with format, size and other restrictions.</li><li>Check if multimodal file input is publicly accessible</li><li>In multi-turn conversations under thinking mode, the `reasoning_content` field must be fully passed back to the API.</li></ul></td>
</tr>
<tr>
<td>401 - Authentication Fails</td>
<td><ul><li>Missing or invalid API Key, or incorrect Authorization request header format</li><li>API Key that mixes Token Plan and Pay-as-you-go API</li></ul></td>
<td><ul><li>Check if the API key and request header format are correct</li><li>Check if a dedicated Base URL and API Key are used when using the Token Plan</li></ul></td>
</tr>
<tr>
<td>402 - Insufficient Balance</td>
<td>Insufficient account balance</td>
<td>Check your account balance and recharge in a timely manner</td>
</tr>
<tr>
<td>403 - Forbidden Access</td>
<td>The service is currently not available in the current region, or the API Key has been restricted by risk control</td>
<td>Create a new API Key and pay attention to the security of input content</td>
</tr>
<tr>
<td>404 - Not Found</td>
<td>The requested endpoint or model does not support image input capability</td>
<td>Verify that the model / endpoint being used supports image input capability</td>
</tr>
<tr>
<td>421 - Content Filter</td>
<td>Content moderation and blocking</td>
<td>Avoid entering unsafe or sensitive content</td>
</tr>
<tr>
<td>429 - Too Many Requests</td>
<td>Requests are too frequent, or the quota of Token Plan has been exhausted</td>
<td><ul><li>Implement exponential backoff and retry logic, or reduce the request frequency</li><li>Upgrade the Token Plan package or switch to pay-as-you-go API</li></ul></td>
</tr>
<tr>
<td>500 - Server Error</td>
<td>Our server encounters an issue</td>
<td>Please try again later, or contact us for resolution</td>
</tr>
<tr>
<td>503 - Server Overloaded</td>
<td>The server is overloaded due to high traffic</td>
<td>Please try again later</td>
</tr>
</tbody>
</table>


--- DOCUMENT: Pricing and Rate Limits ---
URL: https://platform.xiaomimimo.com/static/docs/pricing.md

# Pricing and Rate Limits

The platform sets a model concurrency limit for accounts. When server load is high, response delays or 429 errors may occur. For details on the RPM and TPM limits of each model, please refer to the following table. We recommend that you plan your request frequency reasonably. 

> RPM: Requests Per Minute, which refers to the maximum number of requests you can initiate to us within one minute, and is the sum of the number of requests from all API Keys of a single account when invoking a certain model
>
> TPM: Tokens Per Minute, which refers to the maximum number of Tokens you can interact with us within one minute, and is the sum of the number of requested Tokens from all API Keys of a single account when invoking a certain model

## Pricing 

### Domestic Pricing of the Model

<table>
<colgroup>
<col style="width: 259px" />
<col style="width: 152px" />
<col style="width: 152px" />
<col style="width: 103px" />
<col style="width: 145px" />
<col style="width: 154px" />
<col />
</colgroup>
<thead>
<tr>
<th></th>
<th colspan="3">Input ≤ 256K</th>
<th colspan="3">Input 256K - 1M</th>
</tr>
</thead>
<tbody>
<tr>
<td></td>
<td>Input (Cache Hit)</td>
<td>Input (Cache Miss)</td>
<td>Output</td>
<td>Input (Cache Hit)</td>
<td>Input (Cache Miss)</td>
<td>Output</td>
</tr>
<tr>
<td>`mimo-v2.5-pro`<br />`mimo-v2-pro`</td>
<td>¥1.40</td>
<td>¥7.00</td>
<td>¥21.00</td>
<td>¥2.80</td>
<td>¥14.00</td>
<td>¥42.00</td>
</tr>
<tr>
<td>`mimo-v2.5`</td>
<td>¥0.56</td>
<td>¥2.80</td>
<td>¥14.00</td>
<td>¥1.12</td>
<td>¥5.60</td>
<td>¥28.00</td>
</tr>
<tr>
<td>`mimo-v2-omni`</td>
<td>¥0.56</td>
<td>¥2.80</td>
<td>¥14.00</td>
<td>—</td>
<td>—</td>
<td>—</td>
</tr>
<tr>
<td>`mimo-v2-flash`</td>
<td>¥0.07</td>
<td>¥0.70</td>
<td>¥2.10</td>
<td>—</td>
<td>—</td>
<td>—</td>
</tr>
<tr>
<td>`mimo-v2.5-tts`<br />`mimo-v2.5-tts-voiceclone`<br />`mimo-v2.5-tts-voicedesign`<br />`mimo-v2-tts`</td>
<td>Limited-time free</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
</tbody>
</table>

> Note: Cache writing is currently free of charge for a limited time; — indicates that the context limit of this model is 256K, and this range does not apply. Unit: yuan / 1M tokens.

### Overseas Pricing of the Model 

<table>
<colgroup>
<col style="width: 260px" />
<col style="width: 152px" />
<col style="width: 145px" />
<col />
<col style="width: 152px" />
<col style="width: 172px" />
<col style="width: 110px" />
</colgroup>
<thead>
<tr>
<th></th>
<th colspan="3">Input ≤ 256K</th>
<th colspan="3">Input 256K - 1M</th>
</tr>
</thead>
<tbody>
<tr>
<td></td>
<td>Input (Cache Hit)</td>
<td>Input (Cache Miss)</td>
<td>Output</td>
<td>Input (Cache Hit)</td>
<td>Input (Cache Miss)</td>
<td>Output</td>
</tr>
<tr>
<td>`mimo-v2.5-pro`<br /> `mimo-v2-pro`</td>
<td>$0.20</td>
<td>$1.00</td>
<td>$3.00</td>
<td>$0.40</td>
<td>$2.00</td>
<td>$6.00</td>
</tr>
<tr>
<td>`mimo-v2.5`</td>
<td>$0.08</td>
<td>$0.40</td>
<td>$2.00</td>
<td>$0.16</td>
<td>$0.80</td>
<td>$4.00</td>
</tr>
<tr>
<td>`mimo-v2-omni`</td>
<td>$0.08</td>
<td>$0.40</td>
<td>$2.00</td>
<td>—</td>
<td>—</td>
<td>—</td>
</tr>
<tr>
<td>`mimo-v2-flash`</td>
<td>$0.01</td>
<td>$0.10</td>
<td>$0.30</td>
<td>—</td>
<td>—</td>
<td>—</td>
</tr>
<tr>
<td>`mimo-v2.5-tts`<br />`mimo-v2.5-tts-voiceclone`<br />`mimo-v2.5-tts-voicedesign`<br />`mimo-v2-tts`</td>
<td>Limited-time free</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td></td>
</tr>
</tbody>
</table>

> Note: Cache writing is currently free of charge for a limited time; — indicates that the context limit of this model is 256K, and this range does not apply. Unit: $ / 1M tokens.

### Pricing for Network Service Plugins 

<table>
<colgroup>
<col />
<col />
<col style="width: 444px" />
</colgroup>
<thead>
<tr>
<th>Service Item</th>
<th>Price</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td>Domestic Internet Connectivity Service</td>
<td>¥25 / 1000 times</td>
<td>Includes web search and web parsing, used for domestic regional networked search of relevant content</td>
</tr>
<tr>
<td>Overseas Internet Connectivity Service</td>
<td>$5 / 1000 times</td>
<td>Includes web search and web parsing, used for networked search of relevant content in overseas regions</td>
</tr>
</tbody>
</table>

## Model Details

### Pro Series

<table>
<colgroup>
<col />
<col style="width: 612px" />
</colgroup>
<thead>
<tr>
<th>**Model Name**</th>
<th>`mimo-v2.5-pro`, `mimo-v2-pro`</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Category**</td>
<td>Text Generation - General Large Language Model</td>
</tr>
<tr>
<td>**Context Length**</td>
<td>1 M</td>
</tr>
<tr>
<td>**Maximum Output Length**</td>
<td>128 K</td>
</tr>
<tr>
<td>**Model Capability**</td>
<td>Text generation, deep thinking, streaming output, function call, structured output, internet search</td>
</tr>
<tr>
<td>**Flow Control**</td>
<td>RPM: 100<br />TPM: 10 M</td>
</tr>
</tbody>
</table>

### Omni Series

<table>
<colgroup>
<col />
<col style="width: 296px" />
<col style="width: 323px" />
</colgroup>
<thead>
<tr>
<th>**Model Name**</th>
<th>`mimo-v2.5`</th>
<th>`mimo-v2-omni`</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Category**</td>
<td>Text Generation - Full Modal Understanding Model</td>
<td>Text Generation - Full Modal Understanding Model</td>
</tr>
<tr>
<td>**Context Length**</td>
<td>1 M</td>
<td>256 K</td>
</tr>
<tr>
<td>**Maximum Output Length**</td>
<td>128 K</td>
<td>128 K</td>
</tr>
<tr>
<td>**Model Capability**</td>
<td colspan="2">Full-modal understanding, in-depth thinking, streaming output, function call, structured output, and internet search</td>
</tr>
<tr>
<td>**Flow Control**</td>
<td colspan="2">RPM: 100<br />TPM: 10 M</td>
</tr>
</tbody>
</table>

### TTS Series

<table>
<colgroup>
<col />
<col style="width: 207px" />
<col style="width: 236px" />
<col style="width: 261px" />
<col style="width: 237px" />
</colgroup>
<thead>
<tr>
<th>**Model Name**</th>
<th>`mimo-v2.5-tts`</th>
<th>`mimo-v2.5-tts-voiceclone`</th>
<th>`mimo-v2.5-tts-voicedesign`</th>
<th>`mimo-v2-tts`</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Category**</td>
<td>Speech Synthesis Model</td>
<td>Speech Synthesis Model</td>
<td>Speech Synthesis Model</td>
<td>Speech Synthesis Model</td>
</tr>
<tr>
<td>**Context Length**</td>
<td>8 K</td>
<td>8 K</td>
<td>8 K</td>
<td>8 K</td>
</tr>
<tr>
<td>**Maximum Output Length**</td>
<td>8 K</td>
<td>8 K</td>
<td>8 K</td>
<td>8 K</td>
</tr>
<tr>
<td>**Model Capability**</td>
<td>Speech Synthesis</td>
<td>Timbre Cloning</td>
<td>Timbre Design</td>
<td>Speech Synthesis</td>
</tr>
<tr>
<td>**Flow Control**</td>
<td colspan="4">RPM: 100<br />TPM: 10 M</td>
</tr>
</tbody>
</table>

### MiMo-V2-Flash

<table>
<colgroup>
<col />
<col style="width: 659px" />
</colgroup>
<thead>
<tr>
<th>**Model Name**</th>
<th>`mimo-v2-flash`</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Category**</td>
<td>Text Generation - General Large Language Model</td>
</tr>
<tr>
<td>**Context Length**</td>
<td>256 K</td>
</tr>
<tr>
<td>**Maximum Output Length**</td>
<td>64 K</td>
</tr>
<tr>
<td>**Model Capability**</td>
<td>Text generation, deep thinking, streaming output, function call, structured output, internet search</td>
</tr>
<tr>
<td>**Flow Control**</td>
<td>RPM: 100<br />TPM: 10 M</td>
</tr>
</tbody>
</table>


--- DOCUMENT: Xiaomi MiMo-V2.5 series open-sourced & Orbit 100 trillion token plan launched ---
URL: https://platform.xiaomimimo.com/static/docs/news/v2.5-open-sourced.md

# Xiaomi MiMo-V2.5 series open-sourced & Orbit 100 trillion token plan launched

Today, we officially open source the Xiaomi MiMo-V2.5 series, which uses the MIT license, supports commercial inference deployment and secondary training, and requires no additional authorization.

## Open protocol, fully open source

The MiMo V2.5 series models began public testing on April 23rd. We thank all users for their enthusiastic feedback and encouragement during this period.

This series includes two models, both supporting a 1-million-token context window:

- MiMo-V2.5-Pro: Designed for complex task scenarios, deeply optimized for Agent and Coding applications. It ranks first among open-source models globally on the GDPVal-AA and ClawEval leaderboards.

- MiMo-V2.5: A native full-modal model supporting text, image, video, and audio understanding, with powerful Agent capabilities.

![图片](https://platform.xiaomimimo.com/static/VZxrbdHSUoqx63x5RtycLBnznfe.cb0a305d.png)

We deeply understand that the true value of a model does not lie in its ranking on leaderboards, but rather in its ability to efficiently assist developers in solving real-world problems. On the Claw-Eval leaderboard, MiMo V2.5 ranks at the optimal frontier of task completion rate and Token efficiency 

![图片](https://platform.xiaomimimo.com/static/BhnNbzCq5oBDXCxWPOcc9umtnPe.aeb7e48a.jpeg)

After undergoing refinement and verification during the public beta phase, this series has further improved in terms of intelligence level and stability, and has reached the standard for release. 

Today, we are releasing the model weights of the MiMo V2.5 series to global developers under the MIT License, and at the same time, we are collaborating with chip manufacturers and inference frameworks to provide adaptation code, hoping to contribute to the open-source community and developer ecosystem.

The weights of both models (including the Base model) have been fully open-sourced under the permissive MIT license, allowing free commercial use, secondary training, and fine-tuning without additional authorization.

> Model weight collection: [https://huggingface.co/collections/XiaomiMiMo/mimo-v25](https://huggingface.co/collections/XiaomiMiMo/mimo-v25)

For more details, refer to the model Blog:

https://mimo.xiaomi.com/index#blog

## MiMo Orbit Program

We believe that the value of open source lies not only in the public disclosure of weights, but more importantly, in the co-construction of the ecosystem. 

To this end, we are officially launching the MiMo Orbit Program. 

The MiMo Orbit plan is divided into two parts, namely the " **Creator Trillion Token Incentive Plan"** for AI builders and the " **Agent Ecosystem Co-construction Plan** " for Agent framework teams.

### Creator Trillion Token Incentive Program 

![图片](https://platform.xiaomimimo.com/static/QzbXbqNIlou0rYxl8NjcZgQKn9f.49f56c9c.png)

Xiaomi MiMo will distribute free Tokens to global users, with a total of **100 trillion (100T) Tokens** to be distributed within 30 days, and the distribution will end once all Tokens are given out.

This event adopts an application system, and users whose applications are approved will receive the Max-tier Token Plan at most, which includes 1.6 billion Credits and is worth 659 yuan. 

**Event Time**

From 00:00 on April 28, 2026, to 00:00 on May 28, 2026, Beijing Time

**Participation Method**

You can fill out the application via the following link or QR code. We will carefully evaluate each application material and match corresponding benefits based on your usage scenarios and needs. Successful applicants will receive our follow-up emails. 

Application URL: [100t.xiaomimimo.com](http://100t.xiaomimimo.com)

Application QR Code: 

![图片](https://platform.xiaomimimo.com/static/ZDwPbXuHSoURfdxMjW7cxqnmnMe.c8e38d08.png)

### Agent Ecosystem Co-construction Initiative

Xiaomi MiMo provides specialized support to the global Agent Framework Team. We will offer limited-time free support for the Agent Framework, enabling your users to access and experience the MiMo series of models with zero barriers. 

During the model ecosystem adaptation process, we have carried out in-depth cooperation with Agent framework vendors such as OpenCode, Hermes Agent, and KiloCode, and received a great deal of positive feedback and recognition.

<table>
<colgroup>
<col style="width: 215px" />
<col />
<col style="width: 209px" />
<col style="width: 203px" />
</colgroup>
<thead>
<tr>
<th>![图片](https://platform.xiaomimimo.com/static/BFeBbuvrVoxBXfxmpkPcSSASnCx.40e64d37.png)</th>
<th>![图片](https://platform.xiaomimimo.com/static/GByLbKMNGoOqutxZcybcY9D8nOt.eda23ad9.png)</th>
<th>![图片](https://platform.xiaomimimo.com/static/GjbfbWQbho1sE2xayLIc3TCunSd.116ef429.png)</th>
<th>![图片](https://platform.xiaomimimo.com/static/WlzwbOfDXorn7OxU45UczO0xnae.4621aefb.png)</th>
</tr>
</thead>
<tbody>
</tbody>
</table>

We welcome like-minded Agent framework developers and manufacturers to contact us：[ business-mimo@xiaomi.com ](mailto:business-mimo@xiaomi.com)

## Chip ecosystem and inference framework adaptation

MiMo-V2.5-Pro completed the integration and adaptation with multiple chip manufacturers on the first day of its open source release. The following is a partial list of manufacturers:

- Ali T-HEAD

> The T-HEAD Zhenwu 810E relies on a full-stack self-developed AI software stack to achieve deep adaptation. 

- Amazon Web Services

> Amazon Web Services (AWS) has completed the in-depth adaptation of MiMo-V2.5-Pro based on its self-developed Trainium2 chip, Neuron SDK, and vLLM inference framework, achieving first-day adaptation where the model is globally available upon open-sourcing. The next-generation 3nm process Trainium3 will further unleash the Agentic performance potential of the model. 

- AMD

> AMD, relying on the ROCm open-source software stack, provides Day-0 adaptation and comprehensive optimization support for MiMo-V2.5-Pro, helping developers and enterprise users efficiently complete model deployment and go live. 

- Baidu Kunlun Chip

> Kunlun Chip relies on its self-developed architecture, effectively ensuring the stable and efficient operation of models on the platform through underlying operator optimization and software-hardware co-acceleration, and building a solid computing power foundation for upper-layer applications. 

- Suiyuan Technology

> Suiyuan Technology relies on its self-developed Yusuan TopsRider software stack for in-depth optimization. MiMo-V2.5-Pro has completed full adaptation on Suiyuan L600, achieving stable operation with high throughput and low latency, and maintaining excellent performance in complex tasks and long sequence scenarios. 

- Muxi 

> Muxi Xiyun C Series relies on the full stack self-developed MXMACA software stack to achieve end-to-end native support from Triton syntax to Muxi GPU instruction set, with better performance. 

- Days Intelligence Chip

> Tianshu Zhixin can achieve Day 0-level deep adaptation of models, relying on full-stack self-developed software and hardware to build high-quality computing power, with efficient adaptation and easy migration, capable of precisely unleashing model performance and ensuring stable operation. 

In addition, the MiMo-V2.5 series models have also completed Day-0 adaptation for the mainstream inference frameworks SGLang and vLLM.

![图片](https://platform.xiaomimimo.com/static/F6upbwMkIol7iex8R0Sc81XYnhh.3167ebd9.png)

From the first-generation model to today's full open source of MiMo-V2.5, every step of MiMo's growth has been inseparable from the community's feedback and co-construction. 

We will continue to invest in the iteration of model capabilities and the improvement of the ecosystem, and work together with global developers to enable Agent to truly enter every application scenario.


--- DOCUMENT: Xiaomi MiMo-V2.5-TTS-Series + ASR Officially Launched: Your Voice, Under Your Control ---
URL: https://platform.xiaomimimo.com/static/docs/news/v2.5-tts-release.md

# Xiaomi MiMo-V2.5-TTS-Series + ASR Officially Launched: Your Voice, Under Your Control

<img src="./images/K1WEbfl2EolOVvxoIWPcgjlMnJh.jpeg" alt="图片" style="margin: 16px auto;" />

Speech technology is undergoing such a transformation: from "being able to listen and read" to "precise understanding and flexible expression". In real creative and interactive scenarios, machines not only need to penetrate complex spoken language environments - dialect accents, environmental noise, multiple people speaking simultaneously - but also use voice to shape characters, grasp emotions, so that expression is no longer just about conveying words, but also conveying feelings.

Whether it's content creators or businesses relying on speech technology, what they truly need is a speech system that can be freely controlled by language: input a noisy meeting recording, and it can accurately transcribe; input a director's note saying "this part should be low and angry", and it can generate a fitting performance. It understands everything and can express everything. 

To this end, we officially release today **MiMo-V2.5-TTS Series** and **MiMo-V2.5-ASR**  — a whole-link speech model series for the Agent era, covering the two core capabilities of recognition and synthesis, enabling both speech input and output to be freely scheduled by language.

- The MiMo-V2.5-TTS Series includes three models, which have now been launched on  **Xiaomi MiMo Open Platform** , and  **are available for free for a limited time** . The three models share unified style instruction following, audio label control, and text understanding capabilities, enabling voice performance to be precisely regulated by language, respectively covering three typical creative needs: 

   - **MiMo-V2.5-TTS:** Built-in with multiple high-quality premium voices, supports fine-grained control over speech rate, emotion, tone, etc., Out Of The Box, meeting multi-scenario expression needs.

   - **MiMo-V2.5-TTS-VoiceDesign:** Quickly define and generate a brand-new voice in one sentence, making voice creation more intuitive and efficient.

   - **MiMo-V2.5-TTS-VoiceClone:** High-fidelity replication of target timbre with a small number of samples, while maintaining stable style instruction following and audio label control capabilities.

**MiMo-Studio Quick Experience Address:**  **https://aistudio.xiaomimimo.com/#/c**

- **MiMo-V2.5-ASR is officially open-sourced.**  The model's speech recognition performance in complex real-world scenarios such as Chinese-English bilingual, Chinese dialects, Code-Switch, strong noise, and multi-speaker has reached the industry-leading level, providing clear and reliable speech transcription for Agents and ensuring that every interaction is based on accurate understanding.

## MiMo-V2.5-TTS: Let Voice Become Everyone's Creativity

### Core Features of TTS Series

#### Precise ability to follow style instructions

From short single-sentence instructions to an entire director's notes, the model can consistently understand and follow them, covering multiple dimensions such as emotion, tone, speaking speed, vocalization style, and language style. Instructions do not need to be written as structured parameters - simply describe the desired feeling as if giving a briefing to an actor, and the model will translate it into the corresponding performance. 

For scenarios with higher consistency requirements - such as audio dramas, game NPCs, and character-based dialogues - the model also supports **director script-level** structured input:  **characters** ,  **scenes** ,  **detailed instructions** are described in layers, with each layer independently updated at its own pace and freely combined. This layering not only ensures that the timbre identity of the character remains consistent throughout, but also allows the performance of each sentence to be individually controlled. 

**Case1**

Instruct :

声音低沉沙哑一点，像个历经沧桑的老前辈在讲述传奇人物。语气里带点由衷的敬佩，娓娓道来。

Text：

街口那个老周啊，媳妇走得早，一个人拉扯俩娃，白天蹬三轮，晚上还去夜市摆摊修鞋。现在俩孩子都有出息喽，想接他去城里享福——他不去，就守着那间小铺子。哎，人哪，骨头硬，心里头就踏实。

Audio（Voice name：冰糖）：

<mimo-audio src="./audios/EnS1b1joRoQAzZxTENKcu55QnMg.mp3" controls={true} title="db1c31a7-03ef-41ec-a340-10b8499be584.wav" class="mdx-audio"/>

**Case2**

Instruct :

```bash
CHARACTER
曾是守护九天的神祇，见证了凡人的无药可救后，决定以灭世来完成最终的净化。他的心中装满悲悯，但手段是绝对的屠戮。

SCENE
悬浮于崩塌的祭坛之上，俯视下方在火海中哀嚎、曾奉他为信仰的信徒。他在降下最后的毁灭前，发出神圣却残忍的叹息。

DIRECTION
发声机制与共鸣：充分打开胸腔共鸣，制造一种神圣的回音感。声音位置靠后，音色如古钟般低沉且带有金属质感的磁性。
声调与韵律：四声（去声）的下落要极其平缓，不要砸实，带有一种吟诵古籍般的从容与宏大。字句之间的停顿拉长，展现出视万物为刍狗的威压。
气声与实声的较量：在说前两句时，实声饱满，高高在上；但在说出“闭上眼吧”时，声音突然混入大量疲惫的气息，神性开始出现裂痕，流露出勉强的残忍。
咬字细节：古风词汇（如“垂怜”、“沉疴”、“剔骨刮毒”）咬字要深，声母起音圆润而不尖锐。结尾的最后半句，几乎全部转化为气声，像是在哄睡一个婴儿，将残酷包裹在极致的悲哀之中。
```

Text：

你们求我垂怜，求我降下甘霖洗净这浊世。可这世间的沉疴，唯有烈火能剔骨刮毒。闭上眼吧。这业火烧起来的时候，一点也不疼。

Audio（Voice name：白桦）：

<mimo-audio src="./audios/VmQkbuCDyo4i59x0gtXcDp1Encd.mp3" controls={true} title="100e79c0-a79d-4096-ba55-e635eca649dc.wav" class="mdx-audio"/>

#### Flexible audio tag control capabilities

In addition to paragraph-level natural language instructions, the model also supports inline audio tags, which are used to precisely control emotions, states, or styles at specific positions in the text. The tags support both Chinese and English languages and open text descriptions, allowing flexible mixing within the same paragraph of text. From simple emotional annotations to complex arrangements with multi-tag overlay and fine-grained layout, the model can express stably, demonstrating excellent performance in both the expressiveness of tags and the stability of combinations. 

Text：

(调侃) 老张你当时不是说这条航线稳得很吗……

(模仿自信，提高音量) “系统全绿，放心走。”

(突然停顿) ……现在呢？

(爆发，愤怒压不住) 现在整艘船都在报警！你管这叫“放心”？！

(声音变轻) 不过……你看那外面，裂开的星云像在呼吸一样。

(急促｜呼喊) 别断通讯！喂！再撑十秒！十秒！！

(低声｜情绪塌陷般平静) ……算了。

(轻笑｜带点释然) 也挺好，至少是一起看的。

Audio：

<mimo-audio src="./audios/VwqEbtceyopW54xkuMhcTjE0nIf.mp3" controls={true} title="星云.wav" class="mdx-audio"/>

#### Rich text comprehension ability

Even without any prompt or label - just a plain text - the model can directly convey the rhythm and emotion within it. The pauses of punctuation and the undulations of sentence structure will be naturally presented; the emotional arcs hidden in the text, from calm narration to intense twists, can be actively captured by the model; even the speaker's identity (age, temperament, character type) revealed between the lines will automatically be reflected in the voice. In other words: the simplest plain text, when given to it, can still return a vivid and lifelike performance. 

Text：

Ten... nine... eight... seven... six... five... four... three... TWO... ONE... ZERO! LAUNCH! LAUNCH! WE HAVE LIFTOFF! GO GO GO! SHE'S CLIMBING! ALTITUDE 1,000... 5,000... 10,000 FEET AND CLIMBING! BEAUTIFUL! AB-SO-LUTE-LY BEAUTIFUL!

Audio：

<mimo-audio src="./audios/SeyubvO3So5lUIxXnKfcH9vSn5e.mp3" controls={true} title="climb_milo.wav" class="mdx-audio"/>

### Model Series

#### MiMo-V2.5-TTS

 It comes with multiple high-quality voices, covering a variety of usage scenarios. Each voice has been professionally tuned, with natural pronunciation and emotional resonance, allowing you to enjoy high-quality speech synthesis right out of the box.  **Welcome everyone to visit Xiaomi MiMo Studio for voice previews:**  

https://aistudio.xiaomimimo.com/#/c

<img src="./images/YJ8zb7ltOouz1wxKmr0cRXSXnCg.jpeg" alt="图片" style="margin: 16px auto;" />

#### MiMo-V2.5-TTS-VoiceDesign

The timbre design is aimed at scenarios where " **I have a voice in my heart, but the world doesn't have one yet** ": game NPCs, animated characters, virtual LIVE creators, brand IPs, atypical voices of audio dramas - these are difficult to choose directly from the timbre library and are not suitable for human cloning.

This model supports **generating a brand new timbre from scratch through natural language descriptions** ,  without the need for any reference audio. Users can freely use any descriptive dimensions such as age, gender, accent, timbre, vocalization style, personality, etc. - for example, "an elderly Eastern European scholar, with a deep, slightly hoarse voice and a slow speaking rhythm" or "a vibrant young girl, with a clear voice and a slight upward inflection at the end of sentences" - and the model can synthesize the corresponding character timbre. 

Thanks to large-scale pre-training, the model can also reasonably interpret **complex, ambiguous, or even contradictory** descriptions, rather than being limited to coarse-grained labels such as "male/female/young/old". This enables timbre design not only to generate unique voices that are difficult for real people to provide, but also to accurately reproduce the voice lines of a certain type of character. 

**Case1**

Instruct :

一位中年男性，说标准普通话，嗓音低沉有磁性，带有轻微的沙哑质感，像纪录片旁白解说员，沉稳而有感染力。

Text：

当最后一缕阳光消失在地平线之下，这片沉睡了亿万年的大地开始显露它真正的面貌。在这寂静的荒野中，每一块岩石都记录着时间的流逝，每一阵风都在诉说着古老的故事。

Audio：

<mimo-audio src="./audios/MkBPbmGlVoLF4Pxpf7scokGknAb.mp3" controls={true} title="纪录片.wav" class="mdx-audio"/>

**Case2**

Instruct :

一位年迈的老先生，说带北方口音的普通话，语速缓慢而沉稳，嗓音略带沙哑和沧桑感，仿佛一位饱经风霜的老爷爷在讲故事，充满岁月的智慧。

Text：

我这辈子啊，走南闯北六十多年。见过最热闹的集市，也见过最安静的戈壁。到头来才明白一个道理——这人哪，不在走了多远的路，在于记住了多少风景。年轻人，别光顾着赶路，偶尔也停下来看看天。

Audio：

<mimo-audio src="./audios/EHVKbKMaMor5CnxAl4Lc4lTVnmc.mp3" controls={true} title="老年.wav" class="mdx-audio"/>

#### MiMo-V2.5-TTS-VoiceClone

Voice cloning is used to enable the model **to speak in the voice you specify**—replicating a real-life podcaster, voice actor, brand spokesperson, or the user themselves.

**Simply provide a reference audio as short as a few seconds** , and without any additional training, annotation, or fine-tuning process, the model can directly reproduce the speaker's timbre and be immediately available. The reproduced voice not only retains the timbre identity of the original speaker but also preserves personal characteristics such as breath, rhythm, and habitual pauses. 

The cloned timbre can **reuse all the control capabilities of this series of models** — natural language instructions, audio tags, and director-level scripts can all continue to be used in combination. The reproduced voice not only "sounds like the original person" but can also perform according to the style and emotion you specify. 

Prompt：

<mimo-audio src="./audios/EzmLbRLwjocZSOxX2PVcqKezn5g.mp3" controls={true} title="2.wav" class="mdx-audio"/>

Instruct：

用尖锐刻薄的嗓音，带着狐假虎威的得意感说话，在提到大人物的身份时故意放慢语速并加重语气，营造压迫感。

Text：

你以为我是谁，也敢在这儿跟我耍横？我告诉你，站在我身后的那个人，说出来吓死你——是当今的——万岁爷！你今天要是不给我个说法，我让你这铺子明天就开不了门。

Audio：

<mimo-audio src="./audios/YfVPb3dikonP11xfHK3cqEo9nEd.mp3" controls={true} title="3_audio.wav" class="mdx-audio"/>

## MiMo-V2.5-ASR: Understand every expression of yours, no matter how complex

If TTS enables voice to become a creative tool at the "output" end, then ASR opens the door to all this at the "input" end. In real-world scenarios, being able to clearly and accurately understand speech amidst language switching, background noise, and speakers with strong dialect accents is what truly makes a good speech recognition system. 

MiMo-V2.5-ASR, as the auditory foundation of the whole-link speech model series, has achieved industry-leading levels in complex real-world scenarios such as Chinese-English bilingual, Chinese dialects, Code-Switch, strong noise, multi-speaker, and high knowledge density. It is not just about converting clear speech into text, but also enabling agents to capture every word and phrase worthy of understanding in noisy real-world sounds.

### Core Features

Chinese dialects: Supports dialects such as Wu dialect, Cantonese, Minnan dialect, Sichuan dialect, etc.

Complex English Scenarios: Achieved leading performance on the Open ASR Leaderboard in complex English scenarios such as AMI

Code-Switch: Free and smooth speech transcription for Chinese-English Code-Switch, no need to pre-set language labels

Song Recognition: Recognizes lyrics of Chinese and English songs, maintaining high accuracy in scenarios where accompaniment and vocals are mixed 

Strong noise scenario: Maintains robust recognition in complex acoustic environments such as high noise and far-field sound pickup

Multi-speaker: Supports accurate transcription of multi-person cross-dialogue scenarios, such as meeting scenarios

Strong Knowledge Association: Precise identification of knowledge-intensive content such as ancient poems, technical terms, personal names, and place names

Native Punctuation: Outputs punctuation natively by combining speech prosody and semantics, with the transcription results ready for immediate use without post-processing

### Performance

MiMo-V2.5-ASR has achieved the current optimal or highly competitive results across multiple dimensions, including general Chinese and English, Chinese dialects, Code-Switch, and lyrics recognition, demonstrating its stable advantages across scenarios and languages. The following are representative evaluation results:

<img src="./images/TdZBb6yCIo2L0bxH23IcYuJgnob.png" alt="图片" style="margin: 16px auto;" />

For Agent applications, content creation tools, conferencing systems, and voice interaction products, this is a truly verified auditory foundation in complex real-world speech. 

## How to Use 

### MiMo-V2.5-TTS Series

To assist developers in exploring more scenarios,**MiMo-V2.5-TTS, MiMo-V2.5-TTS-VoiceDesign, and MiMo-V2.5-TTS-VoiceClone** are all available for free on the **Xiaomi MiMo API** Open Platform **for a limited time:**
https://platform.xiaomimimo.com/docs/usage-guide/speech-synthesis-v2.5

Meanwhile, everyone is welcome to visit **Xiaomi MiMo Studio** for a quick experience:https://aistudio.xiaomimimo.com/#/c

<img src="./images/AnrTbxLbJoGF7Pxs0s2cMOO3neg.jpeg" alt="图片" style="margin: 16px auto;" />

For more cases, please refer to [https://mimo.xiaomi.com/mimo-v2-5-](https://mimo.xiaomi.com/mimo-v2-5-tts)[tts](https://mimo.xiaomi.com/mimo-v2-5-tts)

### MiMo-V2.5-ASR

**MiMo-V2.5-ASR has now open-sourced its model weights and code**, enabling developers and researchers to directly use or conduct secondary development.

> Demo page: [https://mimo.xiaomi.com/mimo-v2-5-asr](https://mimo.xiaomi.com/mimo-v2-5-asr)
>
> Project Open Source Address: [https://github.com/XiaomiMiMo/MiMo-V2.5-ASR](https://github.com/XiaomiMiMo/MiMo-V2.5-ASR)
>
> Weight Open Source Address: https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR
>
> Huggingface space: https://huggingface.co/spaces/XiaomiMiMo/MiMo-V2.5-ASR

## Agent Tool Call Support 

To facilitate everyone's quick integration of speech capabilities into Agent applications, we have fully open-sourced the access Skill for MiMo-V2.5-TTS related models. Welcome to visit the repository to pull and use: 

[https://github.com/XiaomiMiMo/MiMo-Skills](https://github.com/XiaomiMiMo/MiMo-Skills)

### Sound is just the starting point

Beyond the MiMo-V2.5-TTS Series, we would like to answer a question:

What will audio creation look like when MiMo-V2.5-TTS understands "expression", MiMo-V2.5-Pro understands "planning", and MiMo-V2.5 understands "listening"? 

**The answer is: a complete, closed-loop Agent-style creative chain.** 

- MiMo-V2.5-Pro —— Planning and screenwriting, breaking down tasks, writing scripts, arranging rhythm, and determining the editing sequence.

- MiMo-V2.5-TTS Series —— Timbre and Creatives, Voice Design generates timbre, Voice Clone synthesizes content.

- MiMo-V2.5 —— Listening back and evaluation, checking if the character is consistent, if the rhythm is correct, and if it deviates from the user's original intention.

An example:

> Create a scene of a summer afternoon lasting about 2 minutes. Grandpa (in his 70s, with a Beijing hutong accent, hoarse voice, drawn-out speech, lowered voice when concentrating on chess, and a booming laugh with a table slap) is playing chess under a pagoda tree. A 5-year-old grandson is squatting beside, watching ants, and occasionally interrupting with childish questions (clear, with rising intonation at the end, higher when excited, and occasional unclear pronunciation). Grandpa's tone is solemn when he gets serious, but immediately softens into a laughing scold when interrupted by his grandson.

Users only provide a single sentence, and the finished product is generated automatically:

<video src="./videos/BZdlbxZxGotw9GxYkf6cjjhLnob.mp4" controls={true} playsInline={true} title="video-60s.mp4" class="mdx-video" />

<mimo-audio src="./audios/Nv6AbNOe6oGrIFxEnc2cQaORnzg.mp3" controls={true} title="agent-wav.wav" class="mdx-audio"/>

**Some may say it's a threshold, but being able to listen, think, and collaborate is what truly matters.** 

## Next step

1. **Larger-scale speech pre-training and post-training with reinforcement learning:**  MiMo-V2.5-TTS-Series demonstrates the significant benefits of large-scale pre-training and post-training, expanding the scale of both: through more data, larger models, and stronger computing power, enabling more powerful speech intelligence to emerge from scale; more refined reward modeling and reinforcement learning algorithms drive the model towards higher-order speech expression intelligence. 

1. **Universal Audio Generation:** Speech is just the first step. We are expanding our capabilities to more generalized audio generation: environmental sound effects, action sounds, ambient backgrounds, and even short musical phrases and melody segments—gradually modeling a complete sonic world. We believe that a true universal audio model is not simply piecing together speech, sound effects, and music, but enabling them to understand each other and collaborate in the same space.

1. **Contextual understanding ability:** Speech expression has never been an isolated sentence game. The reason people can "read correctly" is because they understand the context—knowing what happened before and understanding where the current sentence fits into the overall narrative. Contextual understanding means that the model is no longer just a "tool for executing sentences one by one," but an expresser who understands the context of the story. This is a crucial step towards truly general speech intelligence.

1. **General Speech Understanding Ability:** Our goal is to ensure that "real-world norms" such as dialects, noise, and Chinese-English mixtures no longer become the weak points of speech recognition. In the future, we will continue to expand the coverage of more dialects and deepen context awareness capabilities, enabling speech recognition to evolve from "transcription" to "understanding".

<img src="./images/J1qQbcRZmoXwglxvlSccY2ptnQb.jpeg" alt="图片" style="margin: 16px auto;" />


--- DOCUMENT: Xiaomi MiMo-V2.5 Series Large Model Launches Public Beta ---
URL: https://platform.xiaomimimo.com/static/docs/news/v2.5-news.md

# Xiaomi MiMo-V2.5 Series Large Model Launches Public Beta

![图片](https://platform.xiaomimimo.com/static/T8xCbyh88oQkeFx4KtPcVWpMn0c.160cbe4a.jpeg)

Today, the Xiaomi MiMo-V2.5 series of models officially launched its public beta.

The Xiaomi MiMo-V2.5 series includes MiMo-V2.5, V2.5-Pro, V2.5-TTS Series, and V2.5-ASR. 

Stronger reasoning, more stable agents, longer context, stronger instruction following and understanding of ambiguous instructions, better full-modal perception and understanding —— this is a comprehensive leap from "usable" to "user-friendly".

Meanwhile, we have also optimized the Token Plan pricing plan —— making the world's top-notch models easily accessible.

##  MiMo-V2.5-Pro: Stronger Agent, Longer Focus

MiMo-V2.5-Pro is our most powerful model to date. In dimensions such as **general agent capabilities, complex software engineering, and long-range tasks**, it can already compete head-on with the world's top Agent models (Claude Opus 4.6, GPT-5.4), achieving a comprehensive leap compared to the previous generation MiMo-V2-Pro.

During internal testing, the intelligence level demonstrated by MiMo-V2.5-Pro has made us rethink the way humans and models collaborate: when paired with a suitable operating framework, it can stably complete long-range tasks involving nearly a thousand rounds of tool calls in a single instance, and its instruction-following ability in the agent scenario has also significantly improved - it can accurately capture implicit requirements in the context and maintain logical consistency over an extremely long period. By now, MiMo-V2.5-Pro can already undertake truly serious professional work with a higher confidence level. 

![图片](https://platform.xiaomimimo.com/static/Jsu9bEinQoAo1ZxbgJNc9VV3nDc.2e556733.png)

#### Designed for more complex tasks

MiMo-V2.5-Pro is designed for more challenging and complex task objectives. We assign tasks that would take human experts days or even weeks to complete to it, allowing it to independently complete long-term processes while still maintaining extremely high quality. The following are the results it has delivered:

##### **Implement a complete SysY compiler in Rust**

This task originated from the Compilation Principles course project at Peking University, requiring the model to implement a complete SysY compiler from scratch in Rust, including a lexical analyzer, a syntax analyzer, AST, Koopa IR code generation, RISC-V assembly backend, and performance optimization. For reference,  **undergraduate students at Peking University usually take** **several weeks to complete this project, while MiMo-V2.5-Pro only took** **4.3 hours**, completed all tasks after 672 tool calls, and achieved **a perfect score of 233/233 on the hidden test set, demonstrating extremely high productivity value.**  

![图片](https://platform.xiaomimimo.com/static/ZS0NbihSUoqRRtxffeOckXzCnue.5eeb8e55.jpeg)

Instead of getting stuck in brute-force trial-and-error, it builds the entire compiler layer by layer: first constructing the complete pipeline framework, then tackling each layer one by one - Koopa IR achieved a perfect score (110/110), the RISC-V backend achieved a perfect score (103/103), and Performance optimization achieved a perfect score (20/20). The first compilation passed **137/233** , with a cold start pass rate of 59%, which means that the architecture was already correct before running any tests. In the 512th round, a refactoring caused lv9/riscv to regress by two test points; the model self-diagnosed, recovered, and continued to progress. 

**The long-range task rewards precisely this structured and self-correcting work discipline.** 

##### **Develop a video editor**

With just a few simple instructions - "Build a video editor web application" - MiMo-V2.5-Pro delivered a runnable web application: featuring multi-track timeline, clip trimming, cross-fading, audio mixing, and export processes. The final built codebase amounts to 8,192 lines, involves 1,868 tool invocations, and was completed in 11.5 hours of autonomous work.

##  MiMo-V2.5: Overstepping Full-Modal Agent, Million Contexts

MiMo-V2.5 is a native full-modal large model designed for Agent scenarios, capable of seeing, hearing, and reading simultaneously, and translating understanding into action.

This time, MiMo-V2.5 brings a key upgrade: 

**Agent capabilities comprehensively surpass MiMo-V2-Pro**

In authoritative Agent evaluations such as Claw-Eval, MiMo-V2.5 surpasses the level of MiMo-V2-Pro, is capable of handling daily simple tasks, and at the same time reduces API costs by approximately 50%. 

**MultiModal Machine Learning perception comprehensively surpasses MiMo-V2-Omni**

Capabilities such as cross-modal reasoning, video understanding, and chart analysis have been enhanced, approaching and even surpassing industry-leading closed-source models in evaluations such as VideoMME, CharXiv, and MMMU-Pro.

![图片](https://platform.xiaomimimo.com/static/DLIrb2z64odTsCxpfzocBH8tngd.6561e5a0.png)

##  MiMo-V2.5 Full Series: Higher Token Efficiency

The entire MiMo-V2.5 series is optimized for Token efficiency, doing more with fewer Tokens. 

When achieving the same score on the Agent benchmark list ClawEval: 

- MiMo-V2.5-Pro saves 42% Token compared to Kimi K2.6

- MiMo-V2.5 saves 50% of tokens compared to Muse Spark

![图片](https://platform.xiaomimimo.com/static/I1BnbUiTKoQl9QxPoYxczCPEnOf.c23fed3c.jpeg)

##  MiMo-V2.5 Full Series: How to Use Them in Combination?

- MiMo-V2.5-Pro is specifically designed for long and complex Agent tasks, while MiMo-V2.5 covers most general Agent scenarios

- MiMo-V2.5 supports native full-modal Agent capabilities, covering images, audio, and video

- MiMo-V2.5 has a higher average inference speed and can respond more quickly to latency-sensitive tasks

![图片](https://platform.xiaomimimo.com/static/AbE5bpAYaovgIlxz2jPcziYznGf.82134601.png)

##   Token Plan Upgraded and Refreshed 

We have made several substantial optimizations suitable for you regarding the Token Plan: 

**Credits rate updated, more favorable**

- MiMo-V2.5：1x（use 1 Token = 1 Credit）

- MiMo-V2.5-Pro： 2x（use 1 Token = 2 Credits）

**Cancel the billing method of 1 Token = 4 Credits. From now on, the Token Plan will no longer distinguish the Credit multiplier for 256k and 1M context windows.** 

**Exclusive Nighttime Discount Rate**

From 00:00 to 08:00 Beijing Time every day, the consumption rate of Credits for all models**will be further discounted by 20% on top of the original rate**. 

**Enjoy discounts with auto-renewal** 

A new "Continuous Monthly Subscription" model has been added. Existing users who activate auto-renewal will enjoy a 30% discount on the next month's subscription, while new users will enjoy a 23% discount on the next month's subscription, both limited to one time. 

A new "Annual" subscription cycle has been added. Subscribing once will enjoy an 12% discount for the whole year, and no longer be combined with the first purchase/auto-renewal discount. 

##  Online Benefit: Token Plan users' Credits will be fully reset

All users who have purchased the Token Plan (as of 22:00 on April 22, Beijing Time) **will have their Credits quota fully reset to zero**, and the calculation will start anew.

Xiaomi MiMo helps you start from scratch and unleash your creativity to the fullest!

> Note: This online welfare only resets the Credits limit, does not reset the package timing, and the validity period of purchased packages remains unchanged.

![图片](https://platform.xiaomimimo.com/static/BubdbNjLlogILoxgG1vca3mxnEf.27fca4e4.jpeg)

##   is about to be open-sourced 

MiMo-V2.5-Pro and MiMo-V2.5 models are about to be globally open-sourced. Stay tuned!


--- DOCUMENT: Xiaomi MiMo is now integrated with the top-tier Agent framework Hermes Agent and offers a two-week free trial ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/hermes-free.md

# Xiaomi MiMo is now integrated with the top-tier Agent framework Hermes Agent and offers a two-week free trial

The Xiaomi MiMo-V2 series now officially supports Hermes Agent! 

As the flagship base for the Agent era, the Xiaomi MiMo-V2 series of large models has officially joined hands with the world's leading Agent open-source framework Hermes Agent to achieve official integrated access. 

**Hermes Agent is：**  

- One of the most globally watched open-source Agent frameworks currently

- It has the capabilities of self-evolution and cross-session memory, automatically accumulates experience from tasks, and becomes stronger with more use 

- Supports cross-platform communication

MiMo-V2-Pro, with its 1M long context capability, native strong tool invocation, and in-depth Agent-specific optimization, is fully compatible with core features of Hermes Agent such as self-evolution skills, cross-session memory, and complex workflows.

MiMo-V2-Omni further expands the boundaries of perception, integrating the full-modal understanding capabilities of images, videos, audio, and text, enabling Hermes Agent to become a true full-modal agent that can see, understand, and act.

**We sincerely invite developers worldwide to try it out, with a two-week free trial** 

- **Free trial period:**   April 8 - April 22, 12:00 (Beijing Time, UTC+8), a total of two weeks. 

- **Usage:**  Update Hermes Agent to the latest version, and you can call Xiaomi MiMo-V2 Pro, Omni, and Flash models for free via Nous Portal.

![图片](https://platform.xiaomimimo.com/static/TFqGbro9kobTwnx3mwjc5A7PnNe.494f9774.webp)

From "task execution" to "self-evolution", MiMo, in collaboration with Hermes Agent, enables your AI Agent to become "smarter with use". 

![图片](https://platform.xiaomimimo.com/static/ChtgbWq79oVFoBxNyOucPsREnVe.dba4005c.webp)


--- DOCUMENT: Xiaomi MiMo Token Plan Brand New Release ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/token-plan-release.md

# Xiaomi MiMo Token Plan Brand New Release

Since 2025, the capabilities of large models have been continuously redefined. However, for most developers and users, "affordability" remains a more fundamental issue than "usability". Under the pay-as-you-go model, every invocation is accompanied by uncertainty about costs.

We don't want it to be this way. We believe that ** good technology should not be a privilege reserved for only a few; it should, like water and electricity, become a readily accessible productivity tool for everyone at a predictable price.** 

Therefore, we officially launch the Xiaomi MiMo Token Plan.

### MiMo Token Plan: Simplify Complexity

Our original intention in designing the Token Plan was to ensure that the billing method is transparent, simple, and straightforward enough for any user to understand and use with ease.

**1. Transparent design, simple and straightforward** - Unified Credit point system, converting credit consumption based on token usage, helping you easily plan your usage.

> - MiMo-V2-Omni 256k Context: 1x (1 Token Consumed = 1 Credit)
>
> - MiMo-V2-Pro 256k Context: 2x (1 Token Consumed = 2 Credits)
>
> - MiMo-V2-Pro 256k~1M Context: 4x (1 Token Consumed = 4 Credits)
>
> - MiMo-V2-TTS: 0x (Limited-time free, no Credit consumption)

**2. No 5-hour token usage limit** —— Supports concentrated token consumption, enabling high-intensity lobster farming or programming with a full experience and no interruptions.

**3. Users who purchase the package can enjoy the priority internal testing experience right for the new model**—advanced and user-friendly, one step ahead.

![图片](https://platform.xiaomimimo.com/static/C4NKbWi3NoXjfzxBCuscOiyinFe.148081c0.png)

### Four-tier pricing, designed for you

Token Plan offers four tiers of packages, so no matter your frequency and depth of AI usage, you can find a suitable plan:

- **Lite (China: ¥39/month. Overseas: $6/month)** —— 60M Credits, can execute approximately **120 medium to complex tasks**. Suitable for explorers new to AI development, starting at the price of a cup of coffee.

- **Standard (China: ¥99/month. Overseas: $16/month)** —— 200M Credits, capable of performing approximately **400 medium to complex tasks**. A primary solution designed for work and developer users who rely on AI for daily efficiency improvement.

- **Pro (China: ¥329/month. Overseas: $50/month)** —— 700 million (700M) Credits, capable of performing approximately **1,400 medium to complex tasks**. Designed for professional users who deeply integrate AI into their workflows.

- **Max (China: ¥659/month. Overseas: $100/month)** —— 1.6 billion (1600M) Credits, capable of executing approximately **3200 medium to complex tasks**. Designed for developers with all-day, high-intensity usage, offering an almost unrestricted usage experience.

> All packages enjoy a **12% discount** on the first purchase, and this discount is limited to 1 time only.
>
> ![图片](https://platform.xiaomimimo.com/static/LgVzbjs0Wovbkqxj7ImcjZnVnpg.2dc2bce2.png)

### Specifically adapted for mainstream AI tools 

Specifically designed for mainstream AI tools and development platforms such as Claude Code, OpenClaw, OpenCode, Kilo Code, Cline, etc., to help you efficiently boost productivity. 

### This is just the beginning 

Auto-renewal, plan upgrades, and more flexible usage management are all under development. If you have any ideas or suggestions during use, we sincerely look forward to your feedback.

Token Plan is the new starting point for MiMo, and our goal has never changed:** to create the best models, set the most reasonable prices, and enable more people to truly use them.** 

👉 Purchase Now: [Xiaomi MiMo Open Platform](https://platform.xiaomimimo.com/)

![图片](https://platform.xiaomimimo.com/static/IErEbhWMBo8AR6xATDfcFifDnpe.6df914e9.png)


--- DOCUMENT: Xiaomi MiMo Agent Framework Call Free Trial Extension for One Week ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/free-trial-extension.md

# Xiaomi MiMo Agent Framework Call Free Trial Extension for One Week

Since the global release of the new models in the Xiaomi MiMo-V2 series on March 19, 2026, the MiMo-V2-Pro/Omni has been enthusiastically pursued and widely concerned by developers worldwide, especially the flagship model MiMo-V2-Pro in the global call volume ranking of OpenRouter**has continuously ranked No. 1 in the daily, weekly, and trending lists**. 

In addition, our joint operation activities carried out together with  **top Agent frameworks such as OpenClaw, OpenCode, KiloCode, Cline, and BlackBoxAI**  are also highly popular among users. 

Therefore, we have decided - **to extend the "XiaomiMiMo Launches First Week Free Trial in Collaboration with Global Top Agent Framework" event from the originally scheduled one-week free trial to two weeks,**  and the free trial period will be extended to:  **12:00 PM, April 2, 2026, Beijing Time (GMT+8).** 

For the limited-time free access methods of each platform, please refer to:[Xiaomi MiMo Partners with Top Agent Framework : First Week Free](https://platform.xiaomimimo.com/#/docs/news/first-week-free)

AI without barriers, innovation without limits. We sincerely invite global developers to fully unleash the powerful productivity of the combination of Xiaomi MiMo large model and top-tier Agent framework.

![图片](https://platform.xiaomimimo.com/static/JwcCbjtbroZVM2xy4VIcaVoVnHe.1079e224.png)


--- DOCUMENT: Xiaomi MiMo Partners with Top Agent Framework : First Week Free ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/first-week-free.md

# Xiaomi MiMo Partners with Top Agent Framework : First Week Free

![图片](https://platform.xiaomimimo.com/static/RgAbbHPPQoTpLOxnirNcPr1EnXr.34f7b801.png)

MiMo-V2-Pro, MiMo-V2-Omni, and MiMo-V2-TTS are now available. To meet global developers' anticipation for Xiaomi MiMo's new base models, Xiaomi MiMo has partnered with five agent frameworks — OpenClaw, OpenCode, KiloCode, Cline, and BLACKBOXAI — offering free API access worldwide for one week.

**Note: MiMo-V2-Pro and MiMo-V2-Omni can only be used for free in the above five agent frameworks, see below for detailed instructions. To call the Model API directly, see** [**Pricing and Rate Limits**](https://platform.xiaomimimo.com/#/docs/pricing) **for pricing standards.** 

## 01 / OpenClaw

**Free for a Limited Time** — A Highly Anticipated General-Purpose Agent Framework. AI That Truly Gets Things Done.

![图片](https://platform.xiaomimimo.com/static/DrWSbyYP9oqCBAxuR2OcO2yZnGd.0ae1e4fe.png)

#### Integration

Get an API Key from OpenRouter and configure it in your OpenClaw:

- In chat: `/model openrouter/xiaomi/mimo-v2-pro` (or v2-omni)

- In terminal: `openclaw models set openrouter/xiaomi/mimo-v2-pro` (or v2-omni)

- Or edit config: set `model.primary` to `openrouter/xiaomi/mimo-v2-pro` (or v2-omni)

See details on [OpenClaw provides free access to MiMo-V2-Pro/MiMo-V2-Omni replicas via Openrouter](https://platform.xiaomimimo.com/#/docs/integration/openclaw-with-openrouter) .

![图片](https://platform.xiaomimimo.com/static/HfFhbA7DaoyE2SxbmbPcVgxynld.d2246db6.png)

## 02 / OpenCode

**Free for a Limited Time** — Open-Source AI Coding Agent. 120K+ GitHub Stars. 5M+ Developers Monthly.

![图片](https://platform.xiaomimimo.com/static/JE0ZbgLiFoMqcHxYXPscSzeVnHc.ca092ea8.png)

#### Integration

From the terminal, desktop app, or IDE extension, select MiMo V2 Pro / MiMo V2 Omni (FREE tag) under OpenCode → Zen.

![图片](https://platform.xiaomimimo.com/static/HRXbbkfF6o7JBBxT76icaD7Zn0u.e4d63c03.jpeg)

## 03 / KiloCode

**Free for a Limited Time —** A Full-Featured AI Engineering Platform for Developers. 1M+ Kilo Developers.

![图片](https://platform.xiaomimimo.com/static/OaOmb9EotoM6eoxKrDrcXIu5nfI.9e0d3128.png)

#### Integration

From the terminal or IDE extension, select MiMo V2 Pro / MiMo V2 Omni (FREE tag) under Kilo Gateway.

![图片](https://platform.xiaomimimo.com/static/EBAAbV8kNo29Btx6doRcKZltnpb.a278be64.jpeg)

## 04 / Cline

**Free for a Limited Time —** AI Coding Assistant That Helps Developers Build and Refactor High-Quality Software at 2x Speed.

![图片](https://platform.xiaomimimo.com/static/FEv0bcYLzoL83exEPkac3bPKngb.c2d22ecc.png)

#### Integration

From the terminal or IDE extension, select Cline as the Provider and choose mimo-v2-pro (FREE tag).

![图片](https://platform.xiaomimimo.com/static/ToQEbkzrOoAyP8xst0AclL4GnTo.b40ec89d.jpeg)

## 05 / BLACKBOX.AI

One of the Fastest-Growing Coding Agents Globally — Committed to Redefining How You Write Code with AI.

Blackbox.AI is Currently in Final Testing and Coming Soon. Stay Tuned to Blackbox.AI's Official X Posts.

![图片](https://platform.xiaomimimo.com/static/JpcYbeWS7owoE8xZHeMcIvFdn0g.1d66689f.png)

#### Integration

Select the model in the terminal, desktop app, or IDE extension to integrate.

![图片](https://platform.xiaomimimo.com/static/JNzqbHvpyoiRQ8xhTCRc5oZjnUC.31d09dab.jpeg)

## 06 / MiMo-V2-TTS

**Free for an Extended Period.**  — Xiaomi's In-House Text-to-Speech Foundation Model. Empowering Agents with Warm, Expressive, and Soulful Voice.

#### Integration

Access via the official API platform.

For detailed integration, refer to: [MiMo-V2-TTS Usage Guide](https://platform.xiaomimimo.com/#/docs/usage-guide/speech-synthesis)

![图片](https://platform.xiaomimimo.com/static/QdYQbLmfZofJtNxMQ16ca62Lnaf.13effe48.png)

AI Without Barriers. Innovation Without Limits. Global Developers — Unleash the Power of Trillion-Parameter Models Paired with Top-Tier Agent Frameworks.

![图片](https://platform.xiaomimimo.com/static/XkI1bhvB8oHRL7xzyquc1wQEnKg.e4483670.png)


--- DOCUMENT: Xiaomi MiMo-V2-Pro: Flagship Foundation Model towards Agent Era ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/v2-pro-release.md

# Xiaomi MiMo-V2-Pro: Flagship Foundation Model towards Agent Era

Today, we are releasing Xiaomi MiMo-V2-Pro, Xiaomi’s flagship foundation model for the agent era.

Xiaomi MiMo-V2-Pro is built for demanding real-world Agent workflows. It has over **1T** total parameters, with **42B** active parameters, uses an innovative hybrid attention architecture, and supports an ultra-long context window of up to **1M** tokens. Based on the strong foundation model, we continue to scale compute across a broader range of agent scenarios, further expanding the action space of intelligence and achieving an important generalization leap from Coding to Claw.

On the global authoritative model intelligence ranking by Artificial Analysis, MiMo-V2-Pro ranks eighth worldwide and second in China.

![图片](https://platform.xiaomimimo.com/static/FZw6bk5M6odYsSxODBOcZds6nAb.6dbd3629.png)

In agent frameworks such as OpenClaw and Claude Code, MiMo-V2-Pro shows excellent end-to-end task completion ability. It can handle complex workflow orchestration, long-horizon planning, and precise tool use without human intervention, while reliably delivering final results. In overall hands-on experience, it has surpassed Claude Sonnet 4.6 and is approaching Opus 4.6, while its API pricing is only one-fifth of theirs, lowering the barrier to using frontier intelligence.

## A major leap in foundation capabilities

By scaling both parameters and compute, MiMo-V2-Pro reaches to a larger and stronger model foundation.

- **Trillion-parameter scale, efficient architecture**: Total parameters exceed 1T, with 42B active parameters, about 3x larger than the previous MiMo-V2-Flash. It continues to use the innovative Hybrid Attention mechanism introduced in MiMo-V2-Flash, with the hybrid ratio further increased from 5:1 to 7:1. This keeps inference efficient even with the large increase in model size, while also supporting 1M-token context. A lightweight MTP (Multi-Token Prediction) layer enables fast generation.

- **From Chat to Agent**: By scaling during post-training across a broader set of Agent tasks, the model is no longer limited to “answering questions” or “generating polished demos.” It is built to complete tasks. We aim to integrate it deeply into productivity scenarios so it can serve as the “brain” behind working systems and continuously deliver results with real-world impact.

- **Real-world experience beyond benchmark rankings**: MiMo-V2-Pro performs strongly across benchmarks that measure key model capabilities. In Coding Agent, general Agent, and Tool Use tasks, it is in the same tier as Claude 4.5 Sonnet, GPT5.2, and Gemini 3.0 Pro, showing leading intelligence. We remain focused on training and optimization guided by actual user experience, always paying close attention to how the model performs in real applications.

![图片](https://platform.xiaomimimo.com/static/IAt5buS6To3zKExg1RZcsGhhnPc.b9770bef.png)

## A flagship model built for Agents

MiMo-V2-Pro is deeply optimized specifically for Agent scenarios.

### The native brain for OpenClaw

OpenClaw is a general-purpose agent framework that has recently gained strong attention in the open-source community. As the core engine behind frameworks like this, the upper limit of the underlying model directly determines the system’s real-world performance. MiMo-V2-Pro is trained with SFT and RL on complex and diverse Agent scaffolds, giving it stronger tool-use and multi-step reasoning abilities. 

On OpenClaw’s standard benchmark leaderboards, PinchBench and ClawEval, MiMo-V2-Pro ranks among the best in the world. At the same time, with its 1M-token context window, MiMo-V2-Pro can comfortably support demanding real-world Claw application flows. Hunter Alpha shown below is an early anonymous version of MiMo-V2-Pro.

![图片](https://platform.xiaomimimo.com/static/XDC4bTG01opiD1xNgphcTj9gnih.309ccd19.png)

### Continuous Evolution of Coding Capabilities

Going beyond mere "Vibe Coding", MiMo-V2-Pro is capable of participating in more rigorous code engineering construction.

In in-depth evaluations by internal engineers at Xiaomi, MiMo-V2-Pro's user experience has approached that of Claude Opus 4.6, demonstrating advanced code intelligence: it boasts superior system design and task planning capabilities, more elegant coding styles, and more efficient, direct problem-solving pathways.

During the "Hunter Alpha" anonymous testing phase, the most frequently called apps were mostly programming-specific tools, which confirm MiMo-V2-Pro's high usability and reliability in real-world R&D scenarios.

![图片](https://platform.xiaomimimo.com/static/RxMnbgF97owiMPxcclPcrF5CnJd.317a2b2a.png)

## 1M Context Window, Open API

The MiMo-V2-Pro model is now officially available via API with pricing:

- Within 256K: Input at $1 / 1M tokens, Output at $3 / 1M tokens

- 256K ~ 1M: Input at $2 / 1M tokens, Output at $6 / 1M tokens

Visit [https://platform.xiaomimimo.com](https://platform.xiaomimimo.com/) to get started.


--- DOCUMENT: Xiaomi MiMo-V2-Omni: Omni-Modal Agentic Foundation Model that Sees, Understands and Acts ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/v2-omni-release.md

# Xiaomi MiMo-V2-Omni: Omni-Modal Agentic Foundation Model that Sees, Understands and Acts

Today, we are thrilled to announce Xiaomi’s omni‑modal foundation model for agent era: Xiaomi MiMo‑V2‑Omni.

Designed specifically for complex real‑world multimodal interaction and execution scenarios, MiMo‑V2‑Omni is built from the ground up as a unified all‑modal foundation that integrates text, vision, and speech. Its unified architecture deeply binds perception and action, overcoming the traditional limitation of models that prioritize understanding over execution.

Natively equipped with multimodal perception, tool invocation, function execution, and GUI operation capabilities, MiMo‑V2‑Omni seamlessly integrates with major agent frameworks. It enables a true leap from understanding to control, drastically lowering the barrier to deploying all‑modal agents.

## Perception Capabilities: Image, Video, and Audio on the Frontier

Accurate perception is the prerequisite for action. We benchmarked MiMo-V2-Omni against leading international models across all sensory modalities to ensure a rock-solid foundation for its capabilities as an AI agent.

**Visual Understanding**: MiMo-V2-Omni demonstrates robust multidisciplinary visual reasoning and complex chart analysis. It has surpassed Claude 4.6 Opus and is rapidly closing the gap with top-tier closed-source models like Gemini 3.

**Audio Understanding**: The model supports everything from environmental sound classification and multi-speaker separation to audio-visual joint reasoning and deep comprehension of continuous audio exceeding 10 hours. Its comprehensive performance exceeds Gemini 3 Pro, making it one of the most powerful audio understanding base models currently available.

**Video Understanding**: By supporting native audio-video joint input, we have achieved true multimodal video comprehension. Through innovative video pre-training, the model possesses powerful situational awareness and predictive reasoning capabilities.

When multiple modalities are processed simultaneously, the advantages of a unified architecture are magnified: cross-modal signals mutually reinforce one another rather than competing for resources.

## Agentic Capabilities: from Understanding to Execution

If perception is the foundation, then action is the ultimate goal.

A true AI agent model must be capable of observing complex environments across multiple modalities, formulating and executing plans, autonomously recovering from errors, and delivering end-to-end results.

### Omni-Modal Agent Tasks

MiMo-V2-Omni excels in benchmarks involving interaction with real-world digital environments, performing on par with Gemini 3 Pro. This success is underpinned by its industry-leading perceptual capabilities：The more accurate the perception, the more effective execution.

![图片](https://platform.xiaomimimo.com/static/E1mxb9Phxohb4BxWxBXcnA3gnIf.478dbc69.png)

At the same time, MiMo-V2-Omni remains highly competitive in text-only agent tasks.

![图片](https://platform.xiaomimimo.com/static/DZu3bIDUWoBFyHxmBT5cZkGWnio.066549ed.png)

## Capabilities Demonstration

### 💻 Browser-Use Scenarios

Browser Use is the ultimate litmus test for a model’s agentic capabilities. It involves real-world interactions, dynamic web environments, heterogeneous interaction methods, and active anti-automation mechanisms. In these scenarios, the closed loop of perception, decision-making, and action operates continuously in an open environment until the mission is accomplished. When these same capabilities are ported to smart devices or robotics, they form the blueprint for General-Purpose Agents.

- **Shopping, Bargaining, and Ordering on Your Behalf**

We tested an end-to-end shopping task. Controlling the browser, the model first browsed over a dozen posts on Xiaohongshu to complete information gathering and obtain purchasing recommendations. It then performed cross-platform price comparisons across multiple stores on JD, followed by connecting with human customer service to bargain using natural language. After real-time interaction with the representative, it ultimately completed the process of adding items to the cart and placing the order. The model autonomously handled non-standard DOM structures, multi-tab context management, and workflow recovery after encountering platform anti-automation detections.

- **TikTok Video Creation and Publishing**

We tested an end-to-end video publishing task. The model autonomously designed four sets of visuals and synthesized all sound effects on-site with zero reliance on external assets. During rendering, it encountered a Chinese font error, which it self-corrected before continuing. It then controlled the browser to open the TikTok upload page, analyzed non-standard input controls to complete the copywriting, and proceeded to like and comment after clicking "Publish." Finally, it re-checked to confirm the video passed review and was publicly live.

### 🗒️ Smart Office Scenarios

Through natural dialogue, MiMo-V2-Omni can directly generate high-quality Word documents, structured Excel sheets, professionally formatted PDFs, and complete PPTs. These generated documents are no longer drafts requiring heavy revision, but high-quality "near-final versions" tailored to actual needs.

- **2026 Intelligent College Entrance Examination Application**

We tested the college entrance examination application planning task. The model can autonomously initiate web searches to obtain raw information, use skills to process files, and generate an Excel spreadsheet containing detailed application recommendations and tiered classifications.

## Open API

The MiMo-V2-Omni model is now officially available via API with pricing:

- Input: $0.4 / million tokens;

- Output: $2 / million tokens.

Visit [https://platform.xiaomimimo.com](https://platform.xiaomimimo.com/) to get started.


--- DOCUMENT: Xiaomi MiMo-V2-TTS: Versatile Voice Agent that Speaks and Sings ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/v2-tts-release.md

# Xiaomi MiMo-V2-TTS: Versatile Voice Agent that Speaks and Sings

**Xiaomi MiMo-V2-TTS** is a large-scale speech synthesis model independently developed by Xiaomi. Built on a proprietary audio tokenizer and a multi-codebook joint speech–text modeling architecture, it has been trained on hundreds of millions of hours of speech data with large-scale pretraining and multi-dimensional reinforcement learning, enabling highly controllable, fine-grained speech style generation. MiMo-V2-TTS supports precise control ranging from global style setting to nuanced local emotional expression. It can perform tone shifts and gradual emotional transitions within a single utterance, faithfully reproducing the natural prosody of human speech. When singing, it can also accurately render pitch and rhythm, delivering natural and expressive performance.

The MiMo-V2-TTS model is now available through the Xiaomi MiMo API open platform (https://platform.xiaomimimo.com), **with free access for a limited time**.

### Text Control
Flexible and customizable style control

MiMo-V2-TTS supports free-form natural language descriptions instead of being limited to predefined keywords. The model can understand and follow arbitrary descriptive instructions.

- Emotion control: happy, sad, angry, gentle, excited, calm…

- Dialect support: Northeastern Mandarin, Sichuan dialect, Henan dialect, Cantonese, Taiwanese accent…

- Role play: Monkey King, Lin Daiyu, Iron Man…

- Freely combined phrases — true natural language control: “cute and coquettish, soft ‘baby voice’,” “lazy, just woke up, slightly husky,” “deeply affectionate, slow speaking pace,” “passionate and powerful”

### Fine-grained control of vocal events

MiMo-V2-TTS can naturally insert and control various paralinguistic vocal events in speech, making the generated audio more realistic and expressive.

Supported vocal events: laughter, coughing, pauses, thinking/hesitation, sighing, etc.

## Deep Text Understanding

The model can intelligently recognize formatting cues in text and convert them into corresponding speech expressions—such as tone and punctuation—without requiring extra annotations.

Format awareness → speech rendering:

- ALL CAPS text (e.g., “THIS IS IMPORTANT”) → automatically adds emphasis;

- Repeated words or characters (e.g., “no no no no no”) → automatically mapped to matching rhythm and emotion.

During pretraining, the model learned from large-scale text–speech aligned data, enabling it to convert written formatting signals into natural-sounding speech.

## Beyond Speech: Dialects · Characters · Singing

MiMo-V2-TTS goes beyond standard speech synthesis with rich and versatile expressive capabilities. It supports natural pronunciation across multiple dialects, enables role-playing with stylized character performances, and delivers high-quality singing synthesis—allowing a single model to speak, act, and sing with ease.

## Open API

MiMo-V2-TTS is now officially available via API. **Free access is available for a limited time.** 

Visit [https://platform.xiaomimimo.com](https://platform.xiaomimimo.com/) to get started.


--- DOCUMENT: MiMo-V2-Flash Release Note 2026/03/03 ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/news20260303.md

# MiMo-V2-Flash Release Note 2026/03/03

MiMo-V2-Flash now supports web search, enabling access to real-time public information (such as news, products, weather, etc.).

**Core Capabilities**

- **Flexible search modes**: Supports forced search and intent recognition. With intent recognition enabled, the model will autonomously decide whether to perform an online search without manual triggering.

- **Early search source return**: In the streaming response, the first packet will return all search sources.

- **Hybrid multi-tool invocation**: Can work with custom functions and tools; the model will automatically determine invocation priority and necessity.

- **Flexible response modes**: Supports both streaming and non-streaming responses, and both methods will return search and summary content.

**Use Cases**

- **Real-Time News Aggregation**

   - Scenario: A user asks, "What are today's top stories about domestic large language models?"

   - Capability: The model automatically generates search keywords like "Chinese LLM latest news March 1 2026," searches the web, and returns a summarized response with source links.

- **Product Information & Price Comparison**

   - Scenario: A user asks, "What are the price and user reviews for the latest model of [Brand] phone?"

   - Capability: The model searches multiple e-commerce platforms for pricing and reviews, then organizes the information into a concise summary to aid decision-making.

- **Real-Time Weather & Travel Information**

   - Scenario: A user asks, "Is the weather in Shanghai tomorrow good for going out?"

   - Capability: The model fetches the Shanghai weather forecast and provides practical suggestions based on common sense, such as "Rain expected tomorrow in Shanghai, temperatures 10–15°C. Bring an umbrella and dress warmly."

**Instructions and Recommendations**

1. **Enable Web Search Plugin**: Before using this feature, you need to activate the [Web Search Plugin](https://platform.xiaomimimo.com/#/console/plugin). For detailed parameters and invocation instructions, please refer to the [OpenAI API](https://platform.xiaomimimo.com/#/docs/api/text-generation/openai-api).

1. **Fees**: The web search feature incurs additional token consumption for generating search queries and processing results. A separate fee will also be charged per search call. For details, see [Web Search](https://platform.xiaomimimo.com/#/docs/usage-guide/tool-calling/web-search).


--- DOCUMENT: MiMo-V2-Flash Release Note 2026/02/04 ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/news20260212.md

# MiMo-V2-Flash Release Note 2026/02/04

1. **Upgraded Coding Capabilities in Thinking Mode:**
Specifically optimized for programming scenarios, the Thinking Mode now achieves a score of **78.6** on SWE-Bench Verified. Both the resolution rate and the quality of code generation have been significantly improved.

1. **Substantial Boost in Tool Calling Accuracy:**
Stability issues regarding tool usage have been resolved. Tool calling accuracy in Thinking Mode has surged from 64% to **97.0%**, greatly enhancing execution reliability in Agent scenarios.

1. **Enhanced Instruction Following & Reduced Hallucinations:**

- **Instruction Following:** Improved adherence to specific instructions, achieving an **AA-IFBench score of 72**.

- **Factuality:** Enhanced rigor in factual responses, with the **Non-Hallucination Rate updated to 52%**.

1. **Optimized Handling of Complex Tasks:**
Performance on Arena-Hard (Hard Prompts) in Thinking Mode has been strengthened, with the score rising to **60.6**. The model now demonstrates superior performance when handling high-difficulty logic problems.

1. **More Efficient Chain-of-Thought (CoT):**
By optimizing CoT generation strategies, the consumption of redundant tokens has been significantly reduced. In benchmarks such as AIME25 and HMMT, the average generation length has decreased by **13% to 30%**. This effectively lowers latency and token costs while maintaining model performance.

|  | **MiMo-V2-Flash-0204** | **MiMo-V2-Flash-0112** | **MiMo-V2-Flash** |
| --- | --- | --- | --- |
| **SWE-Bench Verified** <br />**Non-Thinking** | **73.7** | 73.3 | 73.4 |
| **SWE-Bench Verified** <br />**Thinking** | **78.6** | 74.2 | - |
| **Arena-Hard(Hard Prompt)** <br />**Non-Thinking** | **49.3** | 52.7 | 46.0 |
| **Arena-Hard(Creative Writing)** <br />**Non-Thinking** | **85.0** | 86.0 | 78.3 |
| **Aren-Hard(Hard Prompt)**<br />**Thinking** | **60.6** | 58.3 | 54.1 |
| **Arena-Hard(Creative Writing)**<br />**Thinking** | **85.8** | 90.4 | 86.2 |
| **AA-IFBench** | **72** | - | 64 |
| **AA-Omniscience Accuracy** | **19** | - | 27 |
| **AA-Omniscience Non-Hallucination Rate** | **52%** | - | 9% |
| **Tool call success rate**<br />**Thinking** | **97.0%** | 64% | 44% |

| **Benchmark** | **MiMo-V2-Flash (Acc)** | **MiMo-V2-Flash (Avg Tokens)** | **MiMo-V2-Flash-0204 (Acc)** | **MiMo-V2-Flash-0204 (Avg Tokens)** | **Length Reduction Ratio (%)** |
| --- | --- | --- | --- | --- | --- |
| **AIME25** | 94.8 | 26984 | 91.1 | 18879 | **30.04%** |
| **HMMT_Feb_25** | 94.2 | 29294 | 92.9 | 21470 | **26.71%** |
| **LiveCodeBench-AA** | 83.2 | 21488 | 84.9 | 18335 | **14.67%** |
| **GPQA-Diamond** | 83.7 | 15862 | 83.8 | 13659 | **13.89%** |

> Note: The model API call method and model name remain unchanged


--- DOCUMENT: Billing for Xiaomi MiMo API Open Platform is Launching Soon ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/billing.md

# Billing for Xiaomi MiMo API Open Platform is Launching Soon

Dear Developers:

Thank you for your attention and support for the Xiaomi MiMo API Open Platform. we hereby inform you that the platform will start billing at **Jan 26, 2026 16:00 (UTC+8)**, and before that, API calls will continue to be open for free, and the recharged amount or free credit will not be consumed for the time being. After the billing starts, **accounts with insufficient balance will be unable to use the API.** We recommend that you **recharge in advance** to avoid service interruption due to insufficient account balance.

### MiMo-V2-Flash API Pricing

- Domestic: Input ¥0.7 / 1M tokens, Input (Cache Hit) ¥0.07 / 1M tokens, Output ¥2.1 / 1M tokens

- Overseas: Input $0.1 / 1M tokens, Input (Cache Hit) $0.01 / 1M tokens, Output $0.3 / 1M tokens

### MiMo-V2-Flash API Pricing

- **China**: Input: ¥0.7 / 1M tokens, Cached Input: ¥0.07 / 1M tokens, Output: ¥2.1 / 1M tokens

- **Overseas**: Input: $0.1 / 1M tokens, Cached Input: $0.01 / 1M tokens, Output: $0.3 / 1M tokens

### Exclusive Benefits Available

To thank you for your support, we have prepared exclusive free credits for all new and existing users. You can log in and go to [Balance](https://platform.xiaomimimo.com/#/console/balance) to collect them.

### Recharge Rules

1. **Real-Name Authentication**: Chinese mainland users must complete individual real-name authentication before recharging. Enterprise authentication is not yet available; please stay tuned for updates. Other users can recharge directly without real-name authentication.

1. **Recharge Process**: Go to the [Balance](https://platform.xiaomimimo.com/#/console/balance) page to recharge. Chinese mainland users can use Xiaomi Pay, Alipay, or WeChat Pay. Other users can use common payment methods such as Apple Pay, Google Pay, and credit/debit cards.

1. **Balance Inquiry**: Recharged funds are generally credited to your account in real time. You can view recharge orders and bonus amounts on the [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge) page, and check your current balance on the [Balance](https://platform.xiaomimimo.com/#/console/balance) page. Once the billing system is activated, API calls will first deduct the complimentary free quota, followed by the recharged balance.

1. **Invoice Issuance**: Chinese mainland users can apply for electronic invoices by selecting successful recharge orders on the [Invoice](https://platform.xiaomimimo.com/#/console/invoice) page. Other users can download order receipts from the [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge) page.

1. **For more details, please refer to** [FAQ](https://platform.xiaomimimo.com/#/docs/faq?target=payment-issue).

### Contact Us

For assistance or business inquiries, feel free to reach out to us through the following channels:

- Email: support-mimo@xiaomi.com

- Scan the QR code at the bottom left to join the developer communication group

- Submit your feedback from [Contact Us](https://platform.xiaomimimo.com/#/contact)

We are committed to continuously optimizing our products and services to provide you with superior AI capabilities. Thank you again for your understanding and trust!

<p className="mb-[16px] w-full text-[14px] leading-[24px] lg:text-[16px] lg:leading-[28px] font-normal text-[#5C5C62]" style={{ textAlign: 'right' }}>**—— Xiaomi MiMo API Open Platform Team**</p>

<p className="mb-[16px] w-full text-[14px] leading-[24px] lg:text-[16px] lg:leading-[28px] font-normal text-[#5C5C62]" style={{ textAlign: 'right' }}>**January 23, 2026**</p>


--- DOCUMENT: Xiaomi MiMo API Open Platform Recharge Function Officially Launched ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/recharge.md

# Xiaomi MiMo API Open Platform Recharge Function Officially Launched

## Dear Developers,

Thank you for your continuous support of the Xiaomi MiMo API Open Platform. We are pleased to announce that the recharge service is now officially available as of **January 20, 2026**. To ensure the continuity of your service, we recommend completing your account recharge in advance to avoid any service interruptions due to insufficient balance after the billing system goes live.

### MiMo-V2-Flash API Pricing

- **China**: Input: ¥0.7 / 1M tokens, Cached Input: ¥0.07 / 1M tokens, Output: ¥2.1 / 1M tokens

- **Overseas**: Input: $0.1 / 1M tokens, Cached Input: $0.01 / 1M tokens, Output: $0.3 / 1M tokens

### Exclusive Benefits Available

To thank you for your support, we have prepared exclusive free credits for all new and existing users. You can log in and go to [Balance](https://platform.xiaomimimo.com/#/console/balance) to collect them.

### About the Billing System

Our billing system will officially launch in the near future. The exact date will be announced in an official announcement. Until then, API calls will remain free—your topped-up balance and free credits won’t be deducted for now.

### Recharge Rules

1. **Real-Name Authentication**: Chinese mainland users must complete individual real-name authentication before recharging. Enterprise authentication is not yet available; please stay tuned for updates. Other users can recharge directly without real-name authentication.

1. **Recharge Process**: Go to the [Balance](https://platform.xiaomimimo.com/#/console/balance) page to recharge. Chinese mainland users can use Xiaomi Pay, Alipay, or WeChat Pay. Other users can use common payment methods such as Apple Pay, Google Pay, and credit/debit cards.

1. **Balance Inquiry**: Recharged funds are generally credited to your account in real time. You can view recharge orders and bonus amounts on the [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge) page, and check your current balance on the [Balance](https://platform.xiaomimimo.com/#/console/balance) page. Once the billing system is activated, API calls will first deduct the complimentary free quota, followed by the recharged balance.

1. **Invoice Issuance**: Chinese mainland users can apply for electronic invoices by selecting successful recharge orders on the [Invoice](https://platform.xiaomimimo.com/#/console/invoice) page. Other users can download order receipts from the [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge) page.

1. **For more details, please refer to** [FAQ](https://platform.xiaomimimo.com/#/docs/faq?target=payment-issue).

### Contact Us

For assistance or business inquiries, feel free to reach out to us through the following channels:

- Email: support-mimo@xiaomi.com

- Scan the QR code at the bottom left to join the developer communication group

- Submit your feedback from [Contact Us](https://platform.xiaomimimo.com/#/contact)

We are committed to continuously optimizing our products and services to provide you with superior AI capabilities. Thank you again for your understanding and trust!

<p className="mb-[16px] w-full text-[14px] leading-[24px] lg:text-[16px] lg:leading-[28px] font-normal text-[#5C5C62]" style={{ textAlign: 'right' }}>**—— Xiaomi MiMo API Open Platform Team**</p>

<p className="mb-[16px] w-full text-[14px] leading-[24px] lg:text-[16px] lg:leading-[28px] font-normal text-[#5C5C62]" style={{ textAlign: 'right' }}>**January 20, 2026**</p>


--- DOCUMENT: MiMo-V2-Flash Release Note 2026/01/12 ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/news20260112.md

# MiMo-V2-Flash Release Note 2026/01/12

1. **Enhanced general capabilities:** Improved the model’s performance on a wide range of general-purpose tasks.

1. **Upgraded coding performance in Thinking mode:** Strengthened code generation quality in Thinking mode, especially for programming scenarios.

1. **Deep integration with Claude Code:** Fully supports using Thinking mode in Claude Code.

   - **Best practice:** Set Thinking as the default mode to achieve more stable, higher-quality code generation.

1. **Optimized Experience for Other Code Agents:**  Synchronized improvements to the interaction experience and generation quality across code assistant tools (Code Scaffolds) such as Kilo, Cline, and Roo.

1. **Improved Stability & Instruction Following:** Enhanced output stability and significantly improved adherence to specific output formats.

|  | **MiMo-v2-Flash-0112** | **MiMo-v2-Flash** |
| --- | --- | --- |
| **SWE-Bench Verified** <br />**Non-Thinking** | **73.3** | 73.4 |
| **SWE-Bench Verified Thinking** | **74.2** | - |
| **Arena-Hard(Hard Prompt)** <br />**Non-Thinking** | **52.7** | 46.0 |
| **Arena-Hard(Creative Writing)** <br />**Non-Thinking** | **86.0** | 78.3 |
| **Arena-Hard(Hard Prompt)**<br />**Thinking** | **58.3** | 54.1 |
| **Arena-Hard(Creative Writing)**<br />**Thinking** | **90.4** | 86.2 |

> Note: The model API call method and model name remain unchanged


--- DOCUMENT: MiMo Public Beta Free Access Extended ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/beta-free.md

# MiMo Public Beta Free Access Extended

Dear Developers,

Since the release of MiMo-V2-Flash, it has received widespread attention and enthusiastic support from users around the world. We appreciate your strong recognition and valuable feedback for the MiMo model! To reciprocate the enthusiastic support of our developers, we have decided to extend the public beta free trial period! The relevant adjustments are announced as follows:

### Extension of 20 days!

The free trial period originally scheduled to end at the end of December 2025 will be postponed to **14:00 (Beijing Time) on January 20, 2026**. During this period, users can continue to use the MiMo-V2-Flash model API for free, utilizing its core features, including efficient text generation, code processing, etc. This extension is aimed at repaying the trust and support of our users, while encouraging more users to participate in testing and provide valuable feedback. We will further optimize model performance, enhance user experience, and ensure comprehensive security testing before the official release.

### Payment capability system launch preview

The payment capability system of XiaomiMiMo API Platform will be enabled before the public beta ends and will undergo a trial run for about a week (the specific trial run period will be announced later). Users can top up their accounts during the trial period, but the service will not be charged at the time. Billing will start automatically and the balance will be consumed after the trial ends.To ensure normal use and stable service, we recommend that users recharge their accounts in advance.

Attached is the model API pricing: **Domestic: Input: ¥0.7 / 1M tokens, Cached Input: ¥0.07 / 1M tokens, Output: ¥2.1 / 1M tokens;International: Input: $0.1 / 1M tokens, Cached Input: $0.01 / 1M tokens, Output: $0.3 / 1M tokens.** Please stay tuned to the official website announcements and Open Platform WeChat group notifications.

We sincerely invite new and existing users to take advantage of the extended free public beta period to continue enjoying the intelligent experience brought by MiMo, and to actively share your usage experiences and suggestions. If you have any questions, please feel free to [contact us](https://platform.xiaomimimo.com/#/contact) or join the developer discussion group (scan the QR code in the lower left corner to join). Let's explore the boundaries of intelligence together.

<p className="mb-[16px] w-full text-[14px] leading-[24px] lg:text-[16px] lg:leading-[28px] font-normal text-[#5C5C62]" style={{ textAlign: 'right' }}>**—— Xiaomi MiMo API Open Platform Team**</p>


--- DOCUMENT: MiMo-V2-Flash Release 2025/12/16 ---
URL: https://platform.xiaomimimo.com/static/docs/news/previous-news/news20251216.md

# MiMo-V2-Flash: High-Efficiency Inference, Code & Agent Foundation Model

Xiaomi MiMo-V2-Flash is officially open-sourced today!!! It is a MoE (Mixture of Experts) model designed for extreme inference efficiency, with 309B total and 15B activated parameters. 

With an innovative hybrid attention and multi-layer MTP (Multi-Token Prediction) architecture, the model ranks **top 2 among all open-source models** across multiple agent evaluation benchmarks. Besides, its coding capability surpasses all open-source models and is comparable with Claude 4.5 Sonnet, while its **inference cost is only 2.5%** of Claude’s and its **generation speed is doubled** — pushing inference efficiency to the limit.

![图片](https://platform.xiaomimimo.com/static/YySMbAqyyoOKG6xVdbScif2UnYp.520e6755.png)

To foster open-source engagement, both the model weights and inference code are fully open-sourced under the MIT license. 

**The API is available free of charge for a limited time.** 

## Extreme Optimization of Cost and Speed

The API pricing for MiMo-V2-Flash is **$0.1 per million input tokens and $0.3 per million output tokens.** 

In the chart below, the horizontal axis compares speed and cost across leading models——MiMo-V2-Flash achieves both the lowest cost and the highest speed.

![图片](https://platform.xiaomimimo.com/static/N2uQbZmpaoHjhHxPZtjcjAz0nTf.eef43149.png)

## Architectural innovations designed for high-efficiency inference

Key architectural designs: 

- **Hybrid Attention:** We adopt a hybrid attention mechanism combining Global Attention and Sliding Window Attention (SWA) at a 1:5 ratio, where the window size of SWA is 128. During pre-training, we train the model with a context length of 32k, and extend it to 256k. Compared to mainstream Linear Attention approaches, extensive early-stage empirical studies show that SWA is simple, efficient, and practical, delivering stronger overall performance in general tasks, long-context handling, and reasoning. It also provides a fixed-size KV cache, making it easy to integrate with existing training and inference infrastructure.

![图片](https://platform.xiaomimimo.com/static/YcY9b26lOo8vdFxRcXMcStthnRe.ff06b4e2.png)

- **MTP Inference Acceleration**: We introduce MTP (Multi-Token Prediction) to strengthen the model's capability and speed up inference. During inference, MTP validates MTP tokens in parallel, breaking the memory bandwidth bottleneck of traditional decoding under large batch sizes. In practice, a 2.5×–3.7× real-world speedup is achieved with a 3-layer MTP setup.

![图片](https://platform.xiaomimimo.com/static/LGrtb2E7Soz2stxEoNpc9ucAnFf.fb860651.png)

## Related links

- Technical Report：[https://github.com/XiaomiMiMo/MiMo-V2-Flash/blob/main/paper.pdf](https://github.com/XiaomiMiMo/MiMo-V2-Flash/blob/main/paper.pdf)

- Model Weights：https://hf.co/XiaomiMiMo/MiMo-V2-Flash

- Github Repository：https://github.com/xiaomimimo/MiMo-V2-Flash

- Blog Post: https://mimo.xiaomi.com/blog/mimo-v2-flash

- LMSYS Blog：[https://lmsys.org/blog/2025-12-16-mimo-v2-flash](https://lmsys.org/blog/2025-12-16-mimo-v2-flash/)


--- DOCUMENT: OpenAI API ---
URL: https://platform.xiaomimimo.com/static/docs/api/chat/openai-api.md

# OpenAI API Compatibility

## Request Address

```bash
https://api.xiaomimimo.com/v1/chat/completions
```

## Request Headers

The API supports the following two authentication methods. Please choose one and add it to the request headers:

1. Method 1: `api-key` field authentication, format:
```json
api-key: $MIMO_API_KEY
Content-Type: application/json
```

1. Method 2: `Authorization: Bearer` authentication, format:
```json
Authorization: Bearer $MIMO_API_KEY
Content-Type: application/json
```

## Request body 

<InlineSchemaV2 schema={`[
  {
    "name": "messages",
    "type": "array",
    "isBold": true,
    "required": true,
    "description": "The current conversation message list.",
    "children": [
      {
        "name": "Developer message",
        "type": "object",
        "isBold": false,
        "description": "Developer-provided instructions that the model should follow, regardless of messages sent by the user.",
        "children": [
          {
            "name": "content",
            "type": [
              "string",
              "array"
            ],
            "isBold": true,
            "required": true,
            "description": "The contents of the developer message.",
            "children": [
              {
                "name": "Text content",
                "type": "string",
                "isBold": false,
                "description": "The contents of the developer message."
              },
              {
                "name": "Array of content parts",
                "type": "array",
                "isBold": false,
                "description": "An array of content parts with a defined type. For developer messages, only type <code class=\\"schema-inline-code\\">text</code> is supported.",
                "children": [
                  {
                    "name": "Text content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "text",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The text content."
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part."
                      }
                    ]
                  }
                ]
              }
            ]
          },
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "The role of the message author.<br />Available options: <code class=\\"schema-inline-code\\">developer</code>"
          },
          {
            "name": "name",
            "type": "string",
            "isBold": true,
            "required": false,
            "description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
          }
        ]
      },
      {
        "name": "System message",
        "type": "object",
        "isBold": false,
        "description": "Developer-provided instructions that the model should follow, regardless of messages sent by the user.",
        "children": [
          {
            "name": "content",
            "type": [
              "string",
              "array"
            ],
            "isBold": true,
            "required": true,
            "description": "The contents of the system message.",
            "children": [
              {
                "name": "Text content",
                "type": "string",
                "isBold": false,
                "description": "The contents of the system message."
              },
              {
                "name": "Array of content parts",
                "type": "array",
                "isBold": false,
                "description": "An array of content parts with a defined type. For system messages, only type <code class=\\"schema-inline-code\\">text</code> is supported.",
                "children": [
                  {
                    "name": "Text content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "text",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The text content."
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part."
                      }
                    ]
                  }
                ]
              }
            ]
          },
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Role of the message author.<br />Available options: <code class=\\"schema-inline-code\\">system</code>"
          },
          {
            "name": "name",
            "type": "string",
            "isBold": true,
            "required": false,
            "description": "An optional name for the participant. Provides the model information to differentiate between participants of the same role."
          }
        ]
      },
      {
        "name": "User message",
        "type": "object",
        "isBold": false,
        "description": "Messages sent by an end user, containing prompts or additional context information.",
        "children": [
          {
            "name": "content",
            "type": [
              "string",
              "array"
            ],
            "isBold": true,
            "required": true,
            "description": "The contents of the user message.<br /><blockquote class=\\"schema-blockquote\\">Note: When generating audio using the <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code> model, messages with role <code class=\\"schema-inline-code\\">user</code> are required. You may provide an <code class=\\"schema-inline-code\\">assistant</code> role message to specify the text for audio synthesis. If <code class=\\"schema-inline-code\\">optimize_text_preview</code> is set to <code class=\\"schema-inline-code\\">true</code>, the <code class=\\"schema-inline-code\\">assistant</code> message can be omitted. Moreover, audio parameters can be configured via <code class=\\"schema-inline-code\\">audio</code>. For detailed usage, please refer to <a target=\\"_blank\\" rel=\\"noopener noreferrer\\" href=\\"https://platform.xiaomimimo.com/#/docs/usage-guide/speech-synthesis-v2.1\\">Speech Synthesis</a>.</blockquote>",
            "children": [
              {
                "name": "Text content",
                "type": "string",
                "isBold": false,
                "description": "The text contents of the message."
              },
              {
                "name": "Array of content parts",
                "type": "array",
                "isBold": false,
                "description": "An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text, image, audio or video inputs.<br /><blockquote class=\\"schema-blockquote\\">Currently, only the <code class=\\"schema-inline-code\\">mimo-v2.5</code> and <code class=\\"schema-inline-code\\">mimo-v2-omni</code> models support image, audio, or video input.</blockquote>",
                "children": [
                  {
                    "name": "Text content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "text",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The text content."
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part."
                      }
                    ]
                  },
                  {
                    "name": "Image content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "image_url",
                        "type": "object",
                        "isBold": true,
                        "required": true,
                        "children": [
                          {
                            "name": "url",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Either a URL of the image or the base64 encoded image data."
                          }
                        ]
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part.<br />Available options: <code class=\\"schema-inline-code\\">image_url</code>"
                      }
                    ]
                  },
                  {
                    "name": "Audio content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "input_audio",
                        "type": "object",
                        "isBold": true,
                        "required": true,
                        "children": [
                          {
                            "name": "data",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Either a URL of the audio or the base64 encoded audio data."
                          }
                        ]
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part.<br />Available options: <code class=\\"schema-inline-code\\">input_audio</code>"
                      }
                    ]
                  },
                  {
                    "name": "Video content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "video_url",
                        "type": "object",
                        "isBold": true,
                        "required": true,
                        "children": [
                          {
                            "name": "url",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Either a URL of the video or the base64 encoded video data."
                          }
                        ]
                      },
                      {
                        "name": "fps",
                        "type": "number",
                        "isBold": true,
                        "required": false,
                        "defaultValue": "2",
                        "description": "Number of frames sampled per second.<br />Required range: <code class=\\"schema-inline-code\\">[0.1, 10.0]</code>"
                      },
                      {
                        "name": "media_resolution",
                        "type": "string",
                        "isBold": true,
                        "required": false,
                        "defaultValue": "default",
                        "description": "Resolution level.<br />Available options: <code class=\\"schema-inline-code\\">default</code>, <code class=\\"schema-inline-code\\">max</code>"
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part.<br />Available options: <code class=\\"schema-inline-code\\">video_url</code>"
                      }
                    ]
                  }
                ]
              }
            ]
          },
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Role of the message author.<br />Available options: <code class=\\"schema-inline-code\\">user</code>"
          },
          {
            "name": "name",
            "type": "string",
            "isBold": true,
            "required": false,
            "description": "An optional name for the participant. Provides model information to differentiate between participants of the same role."
          }
        ]
      },
      {
        "name": "Assistant message",
        "type": "object",
        "isBold": false,
        "description": "Messages sent by the model in response to user messages.",
        "children": [
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Role of the message author.<br />Available options: <code class=\\"schema-inline-code\\">assistant</code>"
          },
          {
            "name": "content",
            "type": [
              "string",
              "array"
            ],
            "isBold": true,
            "required": false,
            "description": "The contents of the assistant message. Required unless <code class=\\"schema-inline-code\\">tool_calls</code> is specified.<br /><blockquote class=\\"schema-blockquote\\">Note: To generate audio, you must add a message with role set to <code class=\\"schema-inline-code\\">assistant</code>, which needs to specify the text for speech synthesis. When using the <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code> model, a message with the role of <code class=\\"schema-inline-code\\">user</code> is required. If <code class=\\"schema-inline-code\\">optimize_text_preview</code> is set to <code class=\\"schema-inline-code\\">true</code>, the <code class=\\"schema-inline-code\\">assistant</code> message can be omitted. Additionally, audio parameters can be configured via <code class=\\"schema-inline-code\\">audio</code>. For detailed usage, please refer to <a target=\\"_blank\\" rel=\\"noopener noreferrer\\" href=\\"https://platform.xiaomimimo.com/#/docs/usage-guide/speech-synthesis-v2.1\\">Speech Synthesis</a>.</blockquote>",
            "children": [
              {
                "name": "Text content",
                "type": "string",
                "isBold": false,
                "description": "The contents of the assistant message."
              },
              {
                "name": "Array of content parts",
                "type": "array",
                "isBold": false,
                "description": "An array of content parts with a defined type. Can be one or more of type <code class=\\"schema-inline-code\\">text</code>.",
                "children": [
                  {
                    "name": "Text content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "text",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The text content."
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part."
                      }
                    ]
                  }
                ]
              }
            ]
          },
          {
            "name": "name",
            "type": "string",
            "isBold": true,
            "required": false,
            "description": "An optional name for the participant. Provides model information to differentiate between participants of the same role."
          },
          {
            "name": "tool_calls",
            "type": "array",
            "isBold": true,
            "required": false,
            "description": "The tool calls generated by the model, such as function calls.",
            "children": [
              {
                "name": "Function tool call",
                "type": "object",
                "isBold": false,
                "description": "A call to a function tool created by the model.",
                "children": [
                  {
                    "name": "function",
                    "type": "object",
                    "isBold": true,
                    "required": true,
                    "description": "The function that the model called.",
                    "children": [
                      {
                        "name": "arguments",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
                      },
                      {
                        "name": "name",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The name of the function to call."
                      }
                    ]
                  },
                  {
                    "name": "id",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The ID of the tool call."
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "Tool type. Currently, only <code class=\\"schema-inline-code\\">function</code> is supported."
                  }
                ]
              }
            ]
          }
        ]
      },
      {
        "name": "Tool message",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "content",
            "type": [
              "string",
              "array"
            ],
            "isBold": true,
            "required": true,
            "description": "The contents of the tool message.",
            "children": [
              {
                "name": "Text content",
                "type": "string",
                "isBold": false,
                "description": "The contents of the tool message."
              },
              {
                "name": "Array of content parts",
                "type": "array",
                "isBold": false,
                "description": "An array of content parts with a defined type. For tool messages, only type <code class=\\"schema-inline-code\\">text</code> is supported.",
                "children": [
                  {
                    "name": "Text content part",
                    "type": "object",
                    "isBold": false,
                    "children": [
                      {
                        "name": "text",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The text content."
                      },
                      {
                        "name": "type",
                        "type": "string",
                        "isBold": true,
                        "required": true,
                        "description": "The type of the content part."
                      }
                    ]
                  }
                ]
              }
            ]
          },
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Role of the message author.<br />Available options: <code class=\\"schema-inline-code\\">tool</code>"
          },
          {
            "name": "tool_call_id",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Tool call that this message is responding to."
          }
        ]
      }
    ]
  },
  {
    "name": "model",
    "type": "string",
    "isBold": true,
    "required": true,
    "description": "Model ID is used to generate the response.<br />Available options: <code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>, <code class=\\"schema-inline-code\\">mimo-v2-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2-flash</code>"
  },
  {
    "name": "audio",
    "type": "object",
    "isBold": true,
    "required": false,
    "description": "Parameters for audio output. For details, please refer to <a target=\\"_blank\\" rel=\\"noopener noreferrer\\" href=\\"https://platform.xiaomimimo.com/#/docs/usage-guide/speech-synthesis-v2.1\\">Speech Synthesis</a>.<br /><blockquote class=\\"schema-blockquote\\">Note: To generate audio, you must add a message with role set to <code class=\\"schema-inline-code\\">assistant</code>, which needs to specify the text for speech synthesis. Additionally, when using the <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code> model, a message with the role of <code class=\\"schema-inline-code\\">user</code> is required. If <code class=\\"schema-inline-code\\">optimize_text_preview</code> is set to <code class=\\"schema-inline-code\\">true</code>, the <code class=\\"schema-inline-code\\">assistant</code> message can be omitted. For detailed usage, please refer to <a target=\\"_blank\\" rel=\\"noopener noreferrer\\" href=\\"https://platform.xiaomimimo.com/#/docs/usage-guide/speech-synthesis-v2.1\\">Speech Synthesis</a>.</blockquote><blockquote class=\\"schema-blockquote\\">Currently, only the <code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code> and <code class=\\"schema-inline-code\\">mimo-v2-tts</code> models are supported.</blockquote>",
    "children": [
      {
        "name": "format",
        "type": "string",
        "isBold": true,
        "required": false,
        "defaultValue": "wav",
        "description": "Specifies the output audio format. Default: <code class=\\"schema-inline-code\\">wav</code>, or <code class=\\"schema-inline-code\\">pcm</code> when you set <code class=\\"schema-inline-code\\">stream: true</code>.<br /><blockquote class=\\"schema-blockquote\\">Passing in <code class=\\"schema-inline-code\\">pcm</code> or <code class=\\"schema-inline-code\\">pcm16</code> both indicate specifying the use of the <code class=\\"schema-inline-code\\">pcm16</code> format.</blockquote>Available options: <code class=\\"schema-inline-code\\">wav</code>, <code class=\\"schema-inline-code\\">mp3</code>, <code class=\\"schema-inline-code\\">pcm</code>, <code class=\\"schema-inline-code\\">pcm16</code>"
      },
      {
        "name": "optimize_text_preview",
        "type": "boolean",
        "isBold": true,
        "required": false,
        "defaultValue": "false",
        "description": "Enables intelligent optimization of the target audio broadcast text.<br />When set to <code class=\\"schema-inline-code\\">true</code>, the input target text is intelligently polished; if no target text is provided, a broadcast-adapted target text is automatically generated. The finalized processed text is then fed into the model for speech synthesis.<br /><blockquote class=\\"schema-blockquote\\">Note: When this parameter is set to <code class=\\"schema-inline-code\\">true</code>, the <code class=\\"schema-inline-code\\">assistant</code> role message for specifying speech synthesis content can be omitted.</blockquote><blockquote class=\\"schema-blockquote\\">Currently, only the <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code> model is supported.</blockquote>"
      },
      {
        "name": "voice",
        "type": "string",
        "isBold": true,
        "description": "The voice ID of the built-in voice or the base64 encoding of the audio sample.<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2-tts</code>: This field is optional and only supports using built-in voices, with the default value being <code class=\\"schema-inline-code\\">mimo_default</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code>: This field is required and only supports passing in the base64 encoding of audio samples, and only supports passing in audio sample files in <code class=\\"schema-inline-code\\">mp3</code> and <code class=\\"schema-inline-code\\">wav</code> formats</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code> does not support this field</li></ul>Available options:<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-tts</code>: <code class=\\"schema-inline-code\\">mimo_default</code>, <code class=\\"schema-inline-code\\">default_en</code>, <code class=\\"schema-inline-code\\">default_zh</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>: <code class=\\"schema-inline-code\\">mimo_default</code>, <code class=\\"schema-inline-code\\">冰糖</code>, <code class=\\"schema-inline-code\\">茉莉</code>, <code class=\\"schema-inline-code\\">苏打</code>, <code class=\\"schema-inline-code\\">白桦</code>, <code class=\\"schema-inline-code\\">Mia</code>, <code class=\\"schema-inline-code\\">Chloe</code>, <code class=\\"schema-inline-code\\">Milo</code>, <code class=\\"schema-inline-code\\">Dean</code></li></ul>"
      }
    ]
  },
  {
    "name": "frequency_penalty",
    "type": [
      "number",
      "null"
    ],
    "isBold": true,
    "required": false,
    "defaultValue": "0",
    "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.<br />Required range: <code class=\\"schema-inline-code\\">[-2.0, 2.0]</code>"
  },
  {
    "name": "max_completion_tokens",
    "type": [
      "integer",
      "null"
    ],
    "isBold": true,
    "required": false,
    "description": "An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-flash</code>: default <code class=\\"schema-inline-code\\">65536</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>: default <code class=\\"schema-inline-code\\">131072</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>: default <code class=\\"schema-inline-code\\">32768</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2-tts</code>: default <code class=\\"schema-inline-code\\">8192</code>, required range is <code class=\\"schema-inline-code\\">[1, 8192]</code></li></ul>Required range: <code class=\\"schema-inline-code\\">[1, 131072]</code>"
  },
  {
    "name": "presence_penalty",
    "type": [
      "number",
      "null"
    ],
    "isBold": true,
    "required": false,
    "defaultValue": "0",
    "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.<br />Required range: <code class=\\"schema-inline-code\\">[-2.0, 2.0]</code>"
  },
  {
    "name": "response_format",
    "type": "object",
    "isBold": true,
    "required": false,
    "description": "An object specifying the format that the model must output.<br /><blockquote class=\\"schema-blockquote\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code> and <code class=\\"schema-inline-code\\">mimo-v2-tts</code> models are not supported.</blockquote>",
    "children": [
      {
        "name": "Text",
        "type": "object",
        "isBold": false,
        "description": "Default response format. Used to generate text responses.",
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "The type of response format being defined. Always <code class=\\"schema-inline-code\\">text</code>."
          }
        ]
      },
      {
        "name": "JSON object",
        "type": "object",
        "isBold": false,
        "description": "JSON object response format. Note that the model will not generate JSON without a system or user message instructing it to do so.",
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "The type of response format being defined. Always <code class=\\"schema-inline-code\\">json_object</code>."
          }
        ]
      }
    ]
  },
  {
    "name": "stop",
    "type": [
      "string",
      "array",
      "null"
    ],
    "isBold": true,
    "required": false,
    "defaultValue": "null",
    "description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.<br /><blockquote class=\\"schema-blockquote\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code> and <code class=\\"schema-inline-code\\">mimo-v2-tts</code> models are not supported.</blockquote>"
  },
  {
    "name": "stream",
    "type": [
      "boolean",
      "null"
    ],
    "isBold": true,
    "required": false,
    "defaultValue": "false",
    "description": "If set to true, the model response data will be streamed to the client as it is generated using server-sent events."
  },
  {
    "name": "thinking",
    "type": "object",
    "isBold": true,
    "required": false,
    "description": "This parameter is used to control whether the model enables the chain of thought.<br /><blockquote class=\\"schema-blockquote\\">Note: During the multi-turn tool calls process in thinking mode, the model returns a <code class=\\"schema-inline-code\\">reasoning_content</code> field alongside <code class=\\"schema-inline-code\\">tool_calls</code>. To continue the conversation, it is recommended to keep all previous <code class=\\"schema-inline-code\\">reasoning_content</code> in the <code class=\\"schema-inline-code\\">messages</code> array for each subsequent request to achieve the best performance.</blockquote><blockquote class=\\"schema-blockquote\\">In thinking mode, the <code class=\\"schema-inline-code\\">mimo-v2.5-pro</code> and <code class=\\"schema-inline-code\\">mimo-v2.5</code> models do not support customizing the <code class=\\"schema-inline-code\\">temperature</code> parameter. Even if this parameter is passed in, it will be forcibly overridden and take effect with the model's recommended default value of <code class=\\"schema-inline-code\\">1.0</code>.</blockquote><blockquote class=\\"schema-blockquote\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code> and <code class=\\"schema-inline-code\\">mimo-v2-tts</code> models are not supported.</blockquote>",
    "children": [
      {
        "name": "type",
        "type": "string",
        "isBold": true,
        "required": true,
        "description": "Whether to enable the chain of thought.<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-flash</code>: default <code class=\\"schema-inline-code\\">disabled</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>: default <code class=\\"schema-inline-code\\">enabled</code></li></ul>Available options: <code class=\\"schema-inline-code\\">enabled</code>, <code class=\\"schema-inline-code\\">disabled</code>"
      }
    ]
  },
  {
    "name": "temperature",
    "type": "number",
    "isBold": true,
    "required": false,
    "description": "What sampling temperature to use, between 0 and 1.5. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or <code class=\\"schema-inline-code\\">top_p</code> but not both.<br /><blockquote class=\\"schema-blockquote\\">In thinking mode, the <code class=\\"schema-inline-code\\">mimo-v2.5-pro</code> and <code class=\\"schema-inline-code\\">mimo-v2.5</code> models do not support customizing the <code class=\\"schema-inline-code\\">temperature</code> parameter. Even if this parameter is passed in, it will be forcibly overridden and take effect with the model's recommended default value of <code class=\\"schema-inline-code\\">1.0</code>.</blockquote><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-flash</code>: default <code class=\\"schema-inline-code\\">0.3</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>: default <code class=\\"schema-inline-code\\">1.0</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2-tts</code>: default <code class=\\"schema-inline-code\\">0.6</code></li></ul>Required range: <code class=\\"schema-inline-code\\">[0, 1.5]</code>"
  },
  {
    "name": "tool_choice",
    "type": "string",
    "isBold": true,
    "required": false,
    "description": "Controls how the model selects a tool.<br /><blockquote class=\\"schema-blockquote\\">Note: When a value other than <code class=\\"schema-inline-code\\">auto</code> is passed to <code class=\\"schema-inline-code\\">tool_choice</code>, the backend will remove this field by default, and the model response behavior will still be equivalent to the <code class=\\"schema-inline-code\\">auto</code> mode (this logic is subject to future adjustments).</blockquote><blockquote class=\\"schema-blockquote\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code> and <code class=\\"schema-inline-code\\">mimo-v2-tts</code> models are not supported.</blockquote>Available options: <code class=\\"schema-inline-code\\">auto</code>"
  },
  {
    "name": "tools",
    "type": "array",
    "isBold": true,
    "required": false,
    "description": "A list of tools the model may call. You can provide function tools.<br /><blockquote class=\\"schema-blockquote\\">Note: During the multi-turn tool calls process in thinking mode, the model returns a <code class=\\"schema-inline-code\\">reasoning_content</code> field alongside <code class=\\"schema-inline-code\\">tool_calls</code>. To continue the conversation, it is recommended to keep all previous <code class=\\"schema-inline-code\\">reasoning_content</code> in the <code class=\\"schema-inline-code\\">messages</code> array for each subsequent request to achieve the best performance.</blockquote><blockquote class=\\"schema-blockquote\\"><code class=\\"schema-inline-code\\">mimo-v2.5-tts</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voicedesign</code>, <code class=\\"schema-inline-code\\">mimo-v2.5-tts-voiceclone</code> and <code class=\\"schema-inline-code\\">mimo-v2-tts</code> models are not supported.</blockquote>",
    "children": [
      {
        "name": "Function tool",
        "type": "object",
        "isBold": false,
        "description": "A function tool that can be used to generate a response.",
        "children": [
          {
            "name": "function",
            "type": "object",
            "isBold": true,
            "required": true,
            "children": [
              {
                "name": "name",
                "type": "string",
                "isBold": true,
                "required": true,
                "description": "The name of the tool function. Must be <code class=\\"schema-inline-code\\">a-z</code>, <code class=\\"schema-inline-code\\">A-Z</code>, <code class=\\"schema-inline-code\\">0-9</code>, or contain underscores (<code class=\\"schema-inline-code\\">_</code>) and dashes (<code class=\\"schema-inline-code\\">-</code>), with a maximum length of 64.<br />Required string length: <code class=\\"schema-inline-code\\">1 - 64</code>"
              },
              {
                "name": "description",
                "type": "string",
                "isBold": true,
                "required": false,
                "description": "A description of what the function does, used by the model to choose when and how to call the function."
              },
              {
                "name": "parameters",
                "type": "object",
                "isBold": true,
                "required": false,
                "description": "The parameters the functions accept, described as a JSON Schema object.<br />Omitting <code class=\\"schema-inline-code\\">parameters</code> defines a function with an empty parameter list."
              },
              {
                "name": "strict",
                "type": "boolean",
                "isBold": true,
                "required": false,
                "defaultValue": "false",
                "description": "Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the <code class=\\"schema-inline-code\\">parameters</code> field. Only a subset of JSON Schema is supported when <code class=\\"schema-inline-code\\">strict</code> is <code class=\\"schema-inline-code\\">true</code>."
              }
            ]
          },
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Tool type. Currently, only <code class=\\"schema-inline-code\\">function</code> is supported."
          }
        ]
      },
      {
        "name": "Web search tool",
        "type": "object",
        "isBold": false,
        "description": "A web search tool that can be used to generate a response.For details, please refer to <a target=\\"_blank\\" rel=\\"noopener noreferrer\\" href=\\"https://platform.xiaomimimo.com/#/docs/usage-guide/tool-calling/web-search\\">Web Search</a>.<br /><blockquote class=\\"schema-blockquote\\">Note：<a target=\\"_blank\\" rel=\\"noopener noreferrer\\" href=\\"https://platform.xiaomimimo.com/#/console/plugin\\">Web Search plugin</a> must be activated before use.</blockquote>",
        "children": [
          {
            "name": "user_location",
            "type": "object",
            "isBold": true,
            "required": false,
            "children": [
              {
                "name": "type",
                "type": "string",
                "isBold": true,
                "required": true,
                "description": "approximate"
              },
              {
                "name": "country",
                "type": "string",
                "isBold": true,
                "required": false,
                "description": "country"
              },
              {
                "name": "region",
                "type": "string",
                "isBold": true,
                "required": false,
                "description": "region"
              },
              {
                "name": "city",
                "type": "string",
                "isBold": true,
                "required": false,
                "description": "city"
              },
              {
                "name": "district",
                "type": "string",
                "isBold": true,
                "required": false,
                "description": "district"
              },
              {
                "name": "longitude",
                "type": "long",
                "isBold": true,
                "required": false,
                "description": "longitude<strong> </strong>"
              },
              {
                "name": "latitude",
                "type": "long",
                "isBold": true,
                "required": false,
                "description": "latitude"
              }
            ]
          },
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "Tool type. Currently, only <code class=\\"schema-inline-code\\">web_search</code> is supported."
          },
          {
            "name": "force_search",
            "type": "string",
            "isBold": true,
            "required": false,
            "defaultValue": "false",
            "description": "Whether to enable forced search. <code class=\\"schema-inline-code\\">true</code> for forced search, <code class=\\"schema-inline-code\\">false</code> for the model to decide whether search is needed."
          },
          {
            "name": "max_keyword",
            "type": "integer",
            "isBold": true,
            "required": false,
            "defaultValue": "5",
            "description": "Limit the maximum number of keywords that can be used in a single search.<br />Required range: <code class=\\"schema-inline-code\\">[1, 50]</code>"
          },
          {
            "name": "limit",
            "type": "integer",
            "isBold": true,
            "required": false,
            "defaultValue": "5",
            "description": "Limit the maximum number of results returned by a single search operation.<br />Required range: <code class=\\"schema-inline-code\\">[1, 50]</code>"
          }
        ]
      }
    ]
  },
  {
    "name": "top_p",
    "type": "number",
    "isBold": true,
    "required": false,
    "defaultValue": "0.95",
    "description": "The probability threshold for nucleus sampling, which controls the diversity of the text that the model generates. A higher <code class=\\"schema-inline-code\\">top_p</code> value results in more diverse text. A lower <code class=\\"schema-inline-code\\">top_p</code> value results in more deterministic text.<br />Because both <code class=\\"schema-inline-code\\">temperature</code> and <code class=\\"schema-inline-code\\">top_p</code> control the diversity of the generated text, we recommend that you set only one of them.<br />Required range: <code class=\\"schema-inline-code\\">[0.01, 1.0]</code>"
  }
]`} />

## Chat response object (non-streaming output)

<InlineSchemaV2 schema={`[
  {
    "name": "choices",
    "type": "array",
    "isBold": true,
    "description": "A list of chat completion choices.",
    "children": [
      {
        "name": "finish_reason",
        "type": "string",
        "isBold": true,
        "description": "The reason the model stopped generating tokens. This will be <code class=\\"schema-inline-code\\">stop</code> if the model hit a natural stop point or a provided stop sequence, <code class=\\"schema-inline-code\\">length</code> if the maximum number of tokens specified in the request was reached, <code class=\\"schema-inline-code\\">tool_calls</code> if the model called a tool, <code class=\\"schema-inline-code\\">content_filter</code> if content was omitted due to a flag from our content filters, <code class=\\"schema-inline-code\\">repetition_truncation</code> if the model detects repetition."
      },
      {
        "name": "index",
        "type": "integer",
        "isBold": true,
        "description": "The index of the choice in the list of choices."
      },
      {
        "name": "message",
        "type": "object",
        "isBold": true,
        "description": "A chat completion message generated by the model.",
        "children": [
          {
            "name": "content",
            "type": "string",
            "isBold": true,
            "description": "The contents of the message."
          },
          {
            "name": "reasoning_content",
            "type": "string",
            "isBold": true,
            "description": "The reasoning contents of the assistant message, before the final answer."
          },
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "description": "The role of the author of this message."
          },
          {
            "name": "tool_calls",
            "type": "array",
            "isBold": true,
            "description": "After a function call is initiated, the model returns the tool to be called and the parameters that are Required for the call. This parameter can contain one or more tool response objects.",
            "children": [
              {
                "name": "Function tool call",
                "type": "object",
                "isBold": false,
                "description": "A call to a function tool created by the model.",
                "children": [
                  {
                    "name": "function",
                    "type": "object",
                    "isBold": true,
                    "description": "The function that the model called.",
                    "children": [
                      {
                        "name": "arguments",
                        "type": "string",
                        "isBold": true,
                        "description": "The arguments to call the function with, as generated by the model in JSON format. Note      that the model does not always generate valid JSON, and may hallucinate parameters not    defined by your function schema. Validate the arguments in your code before calling your function."
                      },
                      {
                        "name": "name",
                        "type": "string",
                        "isBold": true,
                        "description": "The name of the function to call."
                      }
                    ]
                  },
                  {
                    "name": "id",
                    "type": "string",
                    "isBold": true,
                    "description": "The ID of the tool call."
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "description": "The type of the tool. Currently, only <code class=\\"schema-inline-code\\">function</code> is supported."
                  }
                ]
              }
            ]
          },
          {
            "name": "annotations",
            "type": "array",
            "isBold": true,
            "description": "After web search, the model returns annotations for all referenced URLs.",
            "children": [
              {
                "name": "web_search tool call",
                "type": "object",
                "isBold": false,
                "description": "A call to a web search tool created by the model.",
                "children": [
                  {
                    "name": "logo_url",
                    "type": "string",
                    "isBold": true,
                    "description": "Logo url."
                  },
                  {
                    "name": "publish_time",
                    "type": "string",
                    "isBold": true,
                    "description": "Publish time."
                  },
                  {
                    "name": "site_name",
                    "type": "string",
                    "isBold": true,
                    "description": "Site name."
                  },
                  {
                    "name": "summary",
                    "type": "string",
                    "isBold": true,
                    "description": "Summary."
                  },
                  {
                    "name": "title",
                    "type": "string",
                    "isBold": true,
                    "description": "Title."
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "description": "Type."
                  },
                  {
                    "name": "url",
                    "type": "string",
                    "isBold": true,
                    "description": "Url."
                  }
                ]
              }
            ]
          },
          {
            "name": "error_message",
            "type": "string",
            "isBold": true,
            "description": "Error message of web search."
          },
          {
            "name": "audio",
            "type": "object",
            "isBold": true,
            "description": "If the audio output is requested, this object contains data about the audio response from the model.",
            "children": [
              {
                "name": "id",
                "type": "string",
                "isBold": true,
                "description": "Unique identifier for this audio response."
              },
              {
                "name": "data",
                "type": "string",
                "isBold": true,
                "description": "Base64 encoded audio bytes generated by the model, in the format specified in the request."
              },
              {
                "name": "expires_at",
                "type": [
                  "number",
                  "null"
                ],
                "isBold": true,
                "description": "The Unix timestamp (in seconds) for when this audio response expires. Currently always <code class=\\"schema-inline-code\\">null</code>."
              },
              {
                "name": "transcript",
                "type": [
                  "string",
                  "null"
                ],
                "isBold": true,
                "description": "Transcript of the audio generated by the model. Currently always <code class=\\"schema-inline-code\\">null</code>."
              }
            ]
          },
          {
            "name": "final_text_preview",
            "type": "string",
            "isBold": true,
            "description": "The final audio broadcast text after intelligent optimization and polishing. This field is only returned when the request parameter <code class=\\"schema-inline-code\\">optimize_text_preview</code> is set to <code class=\\"schema-inline-code\\">true</code>."
          }
        ]
      }
    ]
  },
  {
    "name": "created",
    "type": "integer",
    "isBold": true,
    "description": "The Unix timestamp (in seconds) of when the chat completion was created."
  },
  {
    "name": "id",
    "type": "string",
    "isBold": true,
    "description": "A unique identifier for the chat completion."
  },
  {
    "name": "model",
    "type": "string",
    "isBold": true,
    "description": "The model to generate the completion."
  },
  {
    "name": "object",
    "type": "string",
    "isBold": true,
    "description": "The object type, which is always <code class=\\"schema-inline-code\\">chat.completion</code>."
  },
  {
    "name": "usage",
    "type": [
      "object",
      "null"
    ],
    "isBold": true,
    "description": "Usage statistics for the completion request.",
    "children": [
      {
        "name": "completion_tokens",
        "type": "integer",
        "isBold": true,
        "description": "Number of tokens in the generated completion."
      },
      {
        "name": "prompt_tokens",
        "type": "integer",
        "isBold": true,
        "description": "Number of tokens in the prompt."
      },
      {
        "name": "total_tokens",
        "type": "integer",
        "isBold": true,
        "description": "Total number of tokens used in the request (prompt + completion)."
      },
      {
        "name": "completion_tokens_details",
        "type": "object",
        "isBold": true,
        "description": "Breakdown of tokens used in a completion.",
        "children": [
          {
            "name": "reasoning_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Tokens generated by the model for reasoning."
          }
        ]
      },
      {
        "name": "prompt_tokens_details",
        "type": "object",
        "isBold": true,
        "description": "Breakdown of tokens used in the prompt.",
        "children": [
          {
            "name": "cached_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Number of tokens served from cache."
          },
          {
            "name": "audio_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Audio input tokens present in the prompt."
          },
          {
            "name": "image_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Image input tokens present in the prompt."
          },
          {
            "name": "video_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Video input tokens present in the prompt."
          }
        ]
      },
      {
        "name": "web_search_usage",
        "type": "object",
        "isBold": true,
        "description": "Detailed usage of the web search API.",
        "children": [
          {
            "name": "tool_usage",
            "type": "integer",
            "isBold": true,
            "description": "Number of API calls in web search."
          },
          {
            "name": "page_usage",
            "type": "integer",
            "isBold": true,
            "description": "Number of web pages returned by the web search API."
          }
        ]
      }
    ]
  }
]`} />

## Chat response chunk object (streaming output)
<InlineSchemaV2 schema={`[
  {
    "name": "choices",
    "type": "array",
    "isBold": true,
    "description": "A list of chat completion choices.",
    "children": [
      {
        "name": "delta",
        "type": "object",
        "isBold": true,
        "description": "A chat completion delta generated by streamed model responses.",
        "children": [
          {
            "name": "content",
            "type": "string",
            "isBold": true,
            "description": "The contents of the chunk message."
          },
          {
            "name": "reasoning_content",
            "type": "string",
            "isBold": true,
            "description": "The reasoning contents of the assistant message, before the final answer."
          },
          {
            "name": "role",
            "type": "string",
            "isBold": true,
            "description": "The role of the author of this message."
          },
          {
            "name": "tool_calls",
            "type": "array",
            "isBold": true,
            "description": "The tools to be called by the model and the parameters Required for the calls. It can contain one or more tool response objects.",
            "children": [
              {
                "name": "index",
                "type": "integer",
                "isBold": true,
                "description": "The index of the called tool in the <code class=\\"schema-inline-code\\">tool_calls</code> list, starting from 0."
              },
              {
                "name": "function",
                "type": "object",
                "isBold": true,
                "description": "The function to be called.",
                "children": [
                  {
                    "name": "arguments",
                    "type": "string",
                    "isBold": true,
                    "description": "The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
                  },
                  {
                    "name": "name",
                    "type": "string",
                    "isBold": true,
                    "description": "The name of the function to call."
                  }
                ]
              },
              {
                "name": "id",
                "type": "string",
                "isBold": true,
                "description": "The ID of the tool call."
              },
              {
                "name": "type",
                "type": "string",
                "isBold": true,
                "description": "The type of the tool. Currently, only <code class=\\"schema-inline-code\\">function</code> is supported."
              }
            ]
          },
          {
            "name": "annotations",
            "type": "array",
            "isBold": true,
            "description": "After web search, the model returns annotations for all referenced URLs.",
            "children": [
              {
                "name": "web_search tool call",
                "type": "object",
                "isBold": false,
                "description": "A call to a web search tool created by the model.",
                "children": [
                  {
                    "name": "logo_url",
                    "type": "string",
                    "isBold": true,
                    "description": "Logo url."
                  },
                  {
                    "name": "publish_time",
                    "type": "string",
                    "isBold": true,
                    "description": "Publish time."
                  },
                  {
                    "name": "site_name",
                    "type": "string",
                    "isBold": true,
                    "description": "Site name."
                  },
                  {
                    "name": "summary",
                    "type": "string",
                    "isBold": true,
                    "description": "Summary."
                  },
                  {
                    "name": "title",
                    "type": "string",
                    "isBold": true,
                    "description": "Title."
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "description": "Type."
                  },
                  {
                    "name": "url",
                    "type": "string",
                    "isBold": true,
                    "description": "Url."
                  }
                ]
              }
            ]
          },
          {
            "name": "error_message",
            "type": "string",
            "isBold": true,
            "description": "Error message of web search."
          },
          {
            "name": "audio",
            "type": [
              "object",
              "null"
            ],
            "isBold": true,
            "description": "If the audio output modality is requested, this object contains data about the audio response from the model.",
            "children": [
              {
                "name": "id",
                "type": "string",
                "isBold": true,
                "description": "Unique identifier for this audio response."
              },
              {
                "name": "data",
                "type": "string",
                "isBold": true,
                "description": "Base64 encoded audio bytes generated by the model, in the format specified in the request."
              },
              {
                "name": "expires_at",
                "type": [
                  "number",
                  "null"
                ],
                "isBold": true,
                "description": "The Unix timestamp (in seconds) for when this audio response expires. Currently always <code class=\\"schema-inline-code\\">null</code>."
              },
              {
                "name": "transcript",
                "type": [
                  "string",
                  "null"
                ],
                "isBold": true,
                "description": "Transcript of the audio generated by the model. Currently always <code class=\\"schema-inline-code\\">null</code>."
              }
            ]
          },
          {
            "name": "final_text_preview",
            "type": "string",
            "isBold": true,
            "description": "The final audio broadcast text after intelligent optimization and polishing. This field is only returned when the request parameter <code class=\\"schema-inline-code\\">optimize_text_preview</code> is set to <code class=\\"schema-inline-code\\">true</code>."
          }
        ]
      },
      {
        "name": "finish_reason",
        "type": [
          "string",
          "null"
        ],
        "isBold": true,
        "description": "The reason the model stopped generating tokens. This will be <code class=\\"schema-inline-code\\">stop</code> if the model hit a natural stop point or a provided stop sequence, <code class=\\"schema-inline-code\\">length</code> if the maximum number of tokens specified in the request was reached, <code class=\\"schema-inline-code\\">tool_calls</code> if the model called a tool, <code class=\\"schema-inline-code\\">content_filter</code> if content was omitted due to a flag from our content filters, <code class=\\"schema-inline-code\\">repetition_truncation</code> if the model detects repetition."
      },
      {
        "name": "index",
        "type": "integer",
        "isBold": true,
        "description": "The index of the choice in the list of choices."
      }
    ]
  },
  {
    "name": "created",
    "type": "integer",
    "isBold": true,
    "description": "The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp."
  },
  {
    "name": "id",
    "type": "string",
    "isBold": true,
    "description": "A unique identifier for the chat completion.  Each chunk has the same ID."
  },
  {
    "name": "model",
    "type": "string",
    "isBold": true,
    "description": "The model to generate the completion."
  },
  {
    "name": "object",
    "type": "string",
    "isBold": true,
    "description": "The object type, which is always <code class=\\"schema-inline-code\\">chat.completion.chunk</code>."
  },
  {
    "name": "usage",
    "type": [
      "object",
      "null"
    ],
    "isBold": true,
    "description": "Usage statistics for the completion request.",
    "children": [
      {
        "name": "completion_tokens",
        "type": "integer",
        "isBold": true,
        "description": "Number of tokens in the generated completion."
      },
      {
        "name": "prompt_tokens",
        "type": "integer",
        "isBold": true,
        "description": "Number of tokens in the prompt."
      },
      {
        "name": "total_tokens",
        "type": "integer",
        "isBold": true,
        "description": "Total number of tokens used in the request (prompt + completion)."
      },
      {
        "name": "completion_tokens_details",
        "type": "object",
        "isBold": true,
        "description": "Breakdown of tokens used in a completion.",
        "children": [
          {
            "name": "reasoning_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Tokens generated by the model for reasoning."
          }
        ]
      },
      {
        "name": "prompt_tokens_details",
        "type": "object",
        "isBold": true,
        "description": "Breakdown of tokens used in the prompt.",
        "children": [
          {
            "name": "cached_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Number of tokens served from cache."
          },
          {
            "name": "audio_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Audio input tokens present in the prompt."
          },
          {
            "name": "image_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Image input tokens present in the prompt."
          },
          {
            "name": "video_tokens",
            "type": "integer",
            "isBold": true,
            "description": "Video input tokens present in the prompt."
          }
        ]
      },
      {
        "name": "web_search_usage",
        "type": "object",
        "isBold": true,
        "description": "Detailed usage of the web search API.",
        "children": [
          {
            "name": "tool_usage",
            "type": "integer",
            "isBold": true,
            "description": "Number of API calls in web search."
          },
          {
            "name": "page_usage",
            "type": "integer",
            "isBold": true,
            "description": "Number of web pages returned by the web search API."
          }
        ]
      }
    ]
  }
]`} />


--- DOCUMENT: Anthropic API ---
URL: https://platform.xiaomimimo.com/static/docs/api/chat/anthropic-api.md

# Anthropic API Compatibility

## Request Address

```bash
https://api.xiaomimimo.com/anthropic/v1/messages
```

## Request Headers

The API supports the following two authentication methods. Please choose one and add it to the request headers:

1. Method 1: `api-key` field authentication, format:
```json
api-key: $MIMO_API_KEY
Content-Type: application/json
```

1. Method 2: `Authorization: Bearer` authentication, format:
```json
Authorization: Bearer $MIMO_API_KEY
Content-Type: application/json
```

## Request Body

<InlineSchemaV2 schema={`[
  {
    "name": "messages",
    "type": "array",
    "isBold": true,
    "required": true,
    "description": "Input messages. Each input message must be an object with a <code class=\\"schema-inline-code\\">role</code> and <code class=\\"schema-inline-code\\">content</code>.<br />Each input message <code class=\\"schema-inline-code\\">content</code> may be either a single <code class=\\"schema-inline-code\\">string</code> or an array of content blocks, where each block has a specific <code class=\\"schema-inline-code\\">type</code>. Using a <code class=\\"schema-inline-code\\">string</code> for <code class=\\"schema-inline-code\\">content</code> is shorthand for an array of one content block of type <code class=\\"schema-inline-code\\">text</code>.",
    "children": [
      {
        "name": "role",
        "type": "string",
        "isBold": true,
        "required": true,
        "description": "Role of the message.<br />Available options: <code class=\\"schema-inline-code\\">user</code>, <code class=\\"schema-inline-code\\">assistant</code>"
      },
      {
        "name": "content",
        "type": [
          "string",
          "array"
        ],
        "isBold": true,
        "required": true,
        "children": [
          {
            "name": "Text content",
            "type": "string",
            "isBold": false,
            "description": "The text contents of the message."
          },
          {
            "name": "Array of content parts",
            "type": "array",
            "isBold": false,
            "description": "An array of content parts with a defined type. Such text, image, tool use, tool result, and thinking.<br /><blockquote class=\\"schema-blockquote\\">Only the <code class=\\"schema-inline-code\\">mimo-v2.5</code> and <code class=\\"schema-inline-code\\">mimo-v2-omni</code> models support image input.</blockquote>",
            "children": [
              {
                "name": "Text",
                "type": "object",
                "isBold": false,
                "children": [
                  {
                    "name": "text",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The content of the text block.<br />Minimum length: <code class=\\"schema-inline-code\\">1</code>"
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">text</code>"
                  }
                ]
              },
              {
                "name": "Image",
                "type": "object",
                "isBold": false,
                "children": [
                  {
                    "name": "source",
                    "type": "object",
                    "isBold": true,
                    "required": true,
                    "description": "Image data is provided via URL or Base64.",
                    "children": [
                      {
                        "name": "Base64ImageSource",
                        "type": "object",
                        "isBold": false,
                        "children": [
                          {
                            "name": "data",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Base64 encoded image data."
                          },
                          {
                            "name": "media_type",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Media type.<br />Available options: <code class=\\"schema-inline-code\\">image/jpeg</code>, <code class=\\"schema-inline-code\\">image/png</code>, <code class=\\"schema-inline-code\\">image/gif</code>, <code class=\\"schema-inline-code\\">image/webp</code>, <code class=\\"schema-inline-code\\">image/bmp</code>"
                          },
                          {
                            "name": "type",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Image source type.<br />Available options: <code class=\\"schema-inline-code\\">base64</code>"
                          }
                        ]
                      },
                      {
                        "name": "URLImageSource",
                        "type": "object",
                        "isBold": false,
                        "children": [
                          {
                            "name": "url",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "A URL of the image."
                          },
                          {
                            "name": "type",
                            "type": "string",
                            "isBold": true,
                            "required": true,
                            "description": "Image source type.<br />Available options: <code class=\\"schema-inline-code\\">url</code>"
                          }
                        ]
                      }
                    ]
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">image</code>"
                  }
                ]
              },
              {
                "name": "Tool use",
                "type": "object",
                "isBold": false,
                "children": [
                  {
                    "name": "id",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The unique identifier for tool use."
                  },
                  {
                    "name": "input",
                    "type": "object",
                    "isBold": true,
                    "required": true,
                    "description": "The parameter object passed when using the tool."
                  },
                  {
                    "name": "name",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "Tool name."
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">tool_use</code>"
                  }
                ]
              },
              {
                "name": "Tool result",
                "type": "object",
                "isBold": false,
                "children": [
                  {
                    "name": "tool_use_id",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The <code class=\\"schema-inline-code\\">tool_use</code> ID corresponding to this result."
                  },
                  {
                    "name": "content",
                    "type": [
                      "string",
                      "array"
                    ],
                    "isBold": true,
                    "description": "The result returned after the tool is executed.",
                    "children": [
                      {
                        "name": "Text content",
                        "type": "string",
                        "isBold": false,
                        "description": "The text contents of the message."
                      },
                      {
                        "name": "Array of content parts",
                        "type": "array",
                        "isBold": false,
                        "description": "An array of content parts with a defined type. Such text and image.",
                        "children": [
                          {
                            "name": "Text",
                            "type": "object",
                            "isBold": false,
                            "children": [
                              {
                                "name": "text",
                                "type": "string",
                                "isBold": true,
                                "required": true,
                                "description": "The content of the text block."
                              },
                              {
                                "name": "type",
                                "type": "string",
                                "isBold": true,
                                "required": true,
                                "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">text</code>"
                              }
                            ]
                          },
                          {
                            "name": "Image",
                            "type": "object",
                            "isBold": false,
                            "children": [
                              {
                                "name": "source",
                                "type": "object",
                                "isBold": true,
                                "required": true,
                                "description": "Image data is provided via URL or Base64.",
                                "children": [
                                  {
                                    "name": "Base64ImageSource",
                                    "type": "object",
                                    "isBold": false,
                                    "children": [
                                      {
                                        "name": "data",
                                        "type": "string",
                                        "isBold": true,
                                        "required": true,
                                        "description": "Base64 encoded image data."
                                      },
                                      {
                                        "name": "media_type",
                                        "type": "string",
                                        "isBold": true,
                                        "required": true,
                                        "description": "Media type.<br />Available options: <code class=\\"schema-inline-code\\">image/jpeg</code>, <code class=\\"schema-inline-code\\">image/png</code>, <code class=\\"schema-inline-code\\">image/gif</code>, <code class=\\"schema-inline-code\\">image/webp</code>, <code class=\\"schema-inline-code\\">image/bmp</code>"
                                      },
                                      {
                                        "name": "type",
                                        "type": "string",
                                        "isBold": true,
                                        "required": true,
                                        "description": "Image source type.<br />Available options: <code class=\\"schema-inline-code\\">base64</code>"
                                      }
                                    ]
                                  },
                                  {
                                    "name": "URLImageSource",
                                    "type": "object",
                                    "isBold": false,
                                    "children": [
                                      {
                                        "name": "url",
                                        "type": "string",
                                        "isBold": true,
                                        "required": true,
                                        "description": "A URL of the image."
                                      },
                                      {
                                        "name": "type",
                                        "type": "string",
                                        "isBold": true,
                                        "required": true,
                                        "description": "Image source type.<br />Available options: <code class=\\"schema-inline-code\\">url</code>"
                                      }
                                    ]
                                  }
                                ]
                              },
                              {
                                "name": "type",
                                "type": "string",
                                "isBold": true,
                                "required": true,
                                "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">image</code>"
                              }
                            ]
                          }
                        ]
                      }
                    ]
                  },
                  {
                    "name": "is_error",
                    "type": "boolean",
                    "isBold": true
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">tool_result</code>"
                  }
                ]
              },
              {
                "name": "Thinking",
                "type": "object",
                "isBold": false,
                "children": [
                  {
                    "name": "signature",
                    "type": "string",
                    "isBold": true,
                    "description": "The signature of the thinking block."
                  },
                  {
                    "name": "thinking",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "Thinking content."
                  },
                  {
                    "name": "type",
                    "type": "string",
                    "isBold": true,
                    "required": true,
                    "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">thinking</code>"
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  },
  {
    "name": "model",
    "type": "string",
    "isBold": true,
    "required": true,
    "description": "The model that will complete your prompt.<br />Available options: <code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>, <code class=\\"schema-inline-code\\">mimo-v2-flash</code>"
  },
  {
    "name": "max_tokens",
    "type": "integer",
    "isBold": true,
    "required": false,
    "description": "The maximum number of tokens to generate before stopping.<br />Note that our models may stop before reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate.<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-flash</code>: default <code class=\\"schema-inline-code\\">65536</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>: default <code class=\\"schema-inline-code\\">131072</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>: default <code class=\\"schema-inline-code\\">32768</code></li></ul>Required range: <code class=\\"schema-inline-code\\">[1, 131072]</code>"
  },
  {
    "name": "stop_sequences",
    "type": "array",
    "isBold": true,
    "required": false,
    "description": "Custom text sequences that will cause the model to stop generating.<br />Our models will normally stop when they have naturally completed their turn, which will result in a response <code class=\\"schema-inline-code\\">stop_reason</code> of <code class=\\"schema-inline-code\\">end_turn</code>.<br />If you want the model to stop generating when it encounters custom strings of text, you can use the <code class=\\"schema-inline-code\\">stop_sequences</code> parameter."
  },
  {
    "name": "stream",
    "type": "boolean",
    "isBold": true,
    "required": false,
    "defaultValue": "false",
    "description": "Whether to incrementally stream the response using server-sent events."
  },
  {
    "name": "system",
    "type": [
      "string",
      "array"
    ],
    "isBold": true,
    "required": false,
    "description": "A system prompt is a way of providing context and instructions to model, such as specifying a particular goal or role.",
    "children": [
      {
        "name": "Text content",
        "type": "string",
        "isBold": false,
        "description": "The content of the system prompt."
      },
      {
        "name": "Array of content parts",
        "type": "array",
        "isBold": false,
        "children": [
          {
            "name": "text",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "The text content.<br />Minimum length: <code class=\\"schema-inline-code\\">1</code>"
          },
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">text</code>"
          }
        ]
      }
    ]
  },
  {
    "name": "temperature",
    "type": "number",
    "isBold": true,
    "required": false,
    "description": "Sampling temperature controls the diversity of the text generated by the model.<br />The higher the temperature, the more diverse the generated text will be; conversely, the lower the temperature, the more deterministic the generated text will be.<br /><blockquote class=\\"schema-blockquote\\">In thinking mode, the <code class=\\"schema-inline-code\\">mimo-v2.5-pro</code> and <code class=\\"schema-inline-code\\">mimo-v2.5</code> models do not support customizing the <code class=\\"schema-inline-code\\">temperature</code> parameter. Even if this parameter is passed in, it will be forcibly overridden and take effect with the model's recommended default value of <code class=\\"schema-inline-code\\">1.0</code>.</blockquote><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-flash</code>: default <code class=\\"schema-inline-code\\">0.3</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>: default <code class=\\"schema-inline-code\\">1.0</code></li></ul>Required range: <code class=\\"schema-inline-code\\">[0, 1.5]</code>"
  },
  {
    "name": "thinking",
    "type": "object",
    "isBold": true,
    "required": false,
    "description": "Configuration for enabling model's extended thinking.<br /><blockquote class=\\"schema-blockquote\\">Note: During the multi-turn tool calls process in thinking mode, the model returns a <code class=\\"schema-inline-code\\">thinking</code> content block alongside <code class=\\"schema-inline-code\\">tool_use</code> content block. To continue the conversation, it is recommended to keep all previous <code class=\\"schema-inline-code\\">thinking</code> content block in the <code class=\\"schema-inline-code\\">messages</code> array for each subsequent request to achieve the best performance.</blockquote><blockquote class=\\"schema-blockquote\\">In thinking mode, the <code class=\\"schema-inline-code\\">mimo-v2.5-pro</code> and <code class=\\"schema-inline-code\\">mimo-v2.5</code> models do not support customizing the <code class=\\"schema-inline-code\\">temperature</code> parameter. Even if this parameter is passed in, it will be forcibly overridden and take effect with the model's recommended default value of <code class=\\"schema-inline-code\\">1.0</code>.</blockquote>",
    "children": [
      {
        "name": "type",
        "type": "string",
        "isBold": true,
        "required": true,
        "description": "<ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2-flash</code>: default <code class=\\"schema-inline-code\\">disabled</code></li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">mimo-v2.5-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2.5</code>, <code class=\\"schema-inline-code\\">mimo-v2-pro</code>, <code class=\\"schema-inline-code\\">mimo-v2-omni</code>: default <code class=\\"schema-inline-code\\">enabled</code></li></ul>Available options: <code class=\\"schema-inline-code\\">enabled</code>, <code class=\\"schema-inline-code\\">disabled</code>"
      }
    ]
  },
  {
    "name": "tool_choice",
    "type": "object",
    "isBold": true,
    "required": false,
    "description": "How the model should use the provided tools.",
    "children": [
      {
        "name": "type",
        "type": "string",
        "isBold": true,
        "required": true,
        "description": "<ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">auto</code> means the model will automatically decide whether to use tools.</li></ul><blockquote class=\\"schema-blockquote\\">Note: When a value other than <code class=\\"schema-inline-code\\">auto</code> is passed to <code class=\\"schema-inline-code\\">type</code>, the backend will remove this field by default, and the model response behavior will still be equivalent to the <code class=\\"schema-inline-code\\">auto</code> mode (this logic is subject to future adjustments).</blockquote>Available options: <code class=\\"schema-inline-code\\">auto</code>"
      },
      {
        "name": "disable_parallel_tool_use",
        "type": "boolean",
        "isBold": true,
        "defaultValue": "false",
        "description": "Whether to disable parallel tool use.<br />If set to <code class=\\"schema-inline-code\\">true</code>:<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\">When type is <code class=\\"schema-inline-code\\">auto</code>, the model will output at most one tool use.</li></ul>"
      }
    ]
  },
  {
    "name": "tools",
    "type": "array",
    "isBold": true,
    "required": false,
    "description": "Definitions of tools that the model may use.<br />If you include <code class=\\"schema-inline-code\\">tools</code> in your API request, the model may return <code class=\\"schema-inline-code\\">tool_use</code> content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using <code class=\\"schema-inline-code\\">tool_result</code> content blocks.<br /><blockquote class=\\"schema-blockquote\\">Note: During the multi-turn tool calls process in thinking mode, the model returns a <code class=\\"schema-inline-code\\">thinking</code> content block alongside <code class=\\"schema-inline-code\\">tool_use</code> content block. To continue the conversation, it is recommended to keep all previous <code class=\\"schema-inline-code\\">thinking</code> content block in the <code class=\\"schema-inline-code\\">messages</code> array for each subsequent request to achieve the best performance.</blockquote>Each tool definition includes:<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">name</code>: Name of the tool.</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">description</code>: Optional, but strongly-recommended description of the tool.</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">input_schema</code>:  JSON schema for the tool <code class=\\"schema-inline-code\\">input</code> shape that the model will produce in <code class=\\"schema-inline-code\\">tool_use</code> output content blocks.</li></ul>",
    "children": [
      {
        "name": "name",
        "type": "string",
        "isBold": true,
        "required": true,
        "description": "Name of the tool.<br />This is how the tool will be called by the model and in <code class=\\"schema-inline-code\\">tool_use</code> blocks."
      },
      {
        "name": "description",
        "type": "string",
        "isBold": true,
        "description": "Description of what this tool does.<br />Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema."
      },
      {
        "name": "type",
        "type": "string",
        "isBold": true,
        "description": "Available options: <code class=\\"schema-inline-code\\">custom</code>"
      },
      {
        "name": "input_schema",
        "type": "object",
        "isBold": true,
        "required": true,
        "description": "JSON schema for the tool input shape that the model will produce in <code class=\\"schema-inline-code\\">tool_use</code> output content blocks.",
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "required": true,
            "description": "The type of <code class=\\"schema-inline-code\\">input_schema</code>, only <code class=\\"schema-inline-code\\">object</code> is supported.<br />Available options: <code class=\\"schema-inline-code\\">object</code>"
          },
          {
            "name": "properties",
            "type": [
              "object",
              "null"
            ],
            "isBold": true,
            "description": "The properties of the tool input."
          },
          {
            "name": "required",
            "type": [
              "array",
              "null"
            ],
            "isBold": true,
            "description": "The list of properties that must be included in the tool input."
          }
        ]
      }
    ]
  },
  {
    "name": "top_p",
    "type": "number",
    "isBold": true,
    "required": false,
    "defaultValue": "0.95",
    "description": "Use nucleus sampling.<br />In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by <code class=\\"schema-inline-code\\">top_p</code>. You should either alter <code class=\\"schema-inline-code\\">temperature</code> or <code class=\\"schema-inline-code\\">top_p</code>, but not both.<br />Recommended for advanced use cases only. You usually only need to use <code class=\\"schema-inline-code\\">temperature</code>.<br />Required range: <code class=\\"schema-inline-code\\">[0.01, 1.0]</code>"
  }
]`} />

## Non-streaming Response

<InlineSchemaV2 schema={`[
  {
    "name": "id",
    "type": "string",
    "isBold": true,
    "description": "Unique object identifier. The format and length of IDs may change over time."
  },
  {
    "name": "type",
    "type": "string",
    "isBold": true,
    "description": "For Messages, this is always <code class=\\"schema-inline-code\\">message</code>."
  },
  {
    "name": "role",
    "type": "string",
    "isBold": true,
    "description": "Conversational role of the generated message. This will always be <code class=\\"schema-inline-code\\">assistant</code>."
  },
  {
    "name": "content",
    "type": "array",
    "isBold": true,
    "description": "Content generated by the model.",
    "children": [
      {
        "name": "Text",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "text",
            "type": "string",
            "isBold": true,
            "description": "The content of the text."
          },
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">text</code>"
          }
        ]
      },
      {
        "name": "Thinking",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "signature",
            "type": "string",
            "isBold": true,
            "description": "The signature of the thinking block."
          },
          {
            "name": "thinking",
            "type": "string",
            "isBold": true,
            "description": "Thinking content."
          },
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">thinking</code>"
          }
        ]
      },
      {
        "name": "Tool use",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "id",
            "type": "string",
            "isBold": true,
            "description": "The unique identifier for tool use."
          },
          {
            "name": "input",
            "type": "object",
            "isBold": true,
            "description": "The parameter object passed when using the tool."
          },
          {
            "name": "name",
            "type": "string",
            "isBold": true,
            "description": "Tool name."
          },
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "The type of the content.<br />Available options: <code class=\\"schema-inline-code\\">tool_use</code>"
          }
        ]
      }
    ]
  },
  {
    "name": "model",
    "type": "string",
    "isBold": true,
    "description": "The model that handled the request."
  },
  {
    "name": "stop_reason",
    "type": "string",
    "isBold": true,
    "description": "The reason the message finished.<br />This may be one the following values:<br /><ul class=\\"schema-list\\"><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">end_turn</code>: the model reached a natural stopping point.</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">max_tokens</code>: we exceeded the requested <code class=\\"schema-inline-code\\">max_tokens</code> or the model's maximum.</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">tool_use</code>: the model invoked one or more tools.</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">content_filter</code>: the content was omitted due to a flag from our content filters.</li><li class=\\"schema-list-item\\"><code class=\\"schema-inline-code\\">repetition_truncation</code>: the model detects repetition.</li></ul>Available options: <code class=\\"schema-inline-code\\">end_turn</code>, <code class=\\"schema-inline-code\\">max_tokens</code>, <code class=\\"schema-inline-code\\">tool_use</code>, <code class=\\"schema-inline-code\\">content_filter</code>, <code class=\\"schema-inline-code\\">repetition_truncation</code>"
  },
  {
    "name": "usage",
    "type": "object",
    "isBold": true,
    "description": "Billing and rate-limit usage.",
    "children": [
      {
        "name": "input_tokens",
        "type": "integer",
        "isBold": true,
        "description": "The number of input tokens which were used."
      },
      {
        "name": "output_tokens",
        "type": "integer",
        "isBold": true,
        "description": "The number of output tokens which were used."
      },
      {
        "name": "cache_read_input_tokens",
        "type": [
          "integer",
          "null"
        ],
        "isBold": true,
        "description": "The number of input tokens read from the cache."
      }
    ]
  }
]`} />

## Streaming Response
<InlineSchemaV2 schema={`[
  {
    "name": "SSE.event",
    "type": "string",
    "isBold": true,
    "description": "A string identifying the type of event described.<br />Available options: <code class=\\"schema-inline-code\\">message_start</code>, <code class=\\"schema-inline-code\\">content_block_start</code>,<code class=\\"schema-inline-code\\"> content_block_delta</code>, <code class=\\"schema-inline-code\\">content_block_stop</code>, <code class=\\"schema-inline-code\\">message_delta</code>, <code class=\\"schema-inline-code\\">message_stop</code>"
  },
  {
    "name": "type",
    "type": "string",
    "isBold": true,
    "description": "Each server-sent event includes a named event type and associated JSON data.<br />Available options: <code class=\\"schema-inline-code\\">message_start</code>, <code class=\\"schema-inline-code\\">content_block_start</code>,<code class=\\"schema-inline-code\\"> content_block_delta</code>, <code class=\\"schema-inline-code\\">content_block_stop</code>, <code class=\\"schema-inline-code\\">message_delta</code>, <code class=\\"schema-inline-code\\">message_stop</code>"
  },
  {
    "name": "message",
    "type": "object",
    "isBold": true,
    "description": "Response message.",
    "children": [
      {
        "name": "id",
        "type": "string",
        "isBold": true,
        "description": "The message ID."
      },
      {
        "name": "type",
        "type": "string",
        "isBold": true,
        "description": "Available options: <code class=\\"schema-inline-code\\">message</code>"
      },
      {
        "name": "role",
        "type": "string",
        "isBold": true,
        "description": "Available options: <code class=\\"schema-inline-code\\">assistant</code>"
      },
      {
        "name": "model",
        "type": "string",
        "isBold": true,
        "description": "The model name."
      },
      {
        "name": "content",
        "type": "array",
        "isBold": true,
        "description": "The array of content blocks in the message."
      },
      {
        "name": "stop_reason",
        "type": [
          "string",
          "null"
        ],
        "isBold": true,
        "description": "The reason the message finished."
      }
    ]
  },
  {
    "name": "index",
    "type": "integer",
    "isBold": true,
    "description": "The position of the content block within the message.。"
  },
  {
    "name": "content_block",
    "type": "object",
    "isBold": true,
    "description": "The content block that is starting.",
    "children": [
      {
        "name": "Text",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "The header for a text content block; actual text arrives via subsequent delta events.<br />Available options: <code class=\\"schema-inline-code\\">text</code>"
          },
          {
            "name": "text",
            "type": "string",
            "isBold": true,
            "description": "Often an empty string at start; text is appended via <code class=\\"schema-inline-code\\">content_block_delta</code> events of type <code class=\\"schema-inline-code\\">text_delta</code>."
          }
        ]
      },
      {
        "name": "Thinking",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "The header for a thinking content block; actual thinking content arrives via subsequent delta events.<br />Available options: <code class=\\"schema-inline-code\\">thinking</code>"
          },
          {
            "name": "thinking",
            "type": "string",
            "isBold": true,
            "description": "Often an empty string at start; thinking content is appended via <code class=\\"schema-inline-code\\">content_block_delta</code> events of type <code class=\\"schema-inline-code\\">thinking_delta</code>."
          }
        ]
      },
      {
        "name": "Tool use",
        "type": "object",
        "isBold": false,
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "Available options: <code class=\\"schema-inline-code\\">tool_use</code>"
          },
          {
            "name": "id",
            "type": "string",
            "isBold": true,
            "description": "The unique identifier for tool use."
          },
          {
            "name": "name",
            "type": "string",
            "isBold": true,
            "description": "Tool name."
          },
          {
            "name": "input",
            "type": "object",
            "isBold": true,
            "description": "The parameter object passed when using the tool."
          }
        ]
      }
    ]
  },
  {
    "name": "delta",
    "type": "object",
    "isBold": true,
    "description": "Actual response content.",
    "children": [
      {
        "name": "Content block delta",
        "type": "object",
        "isBold": false,
        "description": "Incremental data for a content block.",
        "children": [
          {
            "name": "type",
            "type": "string",
            "isBold": true,
            "description": "Available options: <code class=\\"schema-inline-code\\">text_delta</code>, <code class=\\"schema-inline-code\\">thinking_delta</code>, <code class=\\"schema-inline-code\\">input_json_delta</code>"
          },
          {
            "name": "text",
            "type": "string",
            "isBold": true,
            "description": "The text part of the incremental data."
          },
          {
            "name": "thinking",
            "type": "string",
            "isBold": true,
            "description": "The thinking part of the incremental data."
          },
          {
            "name": "partial_json",
            "type": "string",
            "isBold": true,
            "description": "A JSON fragment string. Clients should concatenate fragments in arrival order to form the complete input JSON, then parse."
          }
        ]
      },
      {
        "name": "Message delta",
        "type": "object",
        "isBold": false,
        "description": "Message-level stop metadata updates.",
        "children": [
          {
            "name": "stop_reason",
            "type": [
              "string",
              "null"
            ],
            "isBold": true,
            "description": "The reason the message finished.<br />Available options: <code class=\\"schema-inline-code\\">end_turn</code>, <code class=\\"schema-inline-code\\">max_tokens</code>, <code class=\\"schema-inline-code\\">tool_use</code>, <code class=\\"schema-inline-code\\">content_filter</code>, <code class=\\"schema-inline-code\\">repetition_truncation</code>"
          }
        ]
      }
    ]
  },
  {
    "name": "usage",
    "type": [
      "object",
      "null"
    ],
    "isBold": true,
    "description": "Billing and rate-limit usage.",
    "children": [
      {
        "name": "input_tokens",
        "type": "integer",
        "isBold": true,
        "description": "The number of input tokens which were used."
      },
      {
        "name": "output_tokens",
        "type": "integer",
        "isBold": true,
        "description": "The number of output tokens which were used."
      },
      {
        "name": "cache_read_input_tokens",
        "type": [
          "integer",
          "null"
        ],
        "isBold": true,
        "description": "The number of input tokens read from the cache."
      }
    ]
  }
]`} />


--- DOCUMENT: Subscription Instructions ---
URL: https://platform.xiaomimimo.com/static/docs/tokenplan/subscription.md

# Subscription Instructions

**Token Plan**  is a dedicated subscription plan launched for AI programming scenarios. You can use the cost-effective subscription resource package to call the MiMo flagship large model in various mainstream AI development tools.

## Core Advantages

- **Covers flagship models**  - Supports MiMo-V2.5-Pro, MiMo-V2.5, MiMo-V2.5-TTS-VoiceClone, MiMo-V2.5-TTS-VoiceDesign, MiMo-V2.5-TTS, including a total of 8 models in the V2 series. It adopts a Token conversion mechanism, with transparent and controllable quotas.

- **Elastic Subscription Plan** — Four-tier Gradient Package, meeting the needs from individual development to enterprise-level development

- **Multi-ecosystem Out Of The Box** — Compatible with mainstream development toolchains such as OpenCode, OpenClaw, and Claude Code

## Usage Quota

#### Monthly Package

<table>
<colgroup>
<col />
<col style="width: 256px" />
<col style="width: 256px" />
<col style="width: 284px" />
<col style="width: 284px" />
</colgroup>
<thead>
<tr>
<th></th>
<th>**Lite**</th>
<th>**Standard**</th>
<th>**Pro**</th>
<th>**Max**</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Pricing**</td>
<td>**$6/month, ¥39/month**</td>
<td>**$16/month, ¥99/month**</td>
<td>**$50/month, ¥329/month**</td>
<td>**$100/month, ¥659/month**</td>
</tr>
<tr>
<td>**Monthly Fixed Credit Limit**</td>
<td>**60,000,000 （60M）Credits**</td>
<td>**200,000,000 （200M）Credits**</td>
<td>**700,000,000 （700M）Credits**</td>
<td>**1,600,000,000 （1600M）Credits**</td>
</tr>
</tbody>
</table>

#### Annual Package

<table>
<colgroup>
<col />
<col style="width: 256px" />
<col style="width: 256px" />
<col style="width: 284px" />
<col style="width: 284px" />
</colgroup>
<thead>
<tr>
<th></th>
<th>**Lite**</th>
<th>**Standard**</th>
<th>**Pro**</th>
<th>**Max**</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Pricing**</td>
<td>**$63.36/year，¥411.84/year**</td>
<td>**$168.96/year，¥1045.44/year**</td>
<td>**$528.00/year，¥3474.24/year**</td>
<td>**$1056.00/year，¥6959.04/year**</td>
</tr>
<tr>
<td>**Yearly Fixed Credit Limit**</td>
<td>**720,000,000 （720M）Credits**</td>
<td>**2,400,000,000 （2400M）Credits**</td>
<td>**8,400,000,000 （8400M）Credits**</td>
<td>**19,200,000,000 （19200M）Credits**</td>
</tr>
</tbody>
</table>

#### Applicable Scenarios

<table>
<colgroup>
<col />
<col style="width: 256px" />
<col style="width: 256px" />
<col style="width: 284px" />
<col style="width: 284px" />
</colgroup>
<thead>
<tr>
<th></th>
<th>**Lite**</th>
<th>**Standard**</th>
<th>**Pro**</th>
<th>**Max**</th>
</tr>
</thead>
<tbody>
<tr>
<td>**Applicable Scenarios**</td>
<td>Suitable for first-time lobster-tasting users <br />Using MiMo-V2.5/MiMo-V2-Omni as a benchmark, it can execute approximately **120 rounds of medium to complex tasks**</td>
<td>Suitable for work enthusiasts who often use AI to improve their efficiency <br />Using MiMo-V2.5/MiMo-V2-Omni as a benchmark, it can execute approximately **400 rounds of medium to complex tasks**</td>
<td>Suitable for developers and professional efficiency enthusiasts who use AI frequently every day <br />Using MiMo-V2.5/MiMo-V2-Omni as a baseline, approximately **1400 rounds of medium to complex tasks can be executed**</td>
<td>Suitable for high-intensity, hardcore users who use AI as a core productivity tool <br />Using MiMo-V2.5/MiMo-V2-Omni as a baseline, it can execute approximately **3200 rounds of medium to complex tasks**</td>
</tr>
</tbody>
</table>

> The above is the scope of scenarios for the monthly package, and the order of magnitude of task processing for the annual package is approximately 12 times that of the monthly package.

- **Discount Offer：0.8x consumption at night, 12% discount on the first purchase of a package, 30% discount (for existing users) or 23% discount (for new users) on the first activation of auto-renewal, 12% discount on consecutive annual subscriptions, and existing users of the Token Plan exclusively enjoy the "Credits Usage Refresh and Reset" event once after the launch of the V2.1 model.** 

   - Package Usage Refresh and Reset: To celebrate the official launch of MiMo-V2.5, users who purchased the Token Plan before 22:00 on April 22, Beijing Time, will have their consumed Credits completely reset, regardless of the current usage of their package, with the validity period remaining unchanged.

   - First Purchase Discount: Enjoy 12% off on your first purchase, available only once per account.

   - First-time auto-renewal discount: New users who have never subscribed to a package before enjoy a 23% discount (77% of the original price) when they first activate auto-renewal, while existing users who have subscribed to a package before enjoy a 30% discount (70% of the original price) when they first activate auto-renewal. The first-time auto-renewal discount is mutually exclusive with the first-purchase discount, and each account can only enjoy it once.

   - Continuous annual subscription: Enjoy an 12% discount compared to continuous monthly subscription; the first purchase/first activation auto-renewal discount does not apply to annual subscriptions.

   - Nighttime discount rate: During off-peak hours (0:00-8:00 Beijing Time, i.e., 16:00-24:00 UTC), the consumption coefficient is 0.8x.

- **Supported models:** All packages support a total of 8 models, including MiMo-V2.5-Pro, MiMo-V2.5, MiMo-V2.5-TTS-VoiceClone, MiMo-V2.5-TTS-VoiceDesign, MiMo-V2.5-TTS, MiMo-V2-Pro, MiMo-V2-Omni, and MiMo-V2-TTS.

- **Credit consumption:**  Credit is deducted according to the number of tokens, and the credit of Pro and Omni is consumed in parallel at a 1:2 ratio, not independently. TTS series models are free for a limited time and do not consume package tokens。For example, if you have subscribed to the Lite plan, you can call the MiMo-V2.5 series models individually or in combination. After using 10M Tokens of MiMo-V2.5-Pro, it is equivalent to consuming 20M Credits, and you can still enjoy 40M Tokens of MiMo-V2.5 (equivalent to 40 Credits). You can view the quota and usage of your current plan in [Subscription Management](https://platform.xiaomimimo.com/#/console/plan-manage).

> - V2.5 series
>
> MiMo-V2.5 ：1x（equivalent to the original Token consumption rate）
>
> MiMo-V2.5-Pro： 2x（Equivalent to 2 times the Token consumption rate）
>
> MiMo-V2.5-TTS-VoiceClone、MiMo-V2.5-TTS-VoiceDesign、MiMo-V2.5-TTS：0x（Limited-time free, no Credit consumption）
>
> - V2 series
>
> MiMo-V2-Omni：1x（equivalent to the original Token consumption rate）
>
> MiMo-V2-Pro： 2x（Equivalent to 2 times the Token consumption rate）
>
> MiMo-V2-TTS：0x（Limited-time free, no Credit consumption）

- **Quota Exhausted:**  When the monthly total quota of the package is exhausted, the system will stop service and will not continue to consume your bonus or account balance. 

- **If you need to continue using it:**  Please purchase an upgrade package to unlock new package resources; or switch to the regular API, which is billed at the per-token unit price, and you can continue using it without usage limits. 

## Package Purchase

- **Support for upgrading a package by paying the price difference: Currently, the platform only supports purchasing 1 package at a time. If you wish to obtain more credits before the package expires,**  you can convert the used credit amount into an equivalent amount, and on this basis, pay the price difference to upgrade to a higher package and obtain more credits. Support for upgrading packages across levels by paying the price difference, but package downgrading is not supported. If you have already upgraded to the highest-tier Max package, you cannot continue to upgrade.  **After the package expires, you can purchase a package of any level again.**  

> Price difference = New package price - (Remaining amount of original package / Total amount of original package) * Original package price

- **Auto-renewal supported:** The auto-renewal feature has been launched. Enjoy a discount when subscribing to continuous renewal for the first time. Please stay tuned.

- **Refunds are not currently supported**: Please note that once a subscription service is purchased, it becomes effective immediately, and refunds are not supported. Unused credits within the package will not be refunded. Please carefully select a suitable subscription plan based on your own usage needs.

- **Invoice Support** : Domestic users can apply for invoices based on the transaction orders in the recharge details, and the actual amount eligible for invoicing is the actual payment amount. Overseas users can directly download invoices after purchase or download them from the recharge details page. 

## Package Usage

The Token Plan package quota can only be used in programming tools (such as OpenClaw, OpenCode, etc.), and it is prohibited to use it in the form of API calls for request behaviors in clearly non-Coding scenarios such as automated scripts and custom application backends. 

If an API Key corresponding to a package is used for calls that exceed the permitted scope, it will be considered a violation or abuse, and the platform has the right to take measures such as suspending service and banning the API Key against the relevant subscription. 

## Quick Guide

Quick Start Token Plan, from subscribing to a package to using the MiMo model in coding tools.

### Subscribe to Token Plan

Visit [Token Plan](https://platform.xiaomimimo.com/#/token-plan), select and purchase the appropriate subscription plan as needed.

### Obtain the Base URL and API Key exclusive to the package 

After successful subscription, you can go to the [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page to obtain the Base URL and API Key exclusive to the package. 

- **API Key**: On the [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page, obtain your exclusive API Key (in the format of `tp-xxxxx`).

- **Base URL**: Subsequently, one of the following Base URLs needs to be configured in the AI programming tool ( **protocol varies by tool, Base URL is subject to the display on the** [**Subscription**](https://platform.xiaomimimo.com/#/console/plan-manage) **page** ), for specific operations, please refer to the corresponding AI programming tool user guide document.

   - **OpenAI Compatibility Protocol**

      - China Cluster: `https://token-plan-cn.xiaomimimo.com/v1`

      - Singapore Cluster: `https://token-plan-sgp.xiaomimimo.com/v1`

      - Europe Cluster: `https://token-plan-ams.xiaomimimo.com/v1`

   - **Anthropic Compatibility Protocol**

      - China Cluster: `https://token-plan-cn.xiaomimimo.com/anthropic`

      - Singapore Cluster: `https://token-plan-sgp.xiaomimimo.com/anthropic`

      - Europe Cluster: `https://token-plan-ams.xiaomimimo.com/anthropic`

<div className='mdx-highlight'>

**Precautions** 
- Please keep your API Key properly and do not disclose it to others.
- API Key is only available during the validity period of the Token Plan subscription you have subscribed to.

</div>

## Used in AI Agent and Programming Tools

Token Plan supports use in multiple mainstream AI programming tools, with all tools sharing the usage quota of the subscribed package.

Go to [AI Tools Overview](https://platform.xiaomimimo.com/#/docs/integration/tools-overview) to view the configuration guide for the tools you use (such as OpenCode, OpenClaw, etc.).

## Frequently Asked Questions 

For more frequently asked questions, please refer to [FAQs](https://platform.xiaomimimo.com/#/docs/faq).


--- DOCUMENT: Quick Access ---
URL: https://platform.xiaomimimo.com/static/docs/tokenplan/quick-access.md

# Quick Access

This article describes how to quickly connect to Token Plan, which can be completed in just 3 steps from subscription to invocation. 

## Step 1: Subscribe to the Token Plan 

Go to [Token Plan](https://platform.xiaomimimo.com/#/token-plan), select a suitable subscription plan. 

## Step 2: Obtain Credentials 

After successful subscription, go to [ Subscription](https://platform.xiaomimimo.com/#/console/plan-manage)  to obtain the following credentials: 

- **Base URL**: Subsequently, one of the following Base URLs needs to be configured in the AI programming tool ( **protocol varies by tool, Base URL is subject to the display on the** [**Subscription**](https://platform.xiaomimimo.com/#/console/plan-manage) **page** ), for specific operations, please refer to the corresponding AI programming tool user guide document.

- **OpenAI Compatibility Protocol**

   - China Cluster: `https://token-plan-cn.xiaomimimo.com/v1`

   - Singapore Cluster: `https://token-plan-sgp.xiaomimimo.com/v1`

   - Europe Cluster: `https://token-plan-ams.xiaomimimo.com/v1`

- **Anthropic Compatibility Protocol**

   - China Cluster: `https://token-plan-cn.xiaomimimo.com/anthropic`

   - Singapore Cluster: `https://token-plan-sgp.xiaomimimo.com/anthropic`

   - Europe Cluster: `https://token-plan-ams.xiaomimimo.com/anthropic`

<div className='mdx-highlight'>

The API Key of Token Plan (`tp-xxxxx`) and the API Key for pay-as-you-go API calls (`sk-xxxxx`) are independent of each other and cannot be mixed.

</div>

## Step 3: Connect to AI Programming Tools 

Go to [AI Tools Overview](https://platform.xiaomimimo.com/#/docs/integration/tools-overview) to view the configuration guide for the tools you use (such as OpenCode, OpenClaw, etc.).

## Quick Verification (Optional)

After completing the configuration, you can quickly verify whether the connection is successful through the following methods. 

### Method 1: Verify through AI programming tools 

Enter a simple programming requirement into the configured AI programming tool, for example: 

> Help me write a quick sort algorithm in Python

If the tool returns a normal code, it indicates successful connection. 

### Method 2: Directly call verification via API 

Use the curl command to directly call the API and verify whether the credentials are valid. 

<div className='mdx-highlight'>

In the following examples, both `BASE_URL` and `MIMO_API_KEY` are placeholders. Please replace them with the real credentials obtained from the Console when actually using them.

</div>

**OpenAI Compatibility Protocol:**

```bash
curl --location --request POST 'BASE_URL/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "please introduce yourself"
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Anthropic Compatibility** **Protocol:**

```bash
curl --location --request POST 'BASE_URL/v1/messages' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "max_tokens": 1024,
    "system": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "please introduce yourself"
                }
            ]
        }
    ]
}'
```

## Frequently Asked Questions 

**Question: What is the difference between the API Key of Token Plan and the API Key for Pay-as-you-go  API calls?**

Answer: The API Key format for Token Plan is `tp-xxxxx`, which is only used for Token Plan subscription services; Pay-as-you-go API calls have an API Key format of `sk-xxxxx`, which is used for pay-as-you-go billing. The two are independent of each other and cannot be mixed.

**Question: What is the difference between the Base URL of the Token Plan and the Base URL of Pay-as-you-go API calls?**

Answer: The Base URL format of Token Plan is different, and it shall be subject to the display on the [ Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page.

**Question: Can the API Key still be used after the subscription expires?**

Answer: No. The API Key of Token Plan is only available during the subscription validity period, and renewal is required after the subscription expires to continue using it.


--- DOCUMENT: Overview of AI Tools ---
URL: https://platform.xiaomimimo.com/static/docs/integration/tools-overview.md

# Overview of AI Tools

**The pay-as-you-go MiMo API and Token Plan subscription packages,**  are both supported for use in the following mainstream AI programming tools (the tool list is continuously updated), click to view the detailed access and usage guide for the corresponding tool.

## Use Tools

<ToolGrid />

## Configuration Methods for Other Tools

> Core Steps:
>
> 1. Find a compatible OpenAI protocol or Anthropic protocol, and support custom configuration Provider 
>
> 1. Replace or add as the Base URL for the corresponding protocol
>
> 1. Enter API Key, select or add MiMo model 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li><li>Anthropic Compatibility Protocol: `https://api.xiaomimimo.com/anthropic`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li><li>Anthropic Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/anthropic`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>


--- DOCUMENT: OpenCode Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/opencode.md

# OpenCode Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support OpenCode. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

<div className='mdx-highlight'>

Note: When OpenCode uses MiMo under the Anthropic protocol, since the assistant containing tool calls is missing `reasoning_content`, the API will return a 400 error. For details, see [[Important Notice]Passing Back reasoning_content in Multi-Turn Conversations for Agent Products](https://platform.xiaomimimo.com/docs/zh-CN/usage-guide/passing-back-reasoning_content) .

</div>

## Use OpenCode CLI

### Install OpenCode CLI

OpenCode supports two installation methods.

**Method 1: Official Script Installation (for macOS/Linux)**

```bash
curl -fsSL https://opencode.ai/install | bash
```

**Method 2: npm Installation**

Node.js 18 or later is required.

```bash
npm install -g opencode-ai
```

**Verify installation (if a version number is displayed, the installation was successful):**

```bash
opencode -v
```

### Configure Basic Settings

Edit or create the `opencode.json` configuration file at the following path:

- **macOS/Linux**: `~/.config/opencode/opencode.json`

- **Windows**: `User Directory\.config\opencode\opencode.json`

Copy the following content into the configuration file (replace `BASE_URL` and `MIMO_API_KEY` as needed):

```json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "mimo": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "MiMo",
      "options": {
        "baseURL": "BASE_URL",
        "apiKey": "MIMO_API_KEY"
      },
      "models": {
        "mimo-v2.5-pro": {
          "name": "mimo-v2.5-pro",
          "limit": {
            "context": 1048576,
            "output": 131072
          },
          "modalities": {
            "input": [
              "text"
            ],
            "output": [
              "text"
            ]
          }
        },
        "mimo-v2.5": {
          "name": "mimo-v2.5",
          "limit": {
            "context": 1048576,
            "output": 131072
          },
          "modalities": {
            "input": [
              "text", "image"
            ],
            "output": [
              "text"
            ]
          }
        }
      }
    }
  }
}
```

<div className='mdx-highlight'>

**Note:** If you need to enable the image understanding capability, you need to modify or add the following configuration items under the configuration node of the model that supports this capability (e.g., `mimo-v2.5`). That is, add `image` to the supported input modalities: `"modalities": {"input": ["text", "image"], "output": ["text"]}`

</div>

### Use OpenCode CLI

After completing the configuration, navigate to the project directory and run the following command to start OpenCode:

```bash
opencode
```

After starting, enter `/models` to view and switch between available models.

## Use OpenCode IDE Plugin

### Install Plugin

Search for and install the **opencode** plugin in the VS Code Extensions marketplace.

![图片](https://platform.xiaomimimo.com/static/C6UebPYfKoXvoyx3nQycU7dCneg.bb7c4524.png)

### Configure a Predefined Provider (Recommended)

Just enter `/connect` in the input box, search for `Xiaomi`, select the corresponding Provider, and fill in the API Key.

<div className='mdx-highlight'>

When using the **Xiaomi Token Plan**, you need to select the Provider corresponding to the Base URL displayed on the [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page.
- `https://token-plan-cn.xiaomimimo.com/*`: Xiaomi Token Plan (China)
- `https://token-plan-sgp.xiaomimimo.com/*`: Xiaomi Token Plan (Singapore)
- `https://token-plan-ams.xiaomimimo.com/*`: Xiaomi Token Plan (Europe)

</div>

![图片](https://platform.xiaomimimo.com/static/Bs9oby6sbob2OGxXqNScWeKpnLe.6bb47b0f.png)

### Configure a Custom Provider 

Refer to the "Configure Basic Settings" steps in the OpenCode CLI section above.

### Use OpenCode Plugin

![图片](https://platform.xiaomimimo.com/static/L2cUbHSmko0MCLxkhzCc6bKEnee.981ab390.png)

## FAQ

### When verifying the installation on Windows, I encounter the following error. How to fix it?

> It seems that your package manager failed to install the right version of the opencode CLI for your platform. You can try manually installing "opencode-windows-x64" or "opencode-windows-x64-baseline" package

Run the command `npm install -g opencode-windows-x64` as prompted to resolve the issue.

### Error when starting OpenCode in VS Code on Windows?

> opencode : Cannot load file ... because running scripts is disabled on this system

Change the default terminal type to Git Bash when opening a terminal in VS Code.

![图片](https://platform.xiaomimimo.com/static/XVJnbxkIfoFl3rxaNnWcqoWFnXc.44f2fde2.png)


--- DOCUMENT: Claude Code Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/claudecode.md

# Claude Code Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support Claude Code. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>Anthropic Compatibility Protocol: `https://api.xiaomimimo.com/anthropic`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>Anthropic Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/anthropic`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

## Use Claude Code CLI

### Install Claude Code CLI

Claude Code requires Node.js 18 or later.

- Linux/macOS: No additional setup needed, the default environment is sufficient.

- Windows: Install [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) or [Git for Windows](https://git-scm.com/install/windows), then run the command below in WSL or Git Bash.

**Installation command:**

```bash
npm install -g @anthropic-ai/claude-code
```

**Verify the installation (a version number output indicates success):**

```bash
claude --version
```

<div className='mdx-highlight'>

Do not launch Claude Code immediately after installation. Complete the configuration below first.

</div>

### Configure Basic Settings

<div className='mdx-highlight'>

Before configuring, make sure to clear the following Anthropic official environment variables to avoid API conflicts: `ANTHROPIC_AUTH_TOKEN`, `ANTHROPIC_BASE_URL`

</div>

**1.**  **Create/edit** `settings.json`

> If the `.claude` directory does not exist, you can create it manually.

- macOS/Linux: `~/.claude/settings.json`

- Windows: `User directory\.claude\settings.json`

Please replace `BASE_URL` (Anthropic Compatibility Protocol) and `MIMO_API_KEY` as needed.

<div className='mdx-highlight'>

For MiMo models that support **1M** context, you can append the `[1m]` suffix to the model ID to enable extended context capacity. Example: `mimo-v2.5-pro[1m]`. After configuration, restart Claude Code and run the `/context` command to verify whether the long context takes effect.

</div>

```json
{
  "env": {
    "ANTHROPIC_BASE_URL": "BASE_URL",
    "ANTHROPIC_AUTH_TOKEN": "MIMO_API_KEY",
    "ANTHROPIC_MODEL": "mimo-v2.5-pro",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "mimo-v2.5-pro",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "mimo-v2.5-pro",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "mimo-v2.5-pro"
  }
}
```

**2.**  **Create/edit** `.claude.json`

- macOS/Linux: `~/.claude.json`

- Windows: `User directory\.claude.json`

   ```json
   {
     "hasCompletedOnboarding": true
   }
   ```

**3.**  **Apply the configuration**

After completing the configuration, **reopen the terminal window** for the changes to take effect.

### Use Claude Code CLI

Navigate to your project directory and run:

```bash
claude
```

On first launch, complete the following: select "**Trust This Folder**" to allow Claude Code to access project files. After startup, use the `/status` command to verify the current configuration and model status.

## Use the Claude Code IDE Plugin

Claude Code provides a VS Code IDE plugin. For configuration reference, see the official documentation [Use Claude Code in VS Code](https://code.claude.com/docs/en/vs-code#vs-code-extension-vs-claude-code-cli).

### Install Plugin

Search for and install the **Claude Code for VS Code** plugin from the VS Code Extensions marketplace.

![图片](https://platform.xiaomimimo.com/static/Cpd0bPIpdoHSNdxFu4Yc34W9n52.fdfd71b3.png)

### Configure the Model

Open VS Code settings, search for `Claude Code: Environment Variables`, and then manually configure it in `settings.json`:

```json
{
  "claudeCode.preferredLocation": "panel",
  "claudeCode.selectedModel": "mimo-v2.5-pro",
  "claudeCode.environmentVariables": [
    {
      "name": "ANTHROPIC_BASE_URL",
      "value": "BASE_URL"
    },
    {
      "name": "ANTHROPIC_AUTH_TOKEN",
      "value": "MIMO_API_KEY"
    },
    {
      "name": "ANTHROPIC_DEFAULT_SONNET_MODEL",
      "value": "mimo-v2.5-pro"
    },
    {
      "name": "ANTHROPIC_DEFAULT_OPUS_MODEL",
      "value": "mimo-v2.5-pro"
    },
    {
      "name": "ANTHROPIC_DEFAULT_HAIKU_MODEL",
      "value": "mimo-v2.5-pro"
    }
  ]
}
```

<div className='mdx-highlight'>

If Claude Code CLI is already installed, the VS Code plugin will automatically reuse the CLI configuration. To configure independently, specify the environment variables in the plugin settings as shown above.

</div>

## FAQ

### Installation fails on Windows?

Ensure the following dependencies are installed:

- Node.js 18+

- Git for Windows

If you encounter permission issues with npm, try running the terminal as administrator, or use nvm to manage Node.js versions.


--- DOCUMENT: OpenClaw Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/openclaw.md

# OpenClaw Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support OpenClaw, and you can refer to this article for configuration and usage.

## Prerequisites

### Obtain Credentials

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 608px" />
</colgroup>
<thead>
<tr>
<th>Usage</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are both examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go API call</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol:`https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format:`sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format:`tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [ Subscription Management ](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

<div className='mdx-highlight'>

Note: When OpenClaw uses MiMo under the Anthropic protocol, since the assistant containing tool calls is missing `reasoning_content`, the API will return a 400 error. For details, see [[Important Notice]Passing Back reasoning_content in Multi-Turn Conversations for Agent Products](https://platform.xiaomimimo.com/docs/zh-CN/usage-guide/passing-back-reasoning_content) .

</div>

## Install OpenClaw

Precondition:[ Node.js 22 or later](https://nodejs.org/en/download/)

macOS/Linux：

```bash
curl -fsSL https://openclaw.ai/install.sh | bash
```

Windows (PowerShell)：

```bash
iwr -useb https://openclaw.ai/install.ps1 | iex
```

![图片](https://platform.xiaomimimo.com/static/Fku5bnTYrovJgKxeJQsckRaHnDf.dc535a48.png)

## Configure and Use MiMo Model

<div className='mdx-highlight'>

**Precautions:** 
**OpenClaw supports the preset configuration of MiMo Pay-as-you-go APIs, which can be configured through Method 1 Interactive Configuration Wizard.** 
**OpenClaw has not yet added the MiMo Token Plan preset configuration and needs to manually modify the configuration file through Method 2.** 

</div>

### Method 1: Interactive Configuration Wizard 

After the installation is complete, the configuration process will automatically start. You can also run the following command to start the configuration: 

```bash
openclaw onboard --install-daemon
```

**1. Configure Supplier**

![图片](https://platform.xiaomimimo.com/static/IksBbrAYIotzr4x7LYUc0HN1nUd.ffaf9af7.png)

![图片](https://platform.xiaomimimo.com/static/Yn71b6ouRoIMHvxP42mcqOUMnfc.2aa88eec.png)

- I understand this is personal-by-default and shared/multi-user use requires lock-down. Continue? ➡️ Yes

- Onboarding mode ➡️ QuickStart

- Config handling ➡️ Use existing values

- Model/auth provider ➡️ Xiaomi

**2. Configure the model and API Key**

![图片](https://platform.xiaomimimo.com/static/FYdubTkJcoEQtJx0mCWcKCXsnlg.1803fd19.png)

**3.**  **Continue to complete the subsequent configuration**

- Select channel ➡️ Choose the channel you need

- Configure skills ➡️ Install the skills you need

- Complete Setup

**4. Test Robot**

- How do you want to hatch your bot? ➡️ You can chat with the bot in TUI/Web UI

   - TUI: Enter `openclaw tui`, and if the conversation is successful, it indicates successful configuration

![图片](https://platform.xiaomimimo.com/static/Z5qUbi1IUo67npxsIMZcQ9jmnct.a88e7cbb.png)

   - Web UI: Access the Web UI by opening the `Web UI (with token)` link displayed in the terminal 

![图片](https://platform.xiaomimimo.com/static/MeFvbNm93oUCWZx58ZlcU8BMnU5.aed47535.png)

![图片](https://platform.xiaomimimo.com/static/NQ1UbJ7n6oKLcPxEjIicRNQTnYf.4863ca44.jpeg)

### Method 2: Modify the Configuration File 

 Copy the following content in full to the configuration file`~/.openclaw/openclaw.json` (replace BASE_URL and API Key as needed in actual use):

<div className='mdx-highlight'>

**Notes: Token Plan only supports configuration via Method 2. When using Token Plan, you need to delete the** `"auth"` **field in the configuration file, and you need to add a provider to distinguish it from the pre-set MiMo gateway.**  

</div>

**Token Plan** **Configuration Example:** 

**Delete the** `"auth"` **field**  

```json
 "auth": {
    "profiles": {
      "xiaomi:default": {
        "provider": "xiaomi",
        "mode": "api_key"
      }
    }
  }
```

Add a new provider under the models.provider path. Do not set the provider name to `xiaomi`, to distinguish it from the pre-set MiMo gateway. For example, set it to `xiaomi-coding`

The corresponding default agent configuration also needs to add the corresponding model, with the format ` provider name/model name `, for example ` xiaomi-coding/mimo-v2-pro `

```json
{
  "models": {
    "mode": "merge",
    "providers": {
      "xiaomi-coding": {
        "baseUrl": "BASE_URL",
        "apiKey": "API_KEY",
        "api": "openai-completions",
        "models": [
          {
            "id": "mimo-v2.5-pro",
            "name": "mimo-v2.5-pro",
            "reasoning": true,
            "input": [
              "text"
            ],
            "contextWindow": 1048576,
            "maxTokens": 32000
          },
          {
            "id": "mimo-v2.5",
            "name": "mimo-v2.5",
            "reasoning": true,
            "input": [
              "text",
              "image"
            ],
            "contextWindow": 262144,
            "maxTokens": 32000
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "xiaomi-coding/mimo-v2.5-pro"
      },
      "models": {
        "xiaomi-coding/mimo-v2.5": {},
        "xiaomi-coding/mimo-v2.5-pro": {}
      }
    }
  }
}
```

**Example of Pay-as-you-go API Configuration** 

```json
 {
   "auth": {
    "profiles": {
      "xiaomi:default": {
        "provider": "xiaomi",
        "mode": "api_key"
      }
    }
  },
  "models": {
    "mode": "merge",
    "providers": {
      "xiaomi": {
        "baseUrl": "BASE_URL",
        "apiKey": "API_KEY",
        "api": "openai-completions",
        "models": [
          {
            "id": "mimo-v2.5-pro",
            "name": "mimo-v2.5-pro",
            "reasoning": true,
            "input": [
              "text"
            ],
            "contextWindow": 1048576,
            "maxTokens": 32000
          },
          {
            "id": "mimo-v2.5",
            "name": "mimo-v2.5",
            "reasoning": true,
            "input": [
              "text",
              "image"
            ],
            "contextWindow": 262144,
            "maxTokens": 32000
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "xiaomi/mimo-v2.5-pro"
      },
      "models": {
        "xiaomi/mimo-v2.5": {},
        "xiaomi/mimo-v2.5-pro": {}
      }
    }
  }
}
```

## Connect to More Channels 

OpenClaw provides more channels for you to interact with the robot, such as Web UI, Discord, Feishu, etc. You can refer to the official documentation to set up these channels:[Chat Channels - OpenClaw](https://docs.openclaw.ai/channels).

## FAQ

### Why can't I find `mimo-v2-pro` and `mimo-v2-omni` in the model list when using OpenClaw Interactive Configuration?

`mimo-v2-pro` and `mimo-v2-omni` have been updated to OpenClaw 2026.3.19 and later versions. Please update the version and try again.


--- DOCUMENT: Hermes Agent Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/hermes-agent.md

# Hermes Agent Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support Hermes Agent. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

## Install Hermes Agent

Hermes Agent supports Linux, macOS, WSL2 (Windows), and more. For more information, refer to the [Hermes Agent Official Documentation](https://hermes-agent.nousresearch.com/docs/).

- Linux / macOS: No additional steps required.

- Windows: Refer to [Install WSL](https://learn.microsoft.com/en-us/windows/wsl/install) to install WSL2, then run the commands below in WSL2.

**Installation Command:**

```bash
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
```

**After installation, reload the terminal environment:**

```bash
source ~/.bashrc   # or source ~/.zshrc
```

**Verify installation (if a version number is displayed, the installation was successful):**

```bash
hermes --version
```

After installation, the following interface will appear:

![图片](https://platform.xiaomimimo.com/static/H2j5bNbhioaLeLxhORfcfjB6nMu.09cd72f2.png)

## Configure a Predefined Provider

**1. Select Quick Setup**

Choose Quick setup for initial configuration.

> If not configured initially, you can re-enter the setup wizard via `hermes setup`.

![图片](https://platform.xiaomimimo.com/static/OPcIbfbbbomDXQxmf7ecrjhhnYb.ce8cdddd.png)

**2. Select Provider** `Xiaomi MiMo`

![图片](https://platform.xiaomimimo.com/static/G8LlbfAvToOfUsxOoWscHY3Anlg.884bade2.png)

**3. Fill in Configuration**

Set API Key, Base URL, and default model as guided. The API Key and Base URL should be filled according to your credential type.

![图片](https://platform.xiaomimimo.com/static/OKIebqERYosj5Ex1DAbcxPalnvd.7a0c4ba7.png)

Follow the remaining steps as needed.

<div className='mdx-highlight'>

**If you previously configured Pay-as-you-go MiMo API and need to switch to Token Plan:**
- **Method 1:** Edit `~/.hermes/.env` file, replace `XIAOMI_API_KEY` and `XIAOMI_BASE_URL` with Token Plan credentials (open a new terminal after configuration).
- **Method 2:** Use a custom provider for configuration.

</div>

**4. After configuration, the following interface will appear:**

![图片](https://platform.xiaomimimo.com/static/MiksbQQkpoC2c1xH6mqcQ6Oynfh.c9a04e41.png)

## Configure a Custom Provider

### Configure Basic Settings

Replace `BASE_URL` and `MIMO_API_KEY` in the following methods with your actual credentials.

**Method 1: Quick configuration via terminal commands**

<div className='mdx-highlight'>

Here `model.provider` can only be set to `custom`. Custom names like `xiaomi-coding` will be invalid.

</div>

```bash
hermes config set model.provider custom
hermes config set model.base_url BASE_URL
hermes config set model.api_key MIMO_API_KEY
hermes config set model.default mimo-v2.5-pro
```

After configuration, you can view the settings in `~/.hermes/config.yaml`.

**Method 2: Manually edit configuration file**

Edit `~/.hermes/config.yaml` manually:

```bash
model:
  provider: custom
  base_url: BASE_URL
  api_key: MIMO_API_KEY
  default: mimo-v2.5-pro
```

### Verify Configuration

After configuration, run the following command to verify:

```bash
hermes doctor
```

## Use Hermes Agent

After configuration, run the following command to start:

```bash
hermes            # Classic CLI mode
hermes --tui      # Modern TUI mode
```


--- DOCUMENT: Kilo Code Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/kilocode.md

# Kilo Code Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support Kilo Code. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

<div className='mdx-highlight'>

Note: When Kilo Code uses MiMo under the Anthropic protocol, since the assistant containing tool calls is missing `reasoning_content`, the API will return a 400 error. For details, see [[Important Notice]Passing Back reasoning_content in Multi-Turn Conversations for Agent Products](https://platform.xiaomimimo.com/docs/zh-CN/usage-guide/passing-back-reasoning_content) .

</div>

## Use Kilo Code CLI

### Install Kilo Code CLI

Node.js 18 or later is required.

**Installation command:**

```bash
npm install -g @kilocode/cli
```

**Verify installation (success if version number is displayed):**

```bash
kilocode --version
```

### Configure Basic Settings

Edit or create the `config.json` configuration file at the following paths:

- **macOS/Linux**: `~/.config/kilo/config.json`

- **Windows**: `User Directory\.config\kilo\config.json`

Copy the following content into the configuration file (replace `BASE_URL` and `MIMO_API_KEY` as needed):

```bash
{
  "$schema": "https://kilo.ai/config.json",
  "disabled_providers": [],
  "provider": {
    "mimo": {
      "name": "MiMo",
      "npm": "@ai-sdk/openai-compatible",
      "models": {
        "mimo-v2.5-pro": {
          "name": "mimo-v2.5-pro",
          "options": {
            "thinking": {
              "type": "enabled"
            }
          }
        }
      },
      "options": {
        "apiKey": "MIMO_API_KEY",
        "baseURL": "BASE_URL"
      }
    }
  },
  "permission": {
    "bash": "allow"
  }
}
```

<div className='mdx-highlight'>

For more detailed configuration information, visit the [Kilo Code CLI Official Documentation](https://kilo.ai/docs/cli).

</div>

### Use Kilo Code CLI

After completing the above configuration, open a new terminal and run the following command to start Kilo Code CLI:

```bash
kilocode
```

Once started, enter `/models` to switch models, and you can use MiMo models in Kilo Code CLI.

## Use Kilo Code IDE Plugin

### Install Plugin

Search for and install the **Kilo Code** plugin in the VS Code Extensions marketplace.

![图片](https://platform.xiaomimimo.com/static/LwoAbbDLOo5YtextdBGcnmwUnpd.3c495f09.png)

### Configure a Predefined Provider (Recommended)

Click Providers --> Show more providers, search for `Xiaomi`, select the corresponding Provider, and fill in the API Key.

<div className='mdx-highlight'>

When using the **Xiaomi Token Plan**, you need to select the Provider corresponding to the Base URL displayed on the [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page.
- `https://token-plan-cn.xiaomimimo.com/*`: Xiaomi Token Plan (China)
- `https://token-plan-sgp.xiaomimimo.com/*`: Xiaomi Token Plan (Singapore)
- `https://token-plan-ams.xiaomimimo.com/*`: Xiaomi Token Plan (Europe)

</div>

![图片](https://platform.xiaomimimo.com/static/FHKXbyRaMoX4C0x3jiEcjuKInVh.06649639.png)

### Configure a Custom Provider

Fill in the relevant information according to the following configuration.

**1.**  **Select Custom Provider**

![图片](https://platform.xiaomimimo.com/static/EVQHbk7Zlo8XnQxNXT0c4VZAneh.34a312fd.png)

**2.**  **Fill in configuration details**

- **Provider ID** and **Display name**: Fill in as needed

- **Base URL**: Enter the BASE_URL obtained from your usage method

- **API Key**: Enter the API Key obtained from your usage method

- **Models**: Add as needed, e.g. `mimo-v2.5-pro`

![图片](https://platform.xiaomimimo.com/static/DdUBbS2OHoBJb7xQuHZcF8zmngc.f10c413e.png)

Other unmentioned parameters can be adjusted as needed.

### Use Kilo Code Plugin

After successful configuration, switch to the configured model and enter your requirements in the input box to start using.

![图片](https://platform.xiaomimimo.com/static/Se1ZbimQhonqsoxJYEecFOY5npB.07539c7a.png)

## FAQ

### When verifying installation on Windows, I encounter the following error. How to resolve?

> It seems that your package manager failed to install the right version of the Kilo CLI for your platform. You can try manually installing "@kilocode/cli-windows-x64" or "@kilocode/cli-windows-x64-baseline" package

Run the command `npm install -g @kilocode/cli-windows-x64` as suggested to resolve the issue.


--- DOCUMENT: Cherry Studio Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/cherrystudio.md

# Cherry Studio Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support Cherry Studio. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

## Install Cherry Studio

Cherry Studio is a desktop AI client that supports multi-model conversations.

- Official website: https://www.cherry-ai.com

- Github: https://github.com/CherryHQ/cherry-studio

## Configure Basic Settings

**1.**  **Find provider** `Xiaomi MiMo`

Click the settings icon in the upper right corner, go to the Model Services page, and search for `Xiaomi MiMo` in the search box.

![图片](https://platform.xiaomimimo.com/static/CZhDbutx9o7LeYxOjEoc0RBQnxe.37adec70.png)

**2.**  **Configure basic settings**

**Pay-as-you-go MiMo API**

Since the `Xiaomi MiMo` model service is already provided by Cherry Studio officially, you only need to provide the API Key obtained through this method. Keep the API Host unchanged.

![图片](https://platform.xiaomimimo.com/static/IfjXbN3Tcozm8MxS9XTcDWoDnLf.1f234430.png)

**Token Plan**

After successfully subscribing to Token Plan, replace with the dedicated Token Plan API Key and API Host (BASE_URL).

<div className='mdx-highlight'>

Note: Token Plan is temporarily unavailable in Agent mode.

</div>

## Use Cherry Studio

Select the model you need to use from the model list, and you can have a normal conversation.

![图片](https://platform.xiaomimimo.com/static/QXSmbNqVlohMGExFuqfcvjrHnwc.fb7253fe.png)

### Enable Thinking Mode (Optional)

Click assistant settings and add a custom parameter: `"thinking": {"type": "enabled"}`.

You can also adjust temperature, context window, and other parameters as needed.

![图片](https://platform.xiaomimimo.com/static/M7Fpb4Gn4omCO4xCbmTcvzFwnKg.cc799b69.png)

![图片](https://platform.xiaomimimo.com/static/NHoTbq2eoo1EVfxkrFRcMy8wnNe.0fd35685.png)


--- DOCUMENT: Qwen Code Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/qwencode.md

# Qwen Code Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support Qwen Code. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li><li>Anthropic Compatibility Protocol: `https://api.xiaomimimo.com/anthropic`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li><li>Anthropic Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/anthropic`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

## Use Qwen Code CLI

### Install Qwen Code CLI

**Installation commands:**

- macOS/Linux

```bash
bash -c "$(curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen.sh)" -s --source bailian
```

- Windows

```bash
curl -fsSL -o %TEMP%\install-qwen.bat https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen.bat && %TEMP%\install-qwen.bat --source bailian
```

**Verify the installation (a version number output indicates success):**

```bash
qwen --version
```

### Configure Settings

**1.**  **Select API Key -> Custom API Key to enter custom configuration**

![图片](https://platform.xiaomimimo.com/static/KFCmbZCRkoH1IOxx6x0cEzcEnAc.fc4edc6b.png)

![图片](https://platform.xiaomimimo.com/static/AlRibRrhIoD2S3x3YhRcS4JFnSd.ddaa3f0d.png)

**2.**  **Edit the configuration file**

![图片](https://platform.xiaomimimo.com/static/XPfhbXATyoSJcOx4EsaclpSTnYc.457839d1.png)

<div className='mdx-highlight'>

For more detailed configuration information, visit the [Qwen Code official configuration documentation](https://qwenlm.github.io/qwen-code-docs/en/users/configuration/model-providers/).

</div>

Edit or create the `settings.json` file at the following path:

- macOS/Linux: `~/.qwen/settings.json`

- Windows: `User directory\.qwen\settings.json`

Copy the following content into the configuration file (replace with your actual settings when using):

<div className='mdx-highlight'>

When configuring basic information, you need to first check if the `MIMO_API_KEY` environment variable exists. If it does, please clear it or replace the value with the API Key obtained through the corresponding usage method.

</div>

```bash
{
  "env": {
    "MIMO_API_KEY": "MIMO_API_KEY"
  },
  "modelProviders": {
    "openai": [
      {
        "id": "mimo-v2.5-pro",
        "name": "mimo-v2.5-pro",
        "baseUrl": "BASE_URL",
        "envKey": "MIMO_API_KEY"
      }
    ]
  },
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  },
  "model": {
    "name": "mimo-v2.5-pro"
  },
  "$version": 3
}
```

### Use Qwen Code CLI

After completing the above configuration, open a new terminal and run the following command to start Qwen Code CLI:

```bash
qwen
```

Once started, you can use MiMo models in Qwen Code CLI.

![图片](https://platform.xiaomimimo.com/static/DZQYb5P6EoqfmAxCScDcRIkwnWc.17e4bbfe.png)

## Use the Qwen Code IDE Plugin

### Install the Plugin

Search for and install the **Qwen Code Companion** plugin from the VS Code Extensions marketplace.

![图片](https://platform.xiaomimimo.com/static/Fe4qbzUcnoJswXxiLw0cgpcBncb.353d82bf.png)

### Configure Settings

Follow the same steps as described in the Qwen Code CLI configuration section above.

### Use the Qwen Code Plugin

Click the Qwen Code icon in the top-right corner to open the dialog.

![图片](https://platform.xiaomimimo.com/static/TZEyb0zIDodYvgxHbqscutfAnff.d6bb3e40.png)

Type or click `/`, then select `Switch model` to change the model.

![图片](https://platform.xiaomimimo.com/static/VQftbMiUKoFYYWx2Xsycbj0FnGf.34bfb7ca.png)


--- DOCUMENT: CodeBuddy Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/codebuddy.md

# CodeBuddy Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support CodeBuddy. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

## Use CodeBuddy IDE

### Install CodeBuddy

Visit the [CodeBuddy website](https://www.codebuddy.ai/home) to download and install the IDE, which supports major operating systems (Windows, macOS).

### Configure MiMo Model

**1. Configure Custom Model**

Create or modify the configuration file `models.json` to add custom models. Example configuration:

- **macOS:** `~/.codebuddy/models.json`

- **Windows:** `User Directory\.codebuddy\models.json`

`BASE_URL` and `MIMO_API_KEY` should be modified according to your credential acquisition method.

```json
{
  "models": [
    {
      "id": "mimo-v2.5-pro",
      "name": "mimo-v2.5-pro",
      "vendor": "MiMo",
      "apiKey": "MIMO_API_KEY",
      "url": "BASE_URL/chat/completions",
      "supportsToolCall": true,
      "supportsImages": false
    },
    {
      "id": "mimo-v2.5",
      "name": "mimo-v2.5",
      "vendor": "MiMo",
      "apiKey": "MIMO_API_KEY",
      "url": "BASE_URL/chat/completions",
      "supportsToolCall": true,
      "supportsImages": true
    }
  ]
}
```

**2. View and Switch Models**

After configuration, turn off `Auto mode` and open the model list to see the configured MiMo models.

![图片](https://platform.xiaomimimo.com/static/WI2lblKSeo1O4kxSL4ucFwPPn2f.16f48497.png)

### Use MiMo Model

Select the configured model to start conversations, coding, and other operations.

![图片](https://platform.xiaomimimo.com/static/Smtkbx6rYohJJ7xjG5ic18mhndI.729a4c3e.png)

## Use CodeBuddy IDE Plugin

### Install Plugin

Search for `Tencent Cloud CodeBuddy` in the VS Code extension marketplace and install the plugin.

![图片](https://platform.xiaomimimo.com/static/EjBkbNws4ox1B8xpW6lcKMAOn7f.e212a551.png)

### Configure MiMo Model

Refer to the `models.json` configuration file in the "Use CodeBuddy IDE" section. If previously configured, it will be automatically loaded.

![图片](https://platform.xiaomimimo.com/static/FDBtbBSaDoa70Bx2vBBcHNEynPg.e9336978.png)

## Use CodeBuddy CLI

### Install CodeBuddy CLI

**Install via npm (requires Node.js 18.20 or newer):**

```bash
npm install -g @tencent-ai/codebuddy-code
```

**Verify installation (if a version number is displayed, the installation was successful):**

```bash
codebuddy --version
```

### Configure MiMo Model

<div className='mdx-highlight'>

The `BASE_URL` and `API Key` for **Pay-as-you-go MiMo API** and **Token Plan** are different. Please configure accordingly.

</div>

Refer to the `models.json` configuration file in the "Use CodeBuddy IDE" section. If previously configured, it will be automatically loaded.

### Use CodeBuddy CLI

After configuration, navigate to your project directory and run:

```bash
codebuddy
```

After startup, use `/model` to view or switch models, and `/status` to check the current model.

## FAQ

### Model not appearing in the dropdown after configuration?

- Check if the JSON syntax is correct

- If the `availableModels` field is configured, ensure the model id is included


--- DOCUMENT: Cline Configuration ---
URL: https://platform.xiaomimimo.com/static/docs/integration/cline.md

# Cline Configuration

**Pay-as-you-go MiMo API** and **Token Plan** both support Cline. Refer to this guide for configuration and usage.

## Prerequisites

### Obtain Credentials 

Supports two usage methods, but the corresponding credential acquisition methods are different:

<table>
<colgroup>
<col />
<col style="width: 191px" />
<col style="width: 700px" />
</colgroup>
<thead>
<tr>
<th>Usage Method</th>
<th>Description</th>
<th>Acquisition Method (BASE_URL and API Key below are examples)</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pay-as-you-go MiMo API</td>
<td>Charged based on actual usage, suitable for light use</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://api.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `sk-xxxxx`</li></ul></li></ul><br />Go to [API Keys](https://platform.xiaomimimo.com/#/console/api-keys) to create an API Key</td>
</tr>
<tr>
<td>Token Plan</td>
<td>Fixed subscription fee, with limited calls based on the package</td>
<td><ul><li>BASE_URL<ul><li>OpenAI Compatibility Protocol: `https://token-plan-cn.xiaomimimo.com/v1`</li></ul></li><li>API Key<ul><li>Format: `tp-xxxxx`</li></ul></li></ul><br />After successful subscription, go to [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) to obtain the exclusive Base URL and API Key</td>
</tr>
</tbody>
</table>

## Use Cline CLI

### Install Cline CLI

**Prerequisites:** Node.js 20 or later is required (Node.js 22 recommended).

**Installation command:**

```bash
npm install -g cline
```

**Verify installation (if a version number is displayed, the installation was successful):**

```bash
cline --version
```

### Configure Basic Settings

Cline CLI uses the `cline auth` command to configure API providers. Run the following command to configure MiMo model:

```bash
cline auth -p openai -k MIMO_API_KEY -b BASE_URL -m mimo-v2.5-pro
```

Parameter descriptions:

- `-p openai`: Select OpenAI-compatible provider

- `-k`: Enter the API Key obtained from the corresponding usage method

- `-b`: Enter the BASE_URL obtained from the corresponding usage method

- `-m`: Enter the model ID, e.g. `mimo-v2.5-pro`

<div className='mdx-highlight'>

For more detailed configuration information, visit the [Cline CLI Official Documentation](https://docs.cline.bot/cline-cli/cli-reference).

</div>

You can also configure via the interactive wizard by running `cline auth` and following the prompts.

### Use Cline CLI

After completing the configuration, open a new terminal and run the following command to start Cline CLI.

> If you prefer the classic terminal interface, select `Exit` and run `cline --tui` to return to the familiar command-line environment.

```bash
cline
```

After starting, you can use MiMo models in Cline CLI.

## Use Cline IDE Plugin

### Install Plugin

Search for and install the **Cline** plugin in the VS Code Extensions marketplace.

![图片](https://platform.xiaomimimo.com/static/NDc4bUVoUotWXgx28ghcCoG7nRb.58ee6d35.png)

### Configure Basic Settings

Open the Cline plugin in VS Code and fill in the following configuration:

- Required settings:

   - **API Provider**: Select `OpenAI Compatible`

   - **Base URL**: Fill in the BASE_URL obtained through the corresponding usage method

   - **API Key**: API Key obtained from the corresponding usage method

   - **Model ID**: Enter the model name `mimo-v2.5-pro`

- Optional settings:

   - Uncheck **Supports Images**

   - Set **Context Window Size** to `1048576`

   - Set **Temperature** to `1.0`, adjustable based on task requirements

Other parameters not mentioned can be adjusted as needed.

### Use Cline Plugin

After successful configuration, enter your request in the input box, for example to generate code:

![图片](https://platform.xiaomimimo.com/static/ALYmbrBaEoyUztxcoHVcBVLLnfb.88382e9a.png)


--- DOCUMENT: Web Search ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/tool-calling/web-search.md

# Web Search

Web Search is a basic online search tool that helps your large model obtain real-time public online information (such as news, products, weather, etc.).

**Core Capabilities**

- **Flexible search modes**: Supports forced search and intent recognition. With intent recognition enabled, the model will autonomously decide whether to perform an online search without manual triggering.

- **Early search source return**: In the streaming response, the first packet will return all search sources.

- **Hybrid multi-tool invocation**: Can work with custom functions and tools; the model will automatically determine invocation priority and necessity.

- **Flexible response modes**: Supports both streaming and non-streaming responses, and both methods will return search and summary content.

## Quick Start

<div className='mdx-highlight'>

Note: The [Web Search Plugin](https://platform.xiaomimimo.com/#/console/plugin) must be activated prior to use.

</div>

### Enable the Service

1. Go to [Console → Plugin Management](https://platform.xiaomimimo.com/#/console/plugin), and activate the Web Search Plugin.

1. Web Search Plugin fee, refer to the [Pricing](https://platform.xiaomimimo.com/#/docs/pricing). Note: **Search invocation is determined by the model. A single search round (if required by the model) may initiate multiple keywords concurrently, resulting in multiple invocations of the Internet Content Plugin. You may use the** `max_keyword` **parameter to limit the maximum number of keywords per search round, thereby further controlling invocation frequency and costs**.

**Note**：For preparations such as obtaining an API Key, please refer to [First API Call](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call).

### Sample Code

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5-pro",
    "messages": [
        {
            "role": "user",
            "content": "武汉明天天气怎么样？"
        }
    ],
    "tools": [
        {
          "type": "web_search",
          "max_keyword": 3,
          "force_search": true,
          "limit": 1,
          "user_location": {
            "type": "approximate",
            "country": "China",
            "region": "Hubei",
            "city": "Wuhan"
          }
        }
    ],
    "max_completion_tokens": 1024,
    "temperature": 1.0,
    "top_p": 0.95,
    "stream": false,
    "stop": null,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "thinking": {
        "type": "disabled"
    }
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5-pro",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": "武汉明天天气怎么样？"
        }
    ],
    max_completion_tokens=1024,
    temperature=1.0,
    top_p=0.95,
    stream=False,
    stop=None,
    frequency_penalty=0,
    presence_penalty=0,
    extra_body={
        "thinking": {"type": "disabled"}
    },
    tools=[
        {
            "type": "web_search",
            "max_keyword": 3,
            "force_search": True,
            "limit": 1,
            "user_location": {
                "type": "approximate",
                "country": "China",
                "region": "Hubei",
                "city": "Wuhan"
            }
        }
    ],
    tool_choice="auto"
)

print(completion.model_dump_json())
```

**Response**

```json
{
    "id": "d9cbdd74d5384247a3b9f03580901588",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "根据搜索结果，武汉明天（2026年4月23日，周四）的天气情况如下：\\n\\n*   **天气状况**：白天为阴天，夜间转为晴天。\\n*   **气温范围**：最高气温18℃，最低气温10℃。\\n*   **风力风向**：北风，风力较小，为微风（风力小于3级）。\\n\\n**综合来看**，明天武汉白天阴天，夜间放晴，气温相比今天（4月22日）有所回升，但昼夜温差仍达8℃左右。建议您根据早晚和午后的温差，采用“洋葱式穿衣法”，方便随时增减衣物。明天无需携带雨具，适合进行户外活动。",
                "role": "assistant",
                "annotations": [
                    {
                        "type": "url_citation",
                        "url": "https://news.qq.com/rain/a/20260422A03GDF00",
                        "title": "小雨转晴再迎小雨!武汉未来三天阴晴交替,湿度大温差显_腾讯新闻",
                        "summary": "今天是2026年4月22日,武汉白天天气为小雨,北风微风,夜晚天气为多云,北风微风,最高气温15°C,最低气温11°C,空气湿度92%,体感温度9.5°C,空气质量优。雨天道路湿滑,出行请携带雨具,注意防滑,驾车保持安全车距。明日武汉天气为阴,微风,夜间晴,微风,最高气温18°C,最低气温10°C。未来三天,武汉天气以阴到多云为主,24日夜间转小雨,25日白天有小雨,气温逐步回升,最高气温从18°C升至25°C,最低气温从10°C升至13°C,昼夜风力均为微风。降雨时段需注意低洼路段可能短时积水,建议提前检查排水设施,避免涉水通行。近期武汉天气总体平稳,但阴雨相间,湿度偏高,体感偏凉;24日起气温明显回升,昼夜温差达11°C左右。建议采用洋葱式穿衣法,兼顾早晚清凉与午后温和;室内注意通风除湿,防范衣物、食品受潮霉变;雨天晾晒条件不佳,可优先使用烘干设备。此稿由AI生成(来源:极目新闻)",
                        "site_name": "腾讯网",
                        "publish_time": "2026-04-22T11:24:12+08:00",
                        "logo_url": "https://th.bochaai.com/favicon?domain_url=https://news.qq.com/rain/a/20260422A03GDF00"
                    },
                    {
                        "type": "url_citation",
                        "url": "https://bocha.cn/share/e79b4068-66c6-4f13-bae2-ecbd48336bc5",
                        "title": "2026年04月22日武汉天气预报",
                        "summary": "2026年04月22日武汉天气预报:\\n04/22 (周三):\\n天气:小雨转多云,温度:16/11°C,风向风力:北风<3级\\n04/23 (周四):\\n天气:阴转晴,温度:18/10°C,风向风力:北风<3级\\n04/24 (周五):\\n天气:小雨,温度:22/13°C,风向风力:北风<3级\\n04/25 (周六):\\n天气:多云转晴,温度:25/13°C,风向风力:北风<3级\\n04/26 (周日):\\n天气:多云转阴,温度:28/17°C,风向风力:北风<3级\\n04/27 (周一):\\n天气:阴转晴,温度:28/18°C,风向风力:北风<3级\\n04/28 (周二):\\n天气:多云转阴,温度:29/19°C,风向风力:北风<3级",
                        "site_name": "博查",
                        "publish_time": "2026-04-22T00:00:00+08:00",
                        "logo_url": "https://th.bochaai.com/favicon?domain_url=https://bocha.cn/share/e79b4068-66c6-4f13-bae2-ecbd48336bc5"
                    },
                    {
                        "type": "url_citation",
                        "url": "https://news.qq.com/rain/a/20260421A06R9300",
                        "title": "【明日天气预报】武汉2026年04月22日天气预报,小雨转多云,北风转北风<3级_腾讯新闻",
                        "summary": "武汉04月22日(周三)天气预报,天气现象小雨转多云,\\n风向风力:\\n北风转北风<3级。最高气温16°C摄氏度,最低气温11摄氏度。\\n感冒指数:\\n少发,\\n无明显降温,感冒机率较低。运动指数:\\n适宜,\\n天气较好,尽情感受运动的快乐吧。过敏指数:\\n易发,\\n应减少外出,外出需采取防护措施。穿衣指数:\\n较冷,\\n建议着厚外套加毛衣等服装。洗车指数:\\n较适宜,\\n无雨且风力较小,易保持清洁度。紫外线指数:\\n最弱,\\n辐射弱,涂擦SPF8-12防晒护肤品。\\n【来源:综合自中国气象局】\\n更多出行游玩、民生资讯、办事服务等精彩内容,欢迎下载九派新闻APP查看。声明:此文版权归原作者所有,若有来源错误或者侵犯您的合法权益,您可通过邮箱与我们取得联系,我们将及时进行处理。邮箱地址:jpbl@jp.jiupainews.com",
                        "site_name": "腾讯网",
                        "publish_time": "2026-04-21T19:32:10+08:00",
                        "logo_url": "https://th.bochaai.com/favicon?domain_url=https://news.qq.com/rain/a/20260421A06R9300"
                    }
                ],
                "tool_calls": null
            }
        }
    ],
    "created": 1776850783,
    "model": "mimo-v2.5-pro",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 204,
        "prompt_tokens": 2106,
        "total_tokens": 2310,
        "completion_tokens_details": {
            "reasoning_tokens": 0
        },
        "prompt_tokens_details": {
            "cached_tokens": 192
        },
        "web_search_usage": {
            "tool_usage": 3,
            "page_usage": 3
        }
    }
}
```

For detailed parameters and invocation instructions, please refer to the [OpenAI API](https://platform.xiaomimimo.com/#/docs/api/text-generation/openai-api). Anthropic API is not currently supported.

## Supported models

Currently supports `mimo-v2.5-pro`, `mimo-v2.5`, `mimo-v2-pro`, `mimo-v2-omni`, and `mimo-v2-flash` models.

## Price

The billing for the Web Search Plugin consists of the following two parts:

- **Usage of Web Search**: The number of times internet resources appear in one response of the Internet Service Plugin.

   - Cost per 1,000 calls from the Web Search tool: China ¥25 / 1K requests、Overseas $5 / 1K requests.

<div className='mdx-highlight'>

Note: When invoking Web Search via API, one search round will initiate concurrent keyword searches according to the `max_keyword` value, resulting in multiple uses of this plugin.

</div>

- **Model token fee**: The webpage content from internet search will be appended to the prompt, increasing the model’s input tokens. Billing is based on the model’s standard price. For price details, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing).

## FAQ

**Why doesn’t the model perform a web search after enabling online search?**

There may be three reasons:

- **Cache**: There is a 5-minute cache period after enabling / disabling online search. The online search switch will not take effect immediately within 5 minutes.

- **Model determines no need for search**: The model judges that the current query does not involve real-time information and can be answered directly with its own knowledge. To force a search, set `forced_search: true`.

- **Model not supported**: Currently `mimo-v2.5-pro`, `mimo-v2.5`,  `mimo-v2-pro`, `mimo-v2-omni`, and `mimo-v2-flash` supports online search.


--- DOCUMENT: Image Understanding ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/multimodal-understanding/image-understanding.md

# Image Understanding

The image understanding model can answer based on the images you provide, supporting both image URL and Base64 encoding as input methods, and is suitable for scenarios such as image description and classification. 

## Quick Start

<div className='mdx-highlight'>

Note：For preparations such as obtaining an API Key, please refer to [First API Call](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call).

</div>

Quickly experience the effect of image understanding by passing the model through the image URL method. The sample code is as follows. 

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

**Response**

```json
{
    "id": "be319773af414195b27a9b1cefc3fe6f",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "This is a serene, lush temperate old-growth forest scene, bathed in warm, golden hour light, likely early morning or late afternoon:\\n\\n1.  **Foreground & Stream**: A shallow, clear stream winds through the scene, its surface catching the sunlight to create shimmering highlights. Smooth, rounded river rocks, many covered in thick, vibrant green moss, line the stream's banks and sit partially submerged in the water. On the left, a large, detailed fern with full, feathery fronds anchors the mossy shore.\\n2.  **Midground & Forest Floor**: The forest floor is dense with verdant, mossy growth, small leafy shrubs, and undergrowth, creating a rich, textured green landscape. Ancient, gnarled trees with thick, textured trunks and sprawling, twisted branches rise up, their bases rooted in the mossy earth.\\n3.  **Light & Atmosphere**: Soft, dramatic sunbeams, crepuscular rays, filter through the misty forest canopy, cutting through the hazy air. Tiny particles like pollen or dust catch the light, adding an ethereal, magical quality. Mist hangs between the trees, softening the background and lending the scene a quiet, tranquil, almost enchanted mood.\\n\\nThe image conveys a sense of peace, untouched natural beauty, and the quiet magic of an old, undisturbed forest.",
                "role": "assistant",
                "tool_calls": null,
                "reasoning_content": "Got it, let's break down this image step by step. First, the setting is a lush, misty old-growth forest, early morning or late afternoon (golden hour, since the sunbeams are warm).\\n\\nStart with the foreground: a shallow, clear stream with smooth, moss-covered rocks lining its banks. The rocks are rounded, some partially submerged, with bright green moss growing thickly on them and the shore. On the left, a large, vibrant fern with detailed fronds sits on the mossy bank.\\n\\nThen the midground: the stream winds through the forest, with small shrubs and more mossy growth along its edges. The trees are ancient, with thick, gnarled trunks and sprawling, twisted branches, their bark textured and aged. The forest floor is covered in moss and undergrowth, feeling dense and verdant.\\n\\nThe background and lighting: soft, golden sunbeams (crepuscular rays) filter through the misty forest canopy, illuminating the air—you can see tiny particles (like dust or pollen) catching the light, creating a magical, ethereal glow. The mist hangs in the air between the trees, softening the background and adding depth, making the forest feel quiet, serene, and almost enchanted.\\n\\nOverall, it's a tranquil, lush temperate rainforest scene, full of natural detail, with warm, diffused light creating a peaceful, mystical atmosphere."
            }
        }
    ],
    "created": 1776850561,
    "model": "mimo-v2.5",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 574,
        "prompt_tokens": 1085,
        "total_tokens": 1659,
        "completion_tokens_details": {
            "reasoning_tokens": 288
        },
        "prompt_tokens_details": {
            "cached_tokens": 1081,
            "image_tokens": 1024
        }
    }
}
```

## Supported models

Currently, only the `mimo-v2.5`, `mimo-v2-omni` models are supported.

## Image Input Method

Supported ways to upload images are as follows:

- Image URL Input: A publicly accessible image URL address must be provided. 

- Base64 Encoding Input: Convert the image to a Base64-encoded string before passing it in.

### Image URL Input

Directly pass in the image via the publicly accessible image URL, which is suitable for scenarios where the image is already stored in a publicly accessible environment. The file size of a single image cannot exceed 50 MB.

#### OpenAI API

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

#### Anthropic API

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/anthropic/v1/messages' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "max_tokens": 1024,
    "system": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "source": {
                        "type": "url",
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ]
}'
```

**Python**

```python
import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/anthropic"
)

message = client.messages.create(
    model="mimo-v2.5",
    max_tokens=1024,
    system="You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "source": {
                        "type": "url",
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ]
)

print(message.content)
```

### Base64 Encoded Input

Convert the image file to a Base64-encoded string and then pass it in, which is suitable for scenarios where the image cannot be accessed via a public network URL. The size of the converted Base64-encoded string cannot exceed 50 MB.

#### OpenAI API

<div className='mdx-highlight'>

Please include the prefix before Base64 encoding:`data:{MIME_TYPE};base64,$BASE64_IMAGE`
- `{MIME_TYPE}`: The MIME type (media type) of the image, used to identify the image format, needs to be replaced with the MIME value corresponding to the actual image.
- `$BASE64_IMAGE`: A pure Base64-encoded string of the image file (without any prefix).

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "data:{MIME_TYPE};base64,$BASE64_IMAGE"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "data:{MIME_TYPE};base64,$BASE64_IMAGE"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

#### Anthropic API

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/anthropic/v1/messages' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "max_tokens": 1024,
    "system": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "source": {
                        "type": "base64",
                        "media_type": "{MIME_TYPE}"
                        "data": "$BASE64_IMAGE"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ]
}'
```

**Python**

```python
import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/anthropic"
)

message = client.messages.create(
    model="mimo-v2.5",
    max_tokens=1024,
    system="You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024.",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "source": {
                        "type": "base64",
                        "media_type": "{MIME_TYPE}"
                        "data": "$BASE64_IMAGE"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the image"
                }
            ]
        }
    ]
)

print(message.content)
```

### Multi-image Input

Supports simultaneously passing in public network URLs or Base64-encoded strings of multiple images, and the model can parse the image content and return responses that match the image semantics.

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "data:{MIME_TYPE};base64,$BASE64_IMAGE"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the connections and differences between these two pictures"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/image/image_example.png"
                    }
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "data:{MIME_TYPE};base64,$BASE64_IMAGE"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the connections and differences between these two pictures"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

## Image Restrictions

- Image Formats: JPEG, PNG, GIF, WebP, BMP. 

- Image Size: 

   - When passed in as a URL: single imagefile sizedoes not exceed 50 MB.

   - When passed in as Base64 encoding: The size of the Base64 encoded string of a single image does not exceed 50 MB. 

- Number of images: When multiple images are passed in, the number of images is limited by the model's context length, and the total number of Tokens for all images and text must be less than the model's context length.

> Note: For calculating image tokens, please refer to [Explanation of Image Token Usage](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/image-understanding?target=explanation-of-image-token-usage-and-scaling-rules). For the model context length, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing). 

## Explanation of Image Token Usage and Scaling Rules

The calculation rules for images are relatively complex. For Token conversion and scaling rules, please refer to the following code. The estimated results are for reference only, and the actual usage shall be subject to the API response. 

```python
import math
from PIL import Image

PATCH_SIZE = 16
SPATIAL_MERGE_SIZE = 2
TEMPORAL_PATCH_SIZE = 2
IMAGE_MIN_PIXELS = 8192
IMAGE_MAX_PIXELS = 8388608

def calc_image_tokens(image_path: str) -> dict:
    image = Image.open(image_path)
    height = image.height
    width = image.width

    factor = PATCH_SIZE * SPATIAL_MERGE_SIZE  # 32

    h_bar = round(height / factor) * factor
    w_bar = round(width / factor) * factor

    if h_bar * w_bar > IMAGE_MAX_PIXELS:
        beta = math.sqrt((height * width) / IMAGE_MAX_PIXELS)
        h_bar = math.floor(height / beta / factor) * factor
        w_bar = math.floor(width / beta / factor) * factor
    elif h_bar * w_bar < IMAGE_MIN_PIXELS:
        beta = math.sqrt(IMAGE_MIN_PIXELS / (height * width))
        h_bar = math.ceil(height / beta / factor) * factor
        w_bar = math.ceil(width / beta / factor) * factor

    grid_t = 1
    grid_h = h_bar // PATCH_SIZE
    grid_w = w_bar // PATCH_SIZE
    num_tokens = (grid_t * grid_h * grid_w) // (SPATIAL_MERGE_SIZE ** 2)
    return num_tokens

if __name__ == "__main__":
   token = calc_image_tokens(image_path="xxx/test.jpg")
   print(token)
```

## Price

- Billing: Total cost is calculated based on the number of input, input (cache hits), and output tokens; for pricing, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing). 

   - The Token consumption of images can be calculated through [Explanation of Image Token Usage](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/image-understanding?target=explanation-of-image-token-usage-and-scaling-rules). The estimated results are for reference only, and the actual usage shall be subject to the API response. 

- View Bill: You can view your bill and usage on the [Billing](https://platform.xiaomimimo.com/#/console/usage) page in the Console. 

## FAQ

### Does it support local file upload?

`mimo-v2.5` and `mimo-v2-omni` models do not currently support uploading local image files. For supported upload methods, please refer to [Image Input Method](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/image-understanding?target=image-input-method).


--- DOCUMENT: Audio Understanding ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/multimodal-understanding/audio-understanding.md

# Audio Understanding

The audio understanding model can answer based on the audio you provide, supporting both audio URL and Base64 encoding as input methods, and is suitable for scenarios such as audio analysis. 

## Quick Start

<div className='mdx-highlight'>

Note：For preparations such as obtaining an API Key, please refer to [First API Call](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call).

</div>

Quickly experience the audio understanding effect by passing the audio URL into the model. The sample code is as follows.

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the audio"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the audio"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

**Response**

```json
{
    "id": "550a678a6c2046a29128883eaaf849e7",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "",
                "role": "assistant",
                "tool_calls": null,
                "reasoning_content": "Good morning. Could you tell me what the weather will be like today?"
            }
        }
    ],
    "created": 1776850627,
    "model": "mimo-v2.5",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 17,
        "prompt_tokens": 86,
        "total_tokens": 103,
        "completion_tokens_details": {
            "reasoning_tokens": 15
        },
        "prompt_tokens_details": {
            "audio_tokens": 25,
            "cached_tokens": 82
        }
    }
}
```

## Supported models

Currently, only the `mimo-v2.5`, `mimo-v2-omni` models are supported.

## Audio Input method

Supported audio input methods are as follows:

- Audio URL Input: A publicly accessible audio URL address must be provided.

- Base64 Encoding Input: Convert the audio to a Base64-encoded string before passing it in.

### Audio URL Input

Audio files can be directly passed in via a publicly accessible audio URL address, which is suitable for scenarios where the audio files are already stored in a publicly accessible environment. The size of a single audio file cannot exceed 100 MB.

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the audio"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://example-files.cnbj1.mi-fds.com/example-files/audio/audio_example.wav"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the audio"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

### Base64 encoding Input

Convert the audio file to a Base64-encoded string and then pass it in, which is suitable for scenarios where the audio file cannot be accessed via a public network URL. The size of the converted Base64-encoded string cannot exceed 50 MB.

<div className='mdx-highlight'>

Please include the prefix before Base64 encoding:`data:{MIME_TYPE};base64,$BASE64_AUDIO`
- `{MIME_TYPE}`: The MIME type (media type) of the audio, used to identify the audio format, which needs to be replaced with the MIME value corresponding to the actual audio.
- `$BASE64_AUDIO`: A pure Base64-encoded string of the audio file (without any prefix).

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "data:{MIME_TYPE};base64,$BASE64_AUDIO"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the audio"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "data:{MIME_TYPE};base64,$BASE64_AUDIO"
                    }
                },
                {
                    "type": "text",
                    "text": "please describe the content of the audio"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

## Audio Restrictions

- Audio Formats: MP3, WAV, FLAC, M4A, OGG.

> Audio Formats variants are numerous, and it cannot be guaranteed that all files can be recognized. Please verify through testing that the files can be recognized normally.

- Audio Size:

   - When passed in as a URL:  File size does not exceed 100 MB. 

   - When passed in as Base64 encoding:  The size of the Base64 encoded string of a single audio file does not exceed 50 MB. 

- Number of audios: When multiple audio files are input, the number of audio files is limited by the model's context length, and the total number of tokens for all audio and text must be less than the model's context length.

> Note: For calculating audio tokens, please refer to [Explanation of Audio Token Usage](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/audio-understanding?target=explanation-of-audio-token-usage). For the model context length, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing). 

## Explanation of Audio Token Usage

For the Token conversion of audio, please refer to the following code. The estimated results are for reference only, and the actual usage is subject to the API response. 

```bash
Total tokens ≈ Audio duration (in seconds, e.g., 10.6 seconds) * 6.25
```

## Price

- Billing: The total cost is calculated based on the number of input, input (cache hits), and output tokens; for pricing, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing). 

   - Audio Token consumption can be calculated through [Explanation of Audio Token Usage](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/audio-understanding?target=explanation-of-audio-token-usage). The estimated results are for reference only, and the actual usage is subject to the API response. 

- View Bill: You can view your bill and usage on the [Billing](https://platform.xiaomimimo.com/#/console/usage) page in the Console. 

## FAQ

### Does it support local file upload?

`mimo-v2.5` and `mimo-v2-omni` models do not currently support uploading local audio files. For supported upload methods, please refer to [Audio Input Method](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/audio-understanding?target=audio-input-method).


--- DOCUMENT: Video Understanding ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/multimodal-understanding/video-understanding.md

# Video Understanding

The video understanding model can answer based on the video you provide, supporting both video URL and Base64 encoding as input methods, and is suitable for scenarios such as video analysis. 

## Quick Start

<div className='mdx-highlight'>

Note：For preparations such as obtaining an API Key, please refer to [First API Call](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call).

</div>

Quickly experience the video understanding effect by passing the model through the video URL method. The sample code is as follows.

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/video/video_example.mp4"
                    },
                    "fps": 2,
                    "media_resolution": "default"
                },
                {
                    "type": "text",
                    "text": "please describe the content of the video"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/video/video_example.mp4"
                    },
                    "fps": 2,
                    "media_resolution": "default"
                },
                {
                    "type": "text",
                    "text": "please describe the content of the video"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

**Response**

```json
{
    "id": "a7a6fe52ffeb40ab9e699fe018592b16",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "The video features a small, fluffy white kitten with bright blue eyes sitting on a polished wooden floor. The kitten is positioned near a window draped with sheer, light-colored curtains, through which sunlight is streaming, casting warm shadows on the floorboards. In the background to the right, a potted green plant, resembling a Monstera, adds a touch of color to the room.\\n\\nThroughout the clip, the kitten is meowing repeatedly. It opens its mouth wide to let out high-pitched meows, looking slightly to its left before turning its gaze directly toward the camera. The audio consists entirely of the kitten's vocalizations.",
                "role": "assistant",
                "tool_calls": null,
                "reasoning_content": "The user wants me to describe the video provided.\\n\\n1.  **Analyze the video:**\\n*   **Subject:** A small white kitten with striking blue eyes.\\n*   **Action:** The kitten is sitting on a wooden floor near a window. It is meowing. Its mouth opens and closes repeatedly. It looks slightly to its left and then more directly forward.\\n*   **Setting:** Indoors. There's a window on the left with light-colored curtains. Sunlight is streaming in, casting shadows on the floor. In the background, there's a green plant (looks like a Monstera) in a pot. The walls are light-colored.\\n*   **Audio:** The audio consists of the kitten meowing. It's a series of high-pitched meows.\\n*   **Visual details:** The kitten is fluffy. The floor is polished wood. The lighting is warm and natural.\\n\\n2.  **Break down the description chronologically:**\\n*   **Start (00:00 - 00:01):** The video opens with a white kitten sitting on a wooden floor. It's positioned near a window with sheer curtains. Sunlight is hitting the floor. The kitten is looking slightly to the side.\\n*   **Middle (00:01 - 00:02):** The kitten opens its mouth wide to meow. It does this multiple times. Its gaze shifts a bit. The sunlight highlights its white fur.\\n*   **End (00:02 - 00:03):** The kitten continues to meow. It looks directly at the camera/viewer. The background remains consistent with the plant and the wall.\\n\\n3.  **Synthesize the description:**\\n*   Start with the main subject: A white kitten with blue eyes.\\n*   Describe the environment: Sitting on a wooden floor near a window with curtains. Sunlight is present. A plant is in the background.\\n*   Describe the action: The kitten is meowing repeatedly. It looks around and then at the camera.\\n*   Mention the audio: The sound of the kitten meowing.\\n\\n4.  **Refine the language:**\\n*   \\\"A white kitten with blue eyes is sitting on a wooden floor.\\\"\\n*   \\\"It is positioned next to a window with light curtains.\\\"\\n*   \\\"Sunlight is streaming in, creating shadows.\\\"\\n*   \\\"The kitten is meowing, opening its mouth wide.\\\"\\n*   \\\"In the background, there is a potted green plant.\\\"\\n*   \\\"The kitten looks to the side and then towards the camera while meowing.\\\"\\n\\n5.  **Final Polish:** Combine these points into a coherent paragraph or a list of key observations. The prompt asks to \\\"describe the content of the video,\\\" so a narrative description is appropriate.\\n\\n*   *Draft:* The video shows a cute white kitten with blue eyes sitting on a polished wooden floor. It's near a window with white curtains that are letting in bright sunlight. To the right, in the background, there is a large green plant. The kitten is meowing repeatedly, opening its mouth wide. It looks around a bit and then stares directly at the camera. The audio is just the sound of the kitten's meows.\\n\\n*   *Structure:*\\n*   **Scene:** White kitten, wooden floor, window, sunlight, plant.\\n*   **Action:** Meowing, looking around.\\n*   **Audio:** Meowing sounds.\\n\\nThis covers all the essential aspects of the video."
            }
        }
    ],
    "created": 1776850708,
    "model": "mimo-v2.5",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 849,
        "prompt_tokens": 1260,
        "total_tokens": 2109,
        "completion_tokens_details": {
            "reasoning_tokens": 719
        },
        "prompt_tokens_details": {
            "audio_tokens": 19,
            "cached_tokens": 1256,
            "video_tokens": 1144
        }
    }
}
```

## Supported models

Currently, only the `mimo-v2.5`, `mimo-v2-omni` models are supported.

## Video Input Method

Supported video input methods are as follows:

- Video URL Input: A publicly accessible video URL address must be provided. 

- Base64 Encoding Input: Convert the video to a Base64-encoded string before inputting it.

### Video URL Input

Videos can be directly passed in via a publicly accessible video URL address, which is suitable for scenarios where the video is already stored in a publicly accessible environment. The size of a single video file cannot exceed 300 MB. 

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/video/video_example.mp4"
                    },
                    "fps": 2,
                    "media_resolution": "default"
                },
                {
                    "type": "text",
                    "text": "please describe the content of the video"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://example-files.cnbj1.mi-fds.com/example-files/video/video_example.mp4"
                    },
                    "fps": 2,
                    "media_resolution": "default"
                },
                {
                    "type": "text",
                    "text": "please describe the content of the video"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

### Base64 encoding Input

Convert the video file to a Base64-encoded string and then pass it in, which is suitable for scenarios where the video cannot be accessed via a public network URL. The size of the converted Base64-encoded string cannot exceed 50 MB.

<div className='mdx-highlight'>

Please include the prefix before Base64 encoding:`data:{MIME_TYPE};base64,$BASE64_VIDEO`
- `{MIME_TYPE}`: The MIME type (media type) of the video, used to identify the video format, and needs to be replaced with the MIME value corresponding to the actual video.
- `$BASE64_VIDEO`: Pure Base64-encoded string of the video file (without any prefix).

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "model": "mimo-v2.5",
    "messages": [
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "data:{MIME_TYPE};base64,$BASE64_VIDEO"
                    },
                    "fps": 2,
                    "media_resolution": "default"
                },
                {
                    "type": "text",
                    "text": "please describe the content of the video"
                }
            ]
        }
    ],
    "max_completion_tokens": 1024
}'
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5",
    messages=[
        {
            "role": "system",
            "content": "You are MiMo, an AI assistant developed by Xiaomi. Today is date: Tuesday, December 16, 2025. Your knowledge cutoff date is December 2024."
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "data:{MIME_TYPE};base64,$BASE64_VIDEO"
                    },
                    "fps": 2,
                    "media_resolution": "default"
                },
                {
                    "type": "text",
                    "text": "please describe the content of the video"
                }
            ]
        }
    ],
    max_completion_tokens=1024
)

print(completion.model_dump_json())
```

## Instructions for Use

### Video Restrictions

- Video Formats: MP4, MOV, AVI, WMV.

> Video Formats variants are numerous, and it cannot be guaranteed that all files can be recognized. Please verify through testing that the files can be recognized normally.

- Video Size:

   - When passed in as a URL:  single video file size does not exceed 300 MB. 

   - When passed in as Base64 encoding: The size of the Base64 encoded string of a single video does not exceed 50 MB. 

- Number of videos: When multiple videos are input, the number of videos is limited by the model's context length, and the total number of tokens for all audio and text must be less than the model's context length.

> Note: For calculating video tokens, please refer to [Explanation of Video Token Usage](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/video-understanding?target=explanation-of-video-token-usage). For the model context length, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing). 

### Control the fineness of video understanding

You can control the granularity of video understanding through the two fields `fps` and `media_resolution` respectively.

1. `fps` is the frame number of images extracted from the video per second, used to control the fineness of understanding the time dimension of the video. The default value is 2, with a range of `[0.1, 10]`.

   - The higher the value, the denser the frame extraction, and the more refined the model's perception of frame changes, movements, and temporal details; 

   - The lower the value, the sparser the frame extraction, the faster the processing speed, and the less Token consumption.

1. `media_resolution` refers to the resolution level of video frames, used to control the visual understanding fineness of a single frame. The default value is `default`. 

   - `default`: The default level, balancing recognition effectiveness and processing efficiency;

   - `max`: The highest resolution level, which enhances the recognition ability for small objects and detailed textures.

## Explanation of Video Token Usage

Video tokens are divided into `video_tokens` (visual) and `audio_tokens` (audio). 

- `video_tokens` Calculation please refer to the following code. The estimated results are for reference only, and the actual usage is subject to the API response. 

   ```python
   """
   Estimate the number of tokens consumed by an API call based on video duration and resolution.
   Two parameters control the level of detail:
     - fps: Frames extracted per second. Default 2, range [0.1, 10]. Higher values yield
       finer temporal granularity at the cost of more tokens.
     - media_resolution: Per-frame resolution tier. "default" balances quality and efficiency;
       "max" improves fine-grained detail recognition.
   """
   
   import math
   
   def estimate_video_tokens(
       duration: float,
       width: int,
       height: int,
       fps: float = 2.0,
       media_resolution: str = "default",
       mute: bool = False,
   ) -> int:
       """
       Estimate the token count for a video input.
   
       Args:
           duration:         Video duration in seconds.
           width:            Video width in pixels.
           height:           Video height in pixels.
           fps:              Frame extraction rate. Default 2, range [0.1, 10].
           media_resolution: "default" or "max".
           mute:             If True, audio tokens are excluded.
   
       Returns:
           Estimated total token count.
       """
       # ---- Constants ----
       PATCH, MERGE, T_PATCH = 16, 2, 2
       SPATIAL = PATCH * MERGE                         # 32
       PIX_PER_TOKEN = SPATIAL ** 2                    # 1024
       MAX_TOTAL_TOKENS = 131072
       TOTAL_MAX_PIX = MAX_TOTAL_TOKENS * PIX_PER_TOKEN
       MIN_PIX, MAX_PIX = 8192, 8388608
       MAX_FRAMES = 2048
       DEFAULT_MAX_FRAME_TOKEN = 300
   
       # ---- 1. Number of extracted frames ----
       nframes = math.ceil(duration * fps)
       nframes = min(nframes, MAX_FRAMES)
       nframes = max(math.ceil(nframes / T_PATCH) * T_PATCH, T_PATCH)
   
       # ---- 2. Per-frame pixel budget ----
       max_pix = TOTAL_MAX_PIX * T_PATCH // nframes
       if media_resolution != "max":
           max_pix = min(max_pix, DEFAULT_MAX_FRAME_TOKEN * PIX_PER_TOKEN)
       max_pix = max(MIN_PIX, min(max_pix, MAX_PIX))
   
       # ---- 3. Resolution scaling ----
       h, w = height, width
       if min(h, w) < SPATIAL:
           if h < w:
               w = int(w * SPATIAL / h); h = SPATIAL
           else:
               h = int(h * SPATIAL / w); w = SPATIAL
       h_bar = round(h / SPATIAL) * SPATIAL
       w_bar = round(w / SPATIAL) * SPATIAL
       if h_bar * w_bar > max_pix:
           beta = math.sqrt(h * w / max_pix)
           h_bar = math.floor(h / beta / SPATIAL) * SPATIAL
           w_bar = math.floor(w / beta / SPATIAL) * SPATIAL
       elif h_bar * w_bar < MIN_PIX:
           beta = math.sqrt(MIN_PIX / (h * w))
           h_bar = math.ceil(h * beta / SPATIAL) * SPATIAL
           w_bar = math.ceil(w * beta / SPATIAL) * SPATIAL
   
       # ---- 4. Token calculation ----
       grids = nframes // T_PATCH                       # temporal grid count
       tokens_per_grid = (h_bar // PATCH) * (w_bar // PATCH) // (MERGE ** 2)
       vision = grids * tokens_per_grid
       timestamps = grids * (5 if fps > 2 else 3)       # timestamp text tokens
       special = grids * 2 + 2                           # special markers
   
       # ---- 5. Audio tokens ----
       audio = 0
       if not mute:
           spec_len = int(duration * 24000) // 240 + 1
           t = (spec_len - 1) // 2 + 1
           t = t // 2 + int(t % 2 != 0)
           audio = math.ceil(t / 4) + 2                 # +2 for audio special tokens
   
       return vision + timestamps + special + audio
   
   # ============ Example ============
   if __name__ == "__main__":
       # A 1080p, 60-second video
       tokens = estimate_video_tokens(duration=60, width=1920, height=1080)
       print(f"Default params (fps=2, default): {tokens:,} tokens")
   
       tokens = estimate_video_tokens(duration=60, width=1920, height=1080, fps=5)
       print(f"High frame rate (fps=5, default): {tokens:,} tokens")
   
       tokens = estimate_video_tokens(duration=60, width=1920, height=1080, media_resolution="max")
       print(f"High resolution (fps=2, max):     {tokens:,} tokens")
   
       tokens = estimate_video_tokens(duration=60, width=1920, height=1080, mute=True)
       print(f"Muted           (fps=2, mute):    {tokens:,} tokens")
   ```

- `audio_tokens` Calculation please refer to the following code. The estimated results are for reference only, and the actual usage is subject to the API response. 

   ```bash
   Total tokens ≈ Audio duration (in seconds) * 6.25
   ```

## Price

- Billing: The total cost is calculated based on the number of input, input (cache hits), and output tokens; for pricing, please refer to [Pricing and Rate Limits](https://platform.xiaomimimo.com/#/docs/pricing). 

   - Video Token consumption can be calculated through [Explanation of Video Token Usage](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/video-understanding?target=explanation-of-video-token-usage). The estimated results are for reference only, and the actual usage is subject to the API response. 

- View Bill: You can view your bill and usage on the [Billing](https://platform.xiaomimimo.com/#/console/usage) page in the Console. 

## FAQ

### Does it support local file upload?

`mimo-v2.5` and `mimo-v2-omni` models do not currently support uploading local video files. For supported upload methods, please refer to [Video Input Method](https://platform.xiaomimimo.com/#/docs/usage-guide/multimodal-understanding/video-understanding?target=video-input-method).


--- DOCUMENT: Speech synthesis (MiMo-V2.5-TTS Series) ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/speech-synthesis-v2.5.md

# Speech synthesis (MiMo-V2.5-TTS Series)

Speech Synthesis (Text-to-Speech) supports automatically converting input text into natural and fluent speech output. You can generate natural and vivid speech content by configuring parameters such as speech style and voice.

**Core Capabilities**

- **Out-of-the-box built-in voices:** A variety of high-quality built-in voices are available for quick use without additional configuration.

- **Voice design and cloning:** Supports voice design via text description, or replication of arbitrary voices based on audio samples.

- **Diverse speech styles:** Supports control over speed, emotion, role-play, dialects and other styles, for more vivid and natural speech expression.

## List of Supported Models

Currently, three models of the MiMo-V2.5-TTS series are supported, and the model list is as follows:

<table>
<colgroup>
<col />
<col style="width: 243px" />
<col style="width: 228px" />
<col style="width: 240px" />
<col style="width: 307px" />
</colgroup>
<thead>
<tr>
<th>Model Name</th>
<th>Model ID</th>
<th>Function</th>
<th>Voice</th>
<th>Precautions</th>
</tr>
</thead>
<tbody>
<tr>
<td>MiMo-V2.5-TTS</td>
<td>`mimo-v2.5-tts`</td>
<td>Use built-in high-quality voices for speech synthesis</td>
<td>Use the high-quality voices from the built-in voices list</td>
<td>Supports singing mode, does not support voice design and voice cloning</td>
</tr>
<tr>
<td>MiMo-V2.5-TTS-VoiceDesign</td>
<td>`mimo-v2.5-tts-voicedesign`</td>
<td>Customize voice through text description</td>
<td>Automatically generate voices from text descriptions, without requiring presets or audio samples</td>
<td>Does not support singing mode, built-in voices, or voice cloning</td>
</tr>
<tr>
<td>MiMo-V2.5-TTS-VoiceClone</td>
<td>`mimo-v2.5-tts-voiceclone`</td>
<td>Replicate any voice from audio samples</td>
<td>Precisely replicate voices from audio samples to enable speech synthesis of any voice</td>
<td>Does not support singing mode, built-in voices, or voice design</td>
</tr>
</tbody>
</table>

## Preparation

For preparations such as obtaining API Key, please refer to [ First API Call ](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call). 

## General Precautions

<div className='mdx-highlight'>

**Call Rules**
- The target text for speech synthesis must be filled in the `role` of `assistant` message and cannot be placed in the `user` role message. 
- `user` role messages are optional parameters, and instructions can be passed in to adjust the tone and style of speech synthesis, or they can be conversation history (message content will not appear in synthesized speech). When using the `mimo-v2.5-tts-voicedesign` model, they are required parameters. 
- When using streaming calls, please specify the format of the output audio as `pcm16`, so that it can be spliced into a complete audio. For splicing examples, please refer to the Python calling methods in each chapter. 

</div>

## Style Control 

The instruction-following ability of the model is sufficient to cover the following complex controls (a single natural language instruction is sufficient to take effect): 

- **Multi-style Switching**: A single character completes the style transition from *announcement → whisper → roar* within the same voice segment, with a natural and unobtrusive transition.

- **Multi-emotion Mixing**: Supports complex emotions such as "repressed anger", "smile with a sob", "gentle but tired", "gentleness in mania", etc., rather than only allowing the selection of a single emotion.

- **Multi-granularity control**: From *paragraph level* (overall tone) → *sentence level* (rhythm) → *word level* (stress) → *character granularity* (choking, dragging, or breathy sound of a specific character), all can be specified in the instruction.

We currently offer two control methods: **natural language control** and **tag control** . The placement of the content for both methods in ` messages ` is different: 

- **Natural Language Control** → Placed in `role: user`'s `content`

- **Audio** **Tag Control**  → Placed in ` role: assistant ` 's ` content `

### Natural Language Control

Through natural language description, enable the model to understand and generate speech in the corresponding style. **The content is placed in the** `messages` **field of** `role: user` **in the** `content` **field.**   You can directly describe the desired speech style in a single sentence. 

**Example:**

> Report good news to the leader in a brisk and upbeat tone, speaking at a slightly faster pace, with the uncontrollable excitement and a touch of pride after learning the results, and a bright and energetic voice. 

> Looking at the results of the just-solved difficult problem, couldn't help exclaiming in a self-satisfied and overjoyed manner, with a high-pitched and bright voice, a relatively fast speaking speed, and a tone full of confidence and disbelief. 

> With a bright and lively teenage voice, carrying the pride and playfulness after a successful prank, speaking at a relatively fast pace with light enunciation, and the tone slightly rising when emphasizing the bet. 

On this basis, we also support a more complex and refined **director mode** — just like writing a script for actors, comprehensively depicting characters and voices from the three dimensions of **character, scene, and guidance**, based on which the model can generate more layered and performative voices.

- **[Character]** Clearly describe the character's identity, personality traits, physical appearance and speaking habits.

- **[Scene]** Describe what is happening at this moment, who you are talking to, and what emotional state you are in. The more specific the better — time, location, event, and the other person's reaction can all be included.

- **[Guidance]** Similar to a director giving acting instructions to an actor: speaking speed, breath control, pauses, accents, resonance position, timbre texture, and emotional fluctuations. It can be written in detail, and the model will act according to these "stage directions". 

**Example:**

```python
Role: The current head of the century-old noble Cen family. Since birth, she was adopted and raised by the gatekeeper of the ancestral temple, molded into a flawless, emotionless family totem. She has long lived in seclusion and has a strong sense of class alienation towards others.

Scene: In the shadows of the ancestral hall, she watches the man who has broken through the security cordon at all costs to find her and attempts to elope with her. She will use the coldest and most rigid class barriers to strangle both the other person and the feelings that have just sprouted but are enough to start a prairie fire within herself.

Guidance:
A cold, languid yet extremely imposing deep-voiced mature woman. Her vocal tract is very relaxed, without any sign of tension, yet exuding a bone-chilling sense of oppression.

- Speed and Pauses: Extremely slow, with each word rolling on the tip of her tongue before being uttered, carrying the casual arrogance of a superior. There are extremely long, unsettling pauses between sentences.
- Breathiness and Full Voice: Most of the time, her voice has no obvious pitch fluctuations, with a heavy and hard full voice, like a calm yet cold undercurrent. However, a very slight breathy sound must be added at certain final sounds (such as "sincerity") to reveal a hint of weariness and longing that even she herself is unaware of.
- Articulation Texture: The mixed use of literary and colloquial words bears the traces of the old era, with labiodental sounds pronounced extremely lightly but extremely clearly (such as "collision" and "cheap"), making her speech both elegant and sharp, hitting home with every word.
```

Director Mode is suitable for scenarios with high requirements for voice performance, such as character voiceovers, film-level content generation, etc.

### Audio Tag Control

By embedding style tags and audio tags in the text, fine-grained control over speech can be directly achieved. The overall style tag comes at the beginning, and fine-grained control tags can be inserted in the middle. **All tag control content is placed in the** ` messages ` **of the** ` role: assistant ` ` content `  **field.**  

Add a **start** `(style)` tag to the target text to specify the pronunciation style of the voice. Multiple styles can be set simultaneously by placing multiple style names within the same pair of parentheses, with no restrictions on the delimiter.

**Supported bracket formats:** Half-width `()`, full-width `（）`, or `[]` can be used.

**Format Example:** `(Style 1 Style 2)Content to be Synthesized`

The following are some recommended styles, and custom styles not listed are also supported. 

<div className='mdx-highlight'>

**Precautions** 
- To experience a better singing style, you must add the `(唱歌)` tag at the very beginning of the target text, with the format: `(唱歌)lyrics`. `Lyrics` are recommended to be in Chinese for better synthesis results. The identifiers within the tags support the following values, with equivalent effects: 

- `唱歌`, `sing`, `singing`

</div>

<table>
<colgroup>
<col />
<col style="width: 697px" />
</colgroup>
<thead>
<tr>
<th>**Style Type**</th>
<th>**Style Example**</th>
</tr>
</thead>
<tbody>
<tr>
<td>Basic Emotions</td>
<td>*Happy / Sad / Angry / Fearful / Amazed / Excited / Wronged / Calm / Indifferent*</td>
</tr>
<tr>
<td>Complex Emotions</td>
<td>*Melancholy / Relieved / Helpless / Guilty / Relieved / Jealous / Tired / Apprehensive / Emotional*</td>
</tr>
<tr>
<td>Overall tone</td>
<td>*Gentle / Cold / Lively / Serious / Lazy / Playful / Deep / Capable / Sharp*</td>
</tr>
<tr>
<td>Timbre Positioning</td>
<td>*Magnetic / Mellow / Clear / Ethereal / Innocent / Old / Sweet / Hoarse / Elegant*</td>
</tr>
<tr>
<td>Character Tone</td>
<td>*Clamp voice / Big Sister voice / Shota voice / Uncle voice / Taiwanese accent*</td>
</tr>
<tr>
<td>Dialect</td>
<td>*Northeast dialect / Sichuan dialect / Henan dialect / Cantonese*</td>
</tr>
<tr>
<td>Role-playing</td>
<td>*Sun Wukong / Lin Daiyu*</td>
</tr>
<tr>
<td>Singing</td>
<td>*singing*</td>
</tr>
</tbody>
</table>

**Example:**
- `(Sighing)After all these years, when I walked down that street again, a part of my heart suddenly felt empty.`
- `(Lazy)Let me sleep for five more minutes... just five minutes, really, for the last time.`
- `(Magnetic)The night is already deep, but the city is still breathing. I'm the one accompanying you tonight. Welcome to listen to <Midnight Radio>.`
- `(Northeastern dialect)Oh my goodness, it's so cold today! You know that wind, it's whistling like a knife, cutting into your face!`
- `(Cantonese)This is really amazing! Once you've tasted it, you won't forget!`
- `(singing)Forgive me for my unruly and unrestrained love for freedom throughout my life, and I'm also afraid that one day I'll fall, Oh no. Abandoning ideals, anyone can do it, so how could I be afraid that one day it'll only be you and me.`

On this basis, we also support inserting `[audio tag]` at any position in the text. Through the [audio tag], you can perform fine-grained control over the sound, precisely adjusting tone, mood, and expression style—whether it's a whisper, a hearty laugh, or a little complaint with a touch of emotion. You can also flexibly insert breathing sounds, pauses, coughs, etc., all of which can be easily achieved. The speaking speed can also be flexibly adjusted, allowing each sentence to have its proper rhythm.

<table>
<colgroup>
<col />
<col style="width: 697px" />
</colgroup>
<thead>
<tr>
<th>**Style Type**</th>
<th>**Style Example**</th>
</tr>
</thead>
<tbody>
<tr>
<td>Speech Rate and Rhythm</td>
<td>*Inhale / Take a deep breath / Sigh / Let out a long sigh / Pant / Hold one's breath*</td>
</tr>
<tr>
<td>Emotional State</td>
<td>*nervous / scared / excited / tired / wronged / coquettish / guilty / shocked / impatient*</td>
</tr>
<tr>
<td>Speech Features</td>
<td>*Trembling / Voice trembling / Pitch change / Cracked voice / Nasal voice / Breathiness / Hoarseness*</td>
</tr>
<tr>
<td>Laughing and crying tone</td>
<td>*Smile / Chuckle / Laugh out loud / Sneer / Sob / Whimper / Choke / Wail*</td>
</tr>
</tbody>
</table>

**Example:**
- (nervously, takes a deep breath) Hoo... Calm down, calm down. It's just an interview... (speaking faster, muttering) I've rehearsed my self-introduction fifty times, it should be okay. Come on, you can do it... (softly) Oh, is my tie crooked?
- (extremely exhausted, listless) Master... wake me up when we get there... (sighs deeply) I'll take a little nap first. This overtime has made me feel like my soul is about to scatter. 
- If I had... (pauses for a moment) even if I had persisted for just one more second, would the outcome have been different? (forced smile) Oh, there are no "what ifs" anymore. 
- (Rapid breathing due to the cold) Hoo—hoo—This, this snow in the Greater Khingan Mountains... (cough) It can literally freeze one's bones... Don't, don't stop, keep moving, move quickly. 
- (raising voice and shouting) Sister! This fish is fresh! Just caught this morning! Hey! You there, stop rummaging around! If you crush it, you'll have to pay for it! 

## Speech Synthesis Using Built-in Voices

- It comes with multiple high-quality voices and can be used directly without additional configuration. Currently, only the `mimo-v2.5-tts` model is supported

- Supports controlling the style of synthetic speech by passing natural language instructions in the user message

- Supports controlling the style of synthesized speech through audio tags 

### Built-in Voice List

When in use, you can set the preset timbre in `{"audio": {"voice": "mimo_default"}}`.

<table>
<colgroup>
<col />
<col style="width: 127px" />
<col style="width: 113px" />
<col style="width: 598px" />
</colgroup>
<thead>
<tr>
<th>**Voice** **Name**</th>
<th>**Voice ID**</th>
<th>Language</th>
<th>Gender</th>
</tr>
</thead>
<tbody>
<tr>
<td>MiMo-默认</td>
<td>mimo_default</td>
<td colspan="2">It varies depending on the deployed cluster. The default for the China cluster is `冰糖`, and the default for other clusters is `Mia`</td>
</tr>
<tr>
<td>冰糖</td>
<td>冰糖</td>
<td>Chinese</td>
<td>Female</td>
</tr>
<tr>
<td>茉莉</td>
<td>茉莉</td>
<td>Chinese</td>
<td>Female</td>
</tr>
<tr>
<td>苏打</td>
<td>苏打</td>
<td>Chinese</td>
<td>Male</td>
</tr>
<tr>
<td>白桦</td>
<td>白桦</td>
<td>Chinese</td>
<td>Male</td>
</tr>
<tr>
<td>Mia</td>
<td>Mia</td>
<td>English</td>
<td>Female</td>
</tr>
<tr>
<td>Chloe</td>
<td>Chloe</td>
<td>English</td>
<td>Female</td>
</tr>
<tr>
<td>Milo</td>
<td>Milo</td>
<td>English</td>
<td>Male</td>
</tr>
<tr>
<td>Dean</td>
<td>Dean</td>
<td>English</td>
<td>Male</td>
</tr>
</tbody>
</table>

### Code Sample

#### Non-streaming Call

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts",
    "messages": [
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you are bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "Chloe"
    }
}'
```

**Python**

```python
import os
from openai import OpenAI
import base64

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5-tts",
    messages=[
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you're bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    audio={
        "format": "wav",
        "voice": "Chloe"
    }
)

message = completion.choices[0].message
audio_bytes = base64.b64decode(message.audio.data)
with open("audio_file.wav", "wb") as f:
    f.write(audio_bytes)
```

#### Streaming Call

<div className='mdx-highlight'>

- The low-latency streaming output feature of the MiMo-V2.5-TTS series is not yet available. If you have relevant requirements, please follow the upcoming feature updates.
- The streaming call interface is currently downgraded to compatibility mode, and only **returns the results once in streaming format after all inferences are completed.** 

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts",
    "messages": [
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you are bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    "audio": {
        "format": "pcm16",
        "voice": "Chloe"
    },
    "stream": true
}'
```

**Python**

```python
import base64
import os
import numpy as np
import soundfile as sf
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5-tts",
    messages=[
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you're bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    audio={
        "format": "pcm16",
        "voice": "Chloe"
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), f"Expected audio to be a dict, got {type(audio)}"
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")
```

## Speech Synthesis Using Voice Design

There is no need to provide an audio file. Simply add voice description text to the message with the role of `user`, and a customized voice can be generated. Currently, only the `mimo-v2.5-tts-voicedesign` model is supported.

### How to Write a Good Voice Design Prompt

When using the `mimo-v2.5-tts-voicedesign` model, the text in the `user` message is the voice design description. The more specific and vivid the description, the closer the generated voice will be to the expected one.

#### Key Dimension

A good voice description usually covers the following multiple dimensions (not necessarily comprehensive):

<table>
<colgroup>
<col />
<col style="width: 594px" />
</colgroup>
<thead>
<tr>
<th>Dimension</th>
<th>Example</th>
</tr>
</thead>
<tbody>
<tr>
<td>Gender and Age</td>
<td>"young woman in her mid-20s", "middle-aged man in his 50s"</td>
</tr>
<tr>
<td>Voice / Texture</td>
<td>"deep and gravelly", "silky, mellow, and magnetic"</td>
</tr>
<tr>
<td>Mood / Tone</td>
<td>"warm and confident", "gentle but with a hint of weariness"</td>
</tr>
<tr>
<td>Speech speed / Rhythm</td>
<td>"slow and deliberate", "speaking at an extremely fast pace, like a machine gun."</td>
</tr>
</tbody>
</table>

The following dimensions can be optionally added to increase richness:

- **Role / Character**: narrator, podcast host, storyteller, late-night radio DJ

- **Speaking style**: casual and colloquial, seriously, lowering one's voice as if plotting

- **Scene description**: narrating a nature documentary, during a roadshow for investors

- **Era reference**: 1940s film noir, dubbed voices of translated films from the 1980s

#### Writing Suggestions

**Concise descriptive** -- quickly outline the sound profile using keywords or a single sentence

```bash
Heavy Russian accent, gruff middle-aged male, blunt and matter-of-fact.
```

**Professional Descriptive** -- Three-dimensional portrayal of sound through scenarios, character design, or multi-dimensional details

```bash
Young female, extreme close-up with a binaural, ear-to-ear ASMR feel. Audible breathing, subtle swallowing, and soft natural lip sounds. She speaks very slowly, creating a deeply relaxing and immersive experience.
```

```json
An elderly gentleman, speaking Mandarin with a northern accent, his speech slow and steady, his voice slightly hoarse and weathered, as if an old and seasoned grandfather were telling a story, full of the wisdom of years.
```

#### Precautions

- **Length**: 1-4 sentences are sufficient; there's no need to write a long text. Clearly describing the core features is more important than piling up dimensions

- **Avoid conflicts**: Do not simultaneously request contradictory characteristics (e.g., "innocent childish voice + CEO aura")

- **Avoid using audio quality effect terms**: Do not write descriptions related to post-processing such as reverb, echo, EQ, compression, etc

- **Avoid vague words**: Do not use descriptions lacking specific references such as "ordinary," "normal," or "foreign"

- **Both Chinese and English are supported**: the model supports both Chinese and English voice timbre descriptions, so choose the language in which you can express most precisely

- **Synthetic text should match the voice tone**: The synthetic text in the `assistant` message should match the voice tone description to achieve the best results. For example, pair a goodnight monologue with a "gentle and soothing female voice" instead of a passionate sports commentary. It is recommended to use LLM to automatically generate matching synthetic text based on your voice tone description; on the Studio page, you can directly click the "Generate Text" button after entering the voice tone description.

### Code Sample

<div className='mdx-highlight'>

`mimo-v2.5-tts-voicedesign` supports the optional parameter `optimize_text_preview` to control whether the target broadcast text is intelligently polished. When set to `true`, the `assistant` role message can be omitted.

</div>

#### Non-streaming Call

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voicedesign",
    "messages": [
        {
            "role": "user",
            "content": "Give me a young male tone."
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    "audio": {
        "format": "wav",
        "optimize_text_preview": true
    }
}'
```

**Python**

```python
import os
from openai import OpenAI
import base64

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voicedesign",
    messages=[
        {
            "role": "user",
            "content": "Give me a young male tone."
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "optimize_text_preview": True
    }
)

message = completion.choices[0].message
audio_bytes = base64.b64decode(message.audio.data)
with open("audio_file.wav", "wb") as f:
    f.write(audio_bytes)
```

#### Streaming Call

<div className='mdx-highlight'>

- The low-latency streaming output feature of the MiMo-V2.5-TTS series is not yet available. If you have relevant requirements, please follow the upcoming feature updates.
- The streaming call interface is currently downgraded to compatibility mode, and only **returns the results once in streaming format after all inferences are completed.** 

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voicedesign",
    "messages": [
        {
            "role": "user",
            "content": "Give me a young male tone."
        },
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    "audio": {
        "format": "pcm16",
        "optimize_text_preview": true
    },
    "stream": true
}'
```

**Python**

```python
import base64
import os
import numpy as np
import soundfile as sf
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voicedesign",
    messages=[
        {
            "role": "user",
            "content": "Give me a young male tone."
        },
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    audio={
        "format": "pcm16",
        "optimize_text_preview": True
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), f"Expected audio to be a dict, got {type(audio)}"
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")
```

## Speech Synthesis Using Voice Cloning

- By passing in audio samples, you can accurately replicate the target timbre and generate speech. Currently, only the `mimo-v2.5-tts-voiceclone` model is supported 

- Supports controlling the style of synthetic speech by passing natural language instructions in the user message

- Supports controlling the style of synthesized speech through audio tags 

### Code Sample

Convert the audio file sample to a Base64-encoded string and then pass it in. The size of the converted Base64-encoded string cannot exceed 10 MB, and currently only `mp3` and `wav` format audio sample files are supported.

<div className='mdx-highlight'>

**Precautions** 
- Please include the prefix before Base64 encoding:`data:{MIME_TYPE};base64,$BASE64_AUDIO`

- `{MIME_TYPE}`: The MIME type (media type) of the audio, used to identify the audio format, needs to be replaced with the MIME value corresponding to the actual audio. The values here can be: ` audio/mpeg ` (or ` audio/mp3 `), ` audio/wav `. 

- `$BASE64_AUDIO`: A pure Base64-encoded string of the audio file (without any prefix).

</div>

#### Non-streaming Call

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voiceclone",
    "messages": [
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "data:{MIME_TYPE};base64,$BASE64_AUDIO"
    }
}'
```

**Python**

```python
import base64
import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1",
)

with open("voice.mp3", "rb") as f:
    voice_bytes = f.read()
voice_base64 = base64.b64encode(voice_bytes).decode("utf-8")

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voiceclone",
    messages=[
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant", 
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "voice": f"data:audio/mpeg;base64,{voice_base64}"
    }
)

message = completion.choices[0].message
audio_bytes = base64.b64decode(message.audio.data)
with open("audio_file.wav", "wb") as f:
    f.write(audio_bytes)
```

#### Streaming Call

<div className='mdx-highlight'>

- The low-latency streaming output feature of the MiMo-V2.5-TTS series is not yet available. If you have relevant requirements, please follow the upcoming feature updates.
- The streaming call interface is currently downgraded to compatibility mode, and only **returns** **the results oncein streaming formatafter all inferences are completed.** 

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voiceclone",
    "messages": [
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    "audio": {
        "format": "pcm16",
        "voice": "data:{MIME_TYPE};base64,$BASE64_AUDIO"
    },
    "stream": true
}'
```

**Python**

```python
import base64
import os

import numpy as np
import soundfile as sf
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1",
)

with open("voice.mp3", "rb") as f:
    voice_bytes = f.read()
voice_base64 = base64.b64encode(voice_bytes).decode("utf-8")

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voiceclone",
    messages=[
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant", 
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "voice": f"data:audio/mpeg;base64,{voice_base64}",
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), (
            f"Expected audio to be a dict, got {type(audio)}"
        )
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")
```

## Price

- Billing: Free for a limited time.

- View Bill: You can view your usage on the [Billing](https://platform.xiaomimimo.com/#/console/usage) page in the Console.


--- DOCUMENT: Speech synthesis (MiMo-V2-TTS) ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/speech-synthesis.md

# Speech synthesis (MiMo-V2-TTS)

Speech Synthesis (Text-to-Speech) automatically converts input text into natural and fluent speech output. You can configure parameters such as speech style to generate expressive and vivid speech content.

**Core Capabilities**

- **Provides built-in voices:** Built-in default tones meet the needs for quick use.

- **Diverse speech styles:** Supports specifying speech styles for more vivid and natural voices.

## Supported Models

Only the `mimo-v2-tts` model is currently supported.

## Preparation  

For preparations such as obtaining the API Key, please refer to [First API Call](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call).

## Available Built-in Voices

You may set the built-in voice in `{"audio": {"voice": "mimo_default"}}`.

| **Voice Name** | **Voice Parameter** |
| --- | --- |
| MiMo-Default | mimo_default |
| MiMo-Chinese Female Voice | default_zh |
| MiMo-English Female Voice | default_en |

> Currently, voice cloning is not supported.

## Style Control

### Overall Voice Style Control

Place `<style>style</style>` at the beginning of the target text for conversion, where `style` is the audio style to be generated. If multiple styles need to be set, place multiple style names within the same `<style>` tag, with no restrictions on the separator.

**Format example:** `<style>Style 1 Style 2</style>Content to be synthesized`.

The following are some recommended styles, and styles not on the list are also supported.

| **Style Type** | **Style Example** |
| --- | --- |
| Speech rate control | *Speed up / Slow down* |
| Emotional changes | *Happy / Sad / Angry* |
| Role-playing | *Sun Wukong / Lin Daiyu* |
| Style change | *Whisper / Clamped voice / Taiwanese accent* |
| Dialect | *Northeastern dialect / Sichuan dialect / Henan dialect / Cantonese* |

**Sample:**
- `<style>Happy</style>Tomorrow is Friday, so happy!`
- `<style>Whisper</style>Oh my goodness, it's so cold today! You know that wind, it's howling like a knife, cutting into your face!`

### Fine-grained Control of Audio Tags

Through [Audio Tags], you can exercise fine-grained control over sound, precisely adjusting tone, emotion, and expression style—whether it's a whisper, a hearty laugh, or a little rant with a touch of emotion. You can also flexibly insert breaths, pauses, coughs, etc., all of which can be easily achieved. The speaking speed can also be flexibly adjusted, ensuring that every sentence has its proper rhythm.

**Sample:**
- Achoo! Ahem. I—I really [cough] think I am coming down with  a terrible [cough] terrible cold.
- [heavy breathing] Just... give me... a second. I ran... all the way... from the station.
- I just feel... *long sigh*... like I'm constantly treading water, you know?
- It's just so stupid! (sobbing) We spent all that money on the cake and the dog just... (sudden laugh) he just ate the whole thing in one bite!

## Code Sample

<div className='mdx-highlight'>

**Notes**
- The target text for speech synthesis must be placed in a message with `role`: `assistant`, not in a message with `role`: `user`.
- The message of the `user` role is an optional parameter, but it is recommended that users carry it. You can adjust the tone and style of speech synthesis in some scenarios.
- To specify the speech style, place `<style>style</style>` at the beginning of the target text.
- To achieve a better singing style, you must add only the tag `<style>唱歌</style>` at the very beginning of the target text, in the format: `<style>唱歌</style>lyrics`. The values supported within the tag are as follows, and their effects are equivalent:

- `唱歌`, `sing`, `singing`

</div>

### Non-streaming Call

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2-tts",
    "messages": [
        {
            "role": "user",
            "content": "Hello, MiMo, have you had lunch?"
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "mimo_default"
    }
}'
```

**Python**

```python
import os
from openai import OpenAI
import base64

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2-tts",
    messages=[
        {
            "role": "user",
            "content": "Hello, MiMo, have you had lunch?"
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "voice": "mimo_default"
    }
)

message = completion.choices[0].message
audio_bytes = base64.b64decode(message.audio.data)
with open("audio_file.wav", "wb") as f:
    f.write(audio_bytes)
```

### Streaming Call

<div className='mdx-highlight'>

**Notes**
- When using streaming calls, please specify the format of the output audio as `pcm16` to facilitate splicing into a complete audio. For a splicing example, please refer to the Python calling method.

</div>

**Curl**

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2-tts",
    "messages": [
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    "audio": {
        "format": "pcm16",
        "voice": "default_en"
    },
    "stream": true
}'
```

**Python**

```python
import base64
import os
import numpy as np
import soundfile as sf
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

completion = client.chat.completions.create(
    model="mimo-v2-tts",
    messages=[
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    audio={
        "format": "pcm16",
        "voice": "default_en"
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), f"Expected audio to be a dict, got {type(audio)}"
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")
```

## Price

- Billing: Free for a limited time.

- View Bill: You can view your usage on the [Billing](https://platform.xiaomimimo.com/#/console/usage) page in the Console.


--- DOCUMENT: [Important Notice]Passing Back reasoning_content in Multi-Turn Conversations for Agent Products ---
URL: https://platform.xiaomimimo.com/static/docs/usage-guide/passing-back-reasoning_content.md

# [Important Notice]Passing Back reasoning_content in Multi-Turn Conversations for Agent Products

To ensure the reasoning quality of our models, we are issuing the following guidance on how `reasoning_content` must be passed back in multi-turn conversation scenarios for Agent-style products.

**1. Scope and Requirement**

When the MiMo thinking mode is enabled in multi-round conversations within Agent-based products, and there are tool calls in the conversation history, the `reasoning_content` field must be fully returned in any subsequent user interaction rounds where the returned assistant message contains tool calls. Otherwise, the API will return a 400 error.

This requirement exists because missing historical `reasoning_content` leads to an incomplete model context, which may result in decreased instruction-following ability, increased hallucinations, and an overall degraded user experience.

**2. Affected Agent Products**

The affected agent products are shown in the following table. We're actively working with the maintainers to push compatibility updates. 

<table>
<colgroup>
<col />
<col style="width: 720px" />
</colgroup>
<thead>
<tr>
<th>Protocol</th>
<th>**Affected Agent Products**</th>
</tr>
</thead>
<tbody>
<tr>
<td>OpenAI Compatibility Protocol</td>
<td>TRAE, Cursor, Roo Code, Codex, GitHub Copilot CLI, Zed, AutoGen, Goose</td>
</tr>
<tr>
<td>Anthropic Compatibility Protocol</td>
<td>TRAE, GitHub Copilot CLI, AutoGen, Goose, OpenClaw, OpenCode, Kilo Code</td>
</tr>
</tbody>
</table>

**3. Affected Models**

MiMo-V2.5-Pro, MiMo-V2.5, MiMo-V2-Pro, MiMo-V2-Omni, MiMo-V2-Flash

**4. Sample Code for Correct Usage**

**Code Sample**

```python
import os
import json
from openai import OpenAI

# Initialize client
client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1"
)

# Define tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather for a given city",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City name, e.g. Beijing"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["location"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "get_time",
            "description": "Get the current time in a given timezone",
            "parameters": {
                "type": "object",
                "properties": {
                    "timezone": {"type": "string", "description": "Timezone, e.g. Asia/Shanghai"}
                },
                "required": ["timezone"]
            }
        }
    }
]

# Tool execution functions (replace with real API calls in production)
def get_current_weather(location: str, unit: str = "celsius") -> str:
    weather_data = {"Beijing": "Sunny 25°C", "Shanghai": "Cloudy 22°C", "Shenzhen": "Rainy 28°C"}
    return weather_data.get(location, f"Weather unknown for {location}")

def get_time(timezone: str) -> str:
    from datetime import datetime
    return datetime.now().strftime(f"%Y-%m-%d %H:%M:%S ({timezone})")

TOOL_MAP = {
    "get_current_weather": lambda **kw: get_current_weather(**kw),
    "get_time": lambda **kw: get_time(**kw)
}

def run_turn(messages, turn_num):
    """Execute a single user turn: call model, run tools in a loop until final answer."""
    request_num = 0
    while True:
        request_num += 1
        print(f"\nRequest {turn_num}-{request_num}:")

        response = client.chat.completions.create(
            model="mimo-v2.5-pro",
            messages=messages,
            tools=tools,
            extra_body={"thinking": {"type": "enabled"}}
        )

        assistant_message = response.choices[0].message
        messages.append(assistant_message)

        # Print full model response
        print(f"reasoning_content: {assistant_message.reasoning_content}")
        print(f"content: \"{assistant_message.content}\"")
        print(f"tool_calls: {assistant_message.tool_calls}")

        # If no tool calls, we have the final answer
        if not assistant_message.tool_calls:
            break

        # Execute each tool call and append results
        for tool_call in assistant_message.tool_calls:
            func_name = tool_call.function.name
            func_args = json.loads(tool_call.function.arguments)
            result = TOOL_MAP[func_name](**func_args)

            print(f"-> Tool result [{func_name}]: {result}")
            messages.append({
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": result
            })

# --- Multi-turn conversation ---
messages = []

# Turn 1
print("=== Turn 1 ===")
messages.append({"role": "user", "content": "How is the weather in Beijing today? What time is it now?"})
run_turn(messages, turn_num=1)

# Turn 2: reasoning_content from Turn 1 is already in messages via assistant_message
print("\n=== Turn 2 ===")
messages.append({"role": "user", "content": "How about Shanghai? And is it hotter or colder than Beijing?"})
run_turn(messages, turn_num=2)
```

**Example Output**

**Turn 1:**

The user asks about Beijing's weather and current time. After receiving the message, the model thinks and decides to call both `get_current_weather` and `get_time` tools simultaneously (Request 1-1). The client executes the tools, appends the results as `role: "tool"` messages to `messages`, and calls the model again. The model then generates the final answer based on tool results (Request 1-2).

```bash
=== Turn 1 ===

Request 1-1:
reasoning_content: The user wants to know two things:
1. The current weather in Beijing
2. The current time in Beijing

I can call both functions at the same time since they are independent of each other.
content: ""
tool_calls: [ChatCompletionMessageFunctionToolCall(id='call_dd34ce1810be4afbaaa11c9a', function=Function(arguments='{"location": "Beijing"}', name='get_current_weather'), type='function'), ChatCompletionMessageFunctionToolCall(id='call_cf4c667abd094ce090b40f00', function=Function(arguments='{"timezone": "Asia/Shanghai"}', name='get_time'), type='function')]
-> Tool result [get_current_weather]: Sunny 25°C
-> Tool result [get_time]: 2026-05-12 16:37:26 (Asia/Shanghai)

Request 1-2:
reasoning_content: I got the results for both calls. Let me present this information in a friendly way.
content: "Here's the information for Beijing:

☀️ **Weather:** Sunny, 25°C — a lovely day!

🕒 **Current Time:** 2026年5月12日 16:37 (北京时间)

Looks like a beautiful afternoon in Beijing! Perfect weather for being outdoors. Is there anything else you'd like to know? 😊"
tool_calls: None
```

**Turn 2:**

The user follows up asking about Shanghai's weather and comparing it with Beijing. Since Turn 1's `assistant` message (containing `reasoning_content`, `content`, and `tool_calls`) has been accumulated into the conversation history via `messages.append()`, the model can directly access Beijing's 25°C information from context. It only needs to call `get_current_weather` for Shanghai (Request 2-1), then generates a comparison based on both cities' weather data (Request 2-2).

```bash
=== Turn 2 ===

Request 2-1:
reasoning_content: The user wants to know the weather in Shanghai and compare it with Beijing. I already know Beijing is 25°C, so I just need to get Shanghai's weather.
content: ""
tool_calls: [ChatCompletionMessageFunctionToolCall(id='call_f4fc7fdbfbd14cb497026d21', function=Function(arguments='{"location": "Shanghai"}', name='get_current_weather'), type='function')]
-> Tool result [get_current_weather]: Cloudy 22°C

Request 2-2:
reasoning_content: Shanghai is 22°C and cloudy, while Beijing is 25°C and sunny. So Shanghai is 3°C cooler than Beijing.
content: "Here's the weather for Shanghai:

☁️ **Weather:** Cloudy, 22°C

And comparing the two cities:

| City | Temperature | Conditions |
|------|------------|------------|
| Beijing | 25°C | ☀️ Sunny |
| Shanghai | 22°C | ☁️ Cloudy |

**Beijing is 3°C warmer** than Shanghai right now! Beijing also has clearer skies, while Shanghai is a bit cloudier. Both are pleasant temperatures though — great weather in both cities! 😊

Is there anything else you'd like to check?"
tool_calls: None
```


--- DOCUMENT: Refer & earn ---
URL: https://platform.xiaomimimo.com/static/docs/promotions/refer.md

# Refer & earn

## 1. Eligibility

- **Inviter:** Any registered Xiaomi MiMo Open Platform user

- **Invitee:** Users who signed up to Xiaomi MiMo Open Platform **within 3 days** (accounts older than 3 days, or accounts that have already acted as an inviter or invitee, are not eligible)

## 2. Activity rules

You and your friend each get **$2 in bonus credits**.

1. Copy your **6-character invite code** ("Copy invite code" in the referral popup)

1. Your friend signs up and enters your code via "Enter invite code" in the console sidebar

1. Both sides get credits **instantly**

> Each invitee can redeem **only 1** invite code; once redeemed, it cannot be changed. Each inviter can refer up to **20** friends in total.

## 3. Using your rewards

Bonus credits can offset Xiaomi MiMo model API call charges.

- **Valid for 40 days**: counted from the credited date; unused balance after 40 days expires automatically

- **API calls only**: Token Plan packages cannot be paid with bonus credits

- **Non-cashable, non-transferable, no change given**

> **About reward quota**: Daily referral reward issuance is limited and first-come-first-served; when the daily quota is exhausted, please try again the next day.

## 4. Violations

To keep things fair, the following will result in rewards being withheld or revoked:

- Inviting your own other accounts

- Mass registration via bots, virtual numbers, or other technical means

- Misleading promotion or fraudulent referrals

- Any other violation of these rules

> **About account identity:** Xiaomi MiMo identifies accounts belonging to the same user using account bindings, login environment, network signals, and other signals.

## 5. Contact us

For support or business inquiries:

- Email **support-mimo@xiaomi.com**

## 6. Adjustments

**This is a long-term feature with no fixed end date.** 

- Xiaomi MiMo may adjust, pause, or sunset this feature based on operational needs

- **After sunset, no new rewards will be granted for newly bound invite codes**

- **Already-issued credits remain unaffected** and can be used within their 40-day validity

## 7. Final interpretation

Within the limits of applicable law, Xiaomi MiMo holds final interpretation rights for these rules.


--- DOCUMENT: FAQ ---
URL: https://platform.xiaomimimo.com/static/docs/faq.md

# FAQ

## Verification Issues

### What’s the difference between personal and business verification?

Domestic users are required to complete real-name authentication before recharging. Real-name verification includes personal and business types. An account can only be verified for one type. After completing the real-name authentication for a personal account, it can be converted into a business account through business authentication. Business accounts cannot be converted back into personal accounts.

## Payment Issues

### How to top up on the Open Platform?

Go to the [Balance](https://platform.xiaomimimo.com/#/console/balance) page. Domestic users can use Xiaomi Pay, Alipay, WeChat Pay; overseas users can use Apple Pay, Google Pay, Credit Card / Debit Card. Top-ups are usually instant—check your balance in [Balance](https://platform.xiaomimimo.com/#/console/balance) and transaction history in [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge).

### How to set balance alerts?

Enable alerts in [Balance](https://platform.xiaomimimo.com/#/console/balance). You’ll get SMS/email notifications when your balance drops below the threshold.

### Is refund supported?

If you have a refund request, you contact us by clicking the "Apply for Refund" button in the upper right corner of [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge), select the "Refund" option, and explain the reason to initiate the refund request. The account balance will be returned to the original source after approval (consumed amount, invoiced amount, and platform gifted amount cannot be refunded).

After your refund request is accepted, you will no longer be able to use the model service or recharge. Billing may be delayed, and the refund amount will be based on the actual amount received. The refund will generally be returned to the original source within 3-5 business days.

### How to issue an invoice？

- **Domestic users:**

Go to the [Invoice](https://platform.xiaomimimo.com/#/console/invoice) page, select a successful top-up order, and apply for an e-invoice (personal/business title). Enter your email/phone—you’ll receive the invoice via email/SMS.

Notes:
- Invoicable amount = actual payment (no invoices for coupons, gifts, or refunds).
- Personal titles get digital ordinary invoices; business titles get digital ordinary/ special invoices.
- Invoices are issued within 48 hours (delays may occur).
- Invoices can be red-lettered: If the invoice was deducted/recorded, confirm the red-letter notice in the e-tax bureau within 72 hours. The order can be re-invoiced after red-lettering.
- Issuing entity: Beijing Xiaomi Mobile Software Co., Ltd.

- **Overseas users:**

Invoices are auto-generated after top-ups, you can view them in the order page or download historical invoices in [Recharge Details](https://platform.xiaomimimo.com/#/console/recharge).

### Can I still call the API if the balance is insufficient?

Before the billing system goes live, a balance of 0 can still normally call the model inference service.

After the billing system goes live, due to some delay, the balance may be ≤ 0. Once the balance is negative, you will no longer be able to continue calling the model inference service. The next recharge order will prioritize deducting the overdue amount.

### Will billing continue after the API Key is deleted?

Deleted API Keys can’t make calls (no new charges), but historical usage is still visible in [Billing](https://platform.xiaomimimo.com/#/console/usage).

## Related to Token Plan

### Packages and Prices

- **What packages are available for the Token Plan?**

Currently, four packages are offered: Lite, Standard, Pro, and Max, along with two subscription cycles: continuous monthly and continuous annual. Each package includes different usage quotas and special privileges.

- **Which models does Token Plan support?**

Supports a total of 8 models from the MiMo-V2 series and MiMo-V2.5 series, and can be used with all-tier packages.

> MiMo-V2-Pro / V2.5-Pro：Flagship reasoning model
>
> MiMo-V2-Omni / V2.5：Omnipotent MultiModal Machine Learning Model
>
> MiMo-V2-TTS /V2.5-TTS/ V2.5-TTS-VoiceClone / V2.5-TTS-VoiceDesign：Speech synthesis model (free for a limited time)

- **How much is the set meal? Are there any discounts?**

The specific prices of the four packages shall be subject to the display on the landing page. The platform is currently offering the following time-limited promotional activities:
- Package Usage Refresh and Reset: To celebrate the official launch of MiMo-V2.5, users who purchased the Token Plan before 22:00 on April 22, Beijing Time, will have their consumed Credits completely reset, regardless of the current usage of their package, with the validity period remaining unchanged.
- First Purchase Discount: Enjoy 12% off on your first purchase, available only once per account.
- First-time auto-renewal discount: New users who have never subscribed to a package before enjoy a 23% discount (77% of the original price) when they first activate auto-renewal, while existing users who have subscribed to a package before enjoy a 30% discount (70% of the original price) when they first activate auto-renewal. The first-time auto-renewal discount is mutually exclusive with the first-purchase discount, and each account can only enjoy it once.
- Continuous annual subscription: Enjoy an 12% discount compared to continuous monthly subscription; the first purchase/first activation auto-renewal discount does not apply to annual subscriptions.
- Nighttime discount rate: During off-peak hours (0:00-8:00 Beijing Time, i.e., 16:00-24:00 UTC), the consumption coefficient is 0.8x.

- **Does it support continuous subscription?**

Support. It supports two subscription cycles: continuous monthly and continuous annual, with automatic renewal after expiration. You can cancel automatic renewal at any time on the subscription management page. Continuous annual subscription enjoys an 12% discount, offering higher savings compared to continuous monthly subscription.

- **Can I purchase multiple packages or upgrade a package?**

Currently, the platform only supports purchasing 1 package at a time. If you wish to obtain more credits before the package expires, you can convert the used Credit amount into an equivalent amount, and then top up the price difference on this basis to upgrade to a higher package and obtain more Credits. Cross-level package upgrades by topping up the price difference are supported, while package downgrades are not. If you have already upgraded to the highest-tier Max package, further upgrades are not possible. After the package expires, you can purchase a package of any tier again.

> Price difference = New package price - (Remaining amount of the original package / Total amount of the original package) * Original package price

### Validity Period and Expiration

- **How long is the package valid after purchase?** 

It takes effect immediately after purchase, and the validity period of the package is "the day of purchase + 30 complete natural days (as of 23:59:59 UTC)". Effective immediately upon purchase, valid for one calendar month/year starting from the date of purchase.

For example, if you subscribe to a monthly plan on March 28, the plan will expire at 23:59:59 (UTC) on April 28.

- **Will the package automatically renew after it expires?**

It depends on whether you have enabled auto-renewal. If auto-renewal is enabled, before the package expires, the system will initiate automatic deduction via Alipay/WeChat/Xiaomi Pay (domestic) or via waffo (overseas). After successful deduction, it will automatically enter the next subscription cycle without manual operation; if auto-renewal is not enabled, the service will stop after the package expires, and manual re-subscription is required.

- **Can I still use it if the quota is used up but not expired?** 

No. The service will stop when either the "expiration" or "all Credits used up" condition is met. **The system will not continue to consume your bonus or account balance.**   We support the package upgrade feature. Regardless of your package consumption, we support automatically converting your remaining Credits into an equivalent amount, and you can upgrade your package by paying the price difference to obtain more Credits.  **If you need to continue using it, please upgrade your package or switch to the pay-as-you-go API.**  

- **If the package has expired but there are still unused amounts, can it still be carried forward?** 

- **Will I receive a reminder when the package expires or is almost used up?**

Yes. If your plan has auto-renewal enabled, you will receive renewal reminders via SMS, email, and inbox notifications from payment apps (WeChat Pay/Alipay/Xiaomi Pay) before the renewal date; if your plan does not have auto-renewal enabled, you will receive reminders via SMS and email two days before and on the expiration date.

- **Will there be a reminder when the package quota is almost used up?**

Yes. When your current plan usage reaches 50%, 90%, and 100%, you will receive text message and email reminders.

### Usage and Quota

- **Are the quotas of the Pro and Omni models consumed independently?**

No. For example, the quotas of MiMo-V2-Pro and MiMo-V2-Omni are consumed in parallel at a 1:2 ratio, not independently. All models in the TTS series are free for a limited time and do not consume package tokens.

For example, if you have subscribed to the Standard plan, you can call the MiMo-V2.5-Pro/V2.5/TTS models individually or in combination. After using 10M tokens of MiMo-V2.5-Pro, which is equivalent to consuming 20M credits, you can still enjoy 40M tokens of MiMo-V2.5 (equivalent to 40 credits). You can view the quota and usage of your current plan in Subscription Management.

> - V2.5 series
>
> MiMo-V2.5 ：1x（equivalent to the original Token consumption rate）
>
> MiMo-V2.5-Pro： 2x（Equivalent to 2 times the Token consumption rate）
>
> MiMo-V2.5-TTS-VoiceClone、MiMo-V2.5-TTS-VoiceDesign、MiMo-V2.5-TTS：0x（Limited-time free, no Credit consumption）
>
> - V2 series
>
> MiMo-V2-Omni：1x（equivalent to the original Token consumption rate）
>
> MiMo-V2-Pro： 2x（Equivalent to 2 times the Token consumption rate）
>
> MiMo-V2-TTS：0x（Limited-time free, no Credit consumption）

- **What is the 0.8x coefficient for off-peak periods?**

To balance resource pressure and provide benefits to users, when using the model during off-peak hours (0:00-8:00 Beijing Time, i.e., 16:00-24:00 UTC), the credit consumption coefficient is 0.8 times.

For example, in a scenario where you use the MiMo-V2.5-Pro model and consume 10M Credits during peak hours, it will only consume 8M during off-peak hours.

- **When using Token to calculate usage, I'm worried that Credit will be consumed very quickly. What should I do?**

   - We recommend that you check your past token usage in each AI Agent framework before making a purchase, and choose a suitable package based on your experience. 

   - We have designed a Progress Bar system, and you can view the progress and plan ahead in [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage).

   - We support the package upgrade feature. Regardless of your package consumption status, we support automatically converting your remaining Credits into an equivalent amount. You can upgrade your package by paying the price difference to obtain more Credits. 

- **What is the remaining value of a package?**

When you renew or upgrade from a currently unused/expired package, the system calculates the equivalent value based on the Credits consumption of the current package, and this remaining value will be used to offset a portion of the payment amount for the new package.

- **Why are there still compensation Credits on my subscription management page?**

During your renewal for the current package, since the remaining value of the previous package is higher than the value of the current package, the platform compensates you with Credits equivalent to the difference in value.

### API Key and Access

- **How do I obtain an API Key after purchase?** 

After successful purchase, you can view the exclusive API Key on the [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page.  **Note: The API Key is only visible and copyable when created, please save it properly. The API Key format for Token Plan is** `tp-xxxxx`**, which is only used for Token Plan subscription services; the API Key format for pay-as-you-go API calls is** `sk-xxxxx` **, which is used for pay-as-you-go billing. The two are independent and cannot be mixed. The API Key is only available during the validity period of the Token Plan package you subscribed to.** 

- **What if the API Key is lost or leaked?**

can be reset on the [Subscription](https://platform.xiaomimimo.com/#/console/plan-manage) page. 

- **How to obtain the Base URL?**

Refer to the Base URL provided on the subscription management page: There are 2 types of Base URLs provided, one compatible with the OpenAI interface protocol and the other compatible with the Anthropic interface protocol, which can be copied and used as needed.

- **Which programming tools are supported?**

Supports mainstream programming tools and model frameworks, such as Claude Code, OpenClaw, OpenCode, Kilo Code, Cline, Hermes Agent, CodeBuddy Code, etc. For specific access methods, please refer to [Overview of AI Tools](https://platform.xiaomimimo.com/#/docs/integration/tools-overview). 

- **Can** **Token Plan be used simultaneously in multiple programming tools?** 

The same package can be used across all supported tools, but the quota is shared, and usage of all tools will consume the same package quota. 

### Account and Authentication 

- **Does purchasing a package require real-name authentication?**

Yes, you need to complete personal or corporate real-name authentication before you can make a purchase. Both types of authentication allow you to make a purchase.

- **Is the payment process for enterprise accounts the same as that for personal accounts?**

It is completely consistent, and enterprise accounts also support WeChat/Alipay/Xiaomi Pay. 

### Payment-related

- **Can I use my account balance or bonus to offset the purchase of the Token Plan package?** 

The package does not currently support deduction using account balance or bonus funds and needs to be purchased separately. 

- **What payment methods are supported?** 

Domestically in China, it supports WeChat Pay, Alipay, and Xiaomi Pay, while overseas, it uses the Waffo payment gateway for payment (settled in US dollars $).

- **Is there a time limit for payment?**

The valid payment duration shall be subject to the display on the page. After the timeout, the order will automatically close, and you will need to place a new order. 

- **Can I get a refund after purchase?** 

Once the package is paid, it cannot be refunded. 

- **Does purchasing a package count towards cumulative recharge?** 

Subscriptions are not counted, and orders for subscription packages are not included in cumulative recharge.

### Invoice

- **Can I get an invoice?** 

Domestic users can issue invoices based on the transaction orders in the recharge details, and the actual invoiceable amount is the actual payment amount. Overseas users can download invoices on the recharge details page.

### Domestic/Overseas

- **What are the differences between overseas users and domestic users?** 

Main differences:

1) Different payment methods (domestically supports WeChat Pay, Alipay, and Xiaomi Pay; overseas payments are made through the Waffo cashier (settled in US dollars $)).

2) Return different Base URLs + Keys based on the region where the account is located, which are not interoperable.

3) The overseas version currently has no invoicing function.

- **Can the domestic and overseas usage be aggregated for calculation?** 

No, it's not allowed. Different Base URLs and Keys are returned based on the region where the account is located, and usage is calculated separately. 

## Promotions

### How can the gift amount be used? What is its validity period? 

- Gift Rule: To thank you for your support, we have prepared exclusive free quotas for all new and existing users. After you log in and complete real-name authentication, you can go to the [ Account Balance ](https://platform.xiaomimimo.com/#/console/balance) page to check and receive it. It is valid for 40 days only, and will expire after that. 

- Deduction Order: When invoking the model, the gifted amount will be consumed first, followed by the recharged balance. 

### How do I join "Refer & earn"?

Any registered Xiaomi MiMo Open Platform user can invite. New users (signed up **within 3 days**) can be invited. After the invitee redeems your code, both sides instantly get **$2 in trial credits**, deposited as bonus credits for API call charges.

### Where is my invite code?

Click "**Refer & earn**" at the top of the console — your 6-character code appears in the popup. Tap "**Copy invite code**" or "**Download poster**" to share.

### How does my friend redeem the code?

Your friend signs up via your link, then opens "**Enter invite code**" at the **bottom-left** of the console and enters the 6-character code. Each invitee can redeem only 1 invite code.

### How many friends can I invite at most?

Up to **20 in total**. Once you reach the cap, you cannot send new invites.

### Can I use my own other accounts to invite myself?

No. Self-referrals, mass registration via bots or virtual numbers, and fraudulent referrals will result in rewards being withheld or revoked. Xiaomi MiMo identifies same-user accounts via account bindings, login environment, network signals, and other signals.

### What are the trial credit usage limits?

Valid for **40 days** from the credited date (expires after). API calls only — **Token Plan packages not supported**. Non-cashable, non-transferable, no change given. Daily referral reward issuance is limited (first-come-first-served).

## API Call Issues

## API Key and Quota

### How to obtain and use API Key?

After logging into the Xiaomi MiMo API Open Platform, apply for an API Key on the [Console-API Keys](https://platform.xiaomimimo.com/#/console/api-keys) page. When using the model through the API, please include your API Key in the request header: `api-key: $MIMO_API_KEY` or `Authorization: Bearer $MIMO_API_KEY` .

### What's the difference between OpenAI and Anthropic interfaces?

- OpenAI interface `/v1/chat/completions`  follows OpenAI format, including developer/system/user/assistant roles

- Anthropic interface  `/anthropic/v1/messages` follows Claude format, with a separate system parameter

### How to make multi-turn tool calls in thinking mode?

During the multi-turn tool calls process in thinking mode, the model returns a `reasoning_content` field alongside `tool_calls`. To continue the conversation, it is recommended to keep all previous `reasoning_content` in the `messages` array for each subsequent request to achieve the best performance.

The requested example is as follows:

```bash
curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header "Content-Type: application/json" \
--data-raw '{
    "messages": [
        {
            "role": "assistant",
            "content": "Hello! I am MiMo.",
            "reasoning_content": "Okay, the user just asked me to introduce myself. That is a pretty straightforward request, but I should think about why they are asking this."
        },
        {
            "role": "user",
            "content": "What is the weather like in Hebei?"
        }
    ],
    "model": "mimo-v2.5-pro",
    "max_completion_tokens": 1024,
    "temperature": 1.0,
    "stream": false,
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "get_current_weather",
                "description": "Get the current weather in a given location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "The city and state, e.g. San Francisco, CA"
                        },
                        "unit": {
                            "type": "string",
                            "enum": [
                                "celsius",
                                "fahrenheit"
                            ]
                        }
                    },
                    "required": [
                        "location"
                    ]
                }
            }
        }
    ],
    "tool_choice": "auto"
}'
```

### Why aretool_calls sometimes included in the reasoning_content field and sometimes in a separate tool_calls field?

The appearance of `tool_calls` in the reasoning content indicates instability and incomplete output caused by the model having `thinking` enabled when calling `tool`. It is recommended to disable `thinking` when calling `tool` calls and to adjust the settings according to [Model Hyperparameters](https://platform.xiaomimimo.com/#/docs/quick-start/model-hyperparameters) to achieve a more stable and better user experience.

### What's the response speed?

Response speed depends on:

- Request length and complexity

- Server load and geographic location

- Whether streaming response is used

### Are there rate limits?

During the open beta period, RPM is set to 100, and TPM has no limit for the time being, which may be adjusted after the open beta ends. When server load is high, response delays or 429 errors may occur. It is recommended to reasonably plan the request frequency.

### How to handle timeouts?

Please implement reasonable timeout handling on the client side:

- Set reasonable connection and read timeout times

- Use exponential backoff for retries

- For long responses, it's recommended to use streaming mode

### What if the API returns inappropriate content?

The platform has added content review for both user input and model output. If violations occur, the returned content will be automatically intercepted to ensure the content you receive is safe.

### Why doesn’t the model perform a web search after enabling online search?

There may be three reasons:

- **Cache**: There is a 5-minute cache period after enabling / disabling online search. The online search switch will not take effect immediately within 5 minutes.

- **Model determines no need for search**: The model judges that the current query does not involve real-time information and can be answered directly with its own knowledge. To force a search, set `forced_search: true`.

- **Only some models are supported**: Currently only `mimo-v2.5-pro`, `mimo-v2.5`, `mimo-v2-pro`, `mimo-v2-omni`, and `mimo-v2-flash` supports online search.

### Does it support local file upload?

Local file upload is not currently supported.

## Model Capabilities and More Methods

### How to experience the Xiaomi MiMo model?

1.  Regular users can directly experience Xiaomi MiMO Studio online through the official website (https://aistudio.xiaomimimo.com).

1. Developers can obtain resources through Xiaomi's official channels:

   1. Obtain the open-source model weights and code from the GitHub repository (https://github.com/xiaomimimo/MiMo-V2-Flash).

   2.  Apply for API services through the Xiaomi MiMo Open Platform (https://platform.xiaomimimo.com).

1. Additionally, it should be noted that Xiaomi has not yet released an official standalone MiMo app. Downloading any software from unofficial channels poses security risks; please do not download it.

### Does the model support local deployment? How to perform local deployment?

The currently released large models can be found at https://github.com/XiaomiMiMo/MiMo-V2-Flash. Local deployment is primarily supported for sglang. For related issues, please refer to: https://github.com/sgl-project/sglang/pull/15207.

### Why does "Server busy, please try again later" always appears during the conversation?

The current MiMo output is affected by various factors such as server load, question content, model output, etc., and you can rebuild a new conversation or try to regenerate it for a better communication experience.

### Why are there factual errors in MiMo's answer?

MiMo's knowledge base is up to December 2024, and the model API does not currently support online search.

### When will the file upload feature be supported?

We will support it as soon as possible, please be patient and wait.

## Account Issues

### What login methods are supported?

The platform uses Xiaomi account login. If you already have a Xiaomi account, you can log in directly. If you don't have a Xiaomi account, you can register through the console, or register in advance at [id.mi.com](https://id.mi.com/):

- Registration methods for Mainland China users

   - Phone number registration

   - Third-party account authorization registration (supports WeChat, Weibo, QQ, Alipay, and Apple ID registration. For account security, you may need to bind a commonly used phone number)

- Registration methods for overseas users

   - Email registration

   - Third-party account authorization registration (supports Google/Facebook registration. For account security, third-party account bound email may be used as the Xiaomi account security email)

### Unable to log in?

If you encounter login issues, please visit the [Xiaomi Account Help Center](https://account.xiaomi.com/helpcenter?_locale=zh_CN) to view more account issues and solutions.

### Why am I being prompted with "Abnormal account usage detected" and unable to continue using?

It may be because the system detected certain keywords during the check, triggering the automatic protection mechanism. We highly value each user's experience and regularly perform manual reviews to minimize the risk of false positives. If you encounter this issue, please provide your user ID, and we will verify it as soon as possible and assist you in unlocking your account.

### Can model services still be used after the Xiaomi account is deactivated?

After deactivating the Xiaomi account, platform data will be cleared, and the API Key will be synchronized for expiration. Please evaluate and operate cautiously. If you have any issues, please contact us at support-mimo@xiaomi.com.

## Contact Us

For assistance or business inquiries, feel free to reach out to us through the following channels:

- Email: support-mimo@xiaomi.com

- Scan the QR code at the bottom left to join the developer communication group.

- Submit your feedback from [Contact Us](https://platform.xiaomimimo.com/#/contact).


--- DOCUMENT: Model Release ---
URL: https://platform.xiaomimimo.com/static/docs/updates/model.md

# Model Release

## 2026-04-23 MiMo-V2.5-Pro Released

Model Introduction:

- **Trillion parameters, efficient architecture —** 1T total parameters | 42B activations | 1M ultra-long context

- **Ultimate Agent Performance —** In high-intensity agent scenarios, it performs comparably to Claude Opus4.6

Model Pricing:

- Within 256K context: Input $1 / million tokens, Input (cache hit) $0.2 / 1M tokens, Output $3 / million tokens;

- Within 1M context: Input $2 / million tokens, Input (cache hit) $0.4 / 1M tokens, Output $6 / million tokens.

## 2026-04-23 MiMo-V2.5 Released

Model Introduction:

- **Native full-modal perception + 1M context —**  Supports native understanding of images, videos, audio, and text, enabling cross-modal precise perception and long-range reasoning, with comprehensive perception capabilities ranking among the industry's forefront 

- **Powerful full-modal Agent capabilities —**  It has native Agent execution capabilities, enabling it to efficiently complete complex tasks such as browsing, understanding, reasoning, and operation, with its performance in daily tasks comparable to that of **MiMo V2.5 Pro**

- **Combining Performance and Efficiency —** While maintaining leading capabilities, achieving superior token efficiency, and positioned at the Pareto frontier of performance and efficiency

Model Pricing:

- Within 256K context: Input $0.40 / 1M tokens, Input (cache hit) $0.08 / 1M tokens, Output $2.00 / 1M tokens

- Within 1M context: Input $0.80 / 1M tokens, Input (cache hit) $0.16 / 1M tokens, Output $4.00 / 1M tokens

## 2026-04-23 MiMo-V2.5-TTS Series Release

Model Introduction:

- **Premium Voice TTS —**  Built-in with multiple high-quality premium voices, it has strong capabilities in understanding and adhering to style instructions, supports fine-grained control over speech rate, emotion, tone, etc., and meets the expression needs of multiple scenarios 

-  **Timbre Design —** Supports quickly defining and generating new timbres through a single sentence, making timbre creation more intuitive and efficient

-  **Timbre Cloning —** Based on a small number of audio samples, it can reproduce the target timbre with high fidelity, while maintaining the consistency of timbre characteristics and possessing good generalization and stability

Model Pricing: Free for a Limited Time

## 2026-03-18 MiMo-V2-Pro Release

**Model overview:**

- Uses hybrid architecture with a 1:7 ratio of Global Attention to Sliding Window Attention (SWA);

- 1T total parameters, with 42B active parameters;

- Supports an ultra-long context window of 1M tokens.

**Pricing:**

- Up to 256K context: input 1/M tokens, output 3/M tokens;

- Up to 1M context: input 2/M tokens, output 6/M tokens.

**Model details:** https://platform.xiaomimimo.com/#/docs/news/v2-pro-release

## 2026-03-18 MiMo-V2-Omni Release

**Model overview:**

- Supports up to 256K context length;

- Supports text, vision, and speech modalities.

**Pricing:** input 0.4/M tokens; output 2/M tokens.

**Model details:** https://platform.xiaomimimo.com/#/docs/news/v2-omni-release

## 2026-03-18 MiMo-V2-TTS Release

**Model overview:**

- Pretrained on over 100 million hours of data, using a self-developed multi-codebook speech modeling architecture;

- Offers unique capabilities such as style control, singing, and voice cloning.

**Pricing:** free for a limited time.

**Model details:** https://platform.xiaomimimo.com/#/docs/news/v2-tts-release

## 2026-02-04 MiMo-V2-Flash Update

1. **Upgraded Coding Capabilities in Thinking Mode:**
Specifically optimized for programming scenarios, the Thinking Mode now achieves a score of **78.6** on SWE-Bench Verified. Both the resolution rate and the quality of code generation have been significantly improved.

1. **Substantial Boost in Tool Calling Accuracy:**
Stability issues regarding tool usage have been resolved. Tool calling accuracy in Thinking Mode has surged from 64% to **97.0%**, greatly enhancing execution reliability in Agent scenarios.

1. **Enhanced Instruction Following & Reduced Hallucinations:**

- **Instruction Following:** Improved adherence to specific instructions, achieving an **AA-IFBench score of 72**.

- **Factuality:** Enhanced rigor in factual responses, with the **Non-Hallucination Rate updated to 52%**.

1. **Optimized Handling of Complex Tasks:**
Performance on Arena-Hard (Hard Prompts) in Thinking Mode has been strengthened, with the score rising to **60.6**. The model now demonstrates superior performance when handling high-difficulty logic problems.

1. **More Efficient Chain-of-Thought (CoT):**
By optimizing CoT generation strategies, the consumption of redundant tokens has been significantly reduced. In benchmarks such as AIME25 and HMMT, the average generation length has decreased by **13% to 30%**. This effectively lowers latency and token costs while maintaining model performance.

|  | **MiMo-V2-Flash-0204** | **MiMo-V2-Flash-0112** | **MiMo-V2-Flash** |
| --- | --- | --- | --- |
| **SWE-Bench Verified** <br />**Non-Thinking** | **73.7** | 73.3 | 73.4 |
| **SWE-Bench Verified** <br />**Thinking** | **78.6** | 74.2 | - |
| **Arena-Hard(Hard Prompt)** <br />**Non-Thinking** | **49.3** | 52.7 | 46.0 |
| **Arena-Hard(Creative Writing)** <br />**Non-Thinking** | **85.0** | 86.0 | 78.3 |
| **Aren-Hard(Hard Prompt)**<br />**Thinking** | **60.6** | 58.3 | 54.1 |
| **Arena-Hard(Creative Writing)**<br />**Thinking** | **85.8** | 90.4 | 86.2 |
| **AA-IFBench** | **72** | - | 64 |
| **AA-Omniscience Accuracy** | **19** | - | 27 |
| **AA-Omniscience Non-Hallucination Rate** | **52%** | - | 9% |
| **Tool call success rate**<br />**Thinking** | **97.0%** | 64% | 44% |

| **Benchmark** | **MiMo-V2-Flash (Acc)** | **MiMo-V2-Flash (Avg Tokens)** | **MiMo-V2-Flash-0204 (Acc)** | **MiMo-V2-Flash-0204 (Avg Tokens)** | **Length Reduction Ratio (%)** |
| --- | --- | --- | --- | --- | --- |
| **AIME25** | 94.8 | 26984 | 91.1 | 18879 | **30.04%** |
| **HMMT_Feb_25** | 94.2 | 29294 | 92.9 | 21470 | **26.71%** |
| **LiveCodeBench-AA** | 83.2 | 21488 | 84.9 | 18335 | **14.67%** |
| **GPQA-Diamond** | 83.7 | 15862 | 83.8 | 13659 | **13.89%** |

> Note: The model API call method and model name remain unchanged

## 2026-01-12 MiMo-V2-Flash Update

1. **Enhanced general capabilities:** Improved the model’s performance on a wide range of general-purpose tasks.

1. **Upgraded coding performance in Thinking mode:** Strengthened code generation quality in Thinking mode, especially for programming scenarios.

1. **Deep integration with Claude Code:** Fully supports using Thinking mode in Claude Code.

   - **Best practice:** Set Thinking as the default mode to achieve more stable, higher-quality code generation.

1. **Optimized Experience for Other Code Agents:**  Synchronized improvements to the interaction experience and generation quality across code assistant tools (Code Scaffolds) such as Kilo, Cline, and Roo.

1. **Improved Stability & Instruction Following:** Enhanced output stability and significantly improved adherence to specific output formats.

|  | **MiMo-V2-Flash-0112** | **MiMo-V2-Flash** |
| --- | --- | --- |
| **SWE-Bench Verified** <br />**Non-Thinking** | **73.3** | 73.4 |
| **SWE-Bench Verified Thinking** | **74.2** | - |
| **Arena-Hard(Hard Prompt)** <br />**Non-Thinking** | **52.7** | 46.0 |
| **Arena-Hard(Creative Writing)** <br />**Non-Thinking** | **86.0** | 78.3 |
| **Arena-Hard(Hard Prompt)**<br />**Thinking** | **58.3** | 54.1 |
| **Arena-Hard(Creative Writing)**<br />**Thinking** | **90.4** | 86.2 |

> Note: The model API call method and model name remain unchanged

## 2025-12-16 MiMo-V2-Flash Release

**Model overview:**

- Uses hybrid architecture with a 1:5 ratio of Global Attention to Sliding Window Attention (SWA), a window size of 128, native 32K context, and extended training up to 256K;

- Introduces 3 MTP layers, delivering 2.5 to 3.7× faster inference.

**Pricing:** input 0.1/M tokens, output 0.3/M tokens.

**Model details:** [MiMo-V2-Flash: High-Efficiency Inference, Code & Agent Foundation Model](https://platform.xiaomimimo.com/#/docs/news/news20251216)

**Usage guide:** [First API call](https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call)


--- DOCUMENT: Feature Updates ---
URL: https://platform.xiaomimimo.com/static/docs/updates/feature.md

# Feature Updates

## 2026-4-29 Refer & earn New Release

Invite builders to try Xiaomi's flagship MiMo V2.5 — sign up to instantly get $2 in trial credits, redeemable for API calls (Token Plan not supported).

## 2026-4-23 Token Plan Auto-Renewal Now Available

- Monthly and annual subscription plans available, with options to renew your current plan or upgrade to a new one.

- Five new models added to all plans: MiMo-V2.5-Pro, MiMo-V2.5, MiMo-V2.5-TTS, MiMo-V2.5-TTS-VoiceClone, and MiMo-V2.5-TTS-VoiceDesign.

- Tiered token consumption based on context length has been removed for all models (previously 2x consumption for 256K–1M context).

- Multiple limited-time promotions are now available:

   - **Returning user bonus** : exclusive "usage reset" reward for existing users.

   - **First-time auto-renewal discount** : new users who have never subscribed get 23% off; returning users enabling auto-renewal for the first time get 30% off. This discount cannot be combined with the first-purchase discount. Limited to one per account.

   - **Annual plan savings** : 12% off compared to monthly auto-renewal. First-purchase and first-time auto-renewal discounts do not apply to annual plans.

   - **Off-peak discount rate** : 0.8x token consumption during off-peak hours (12:00 AM – 8:00 AM Beijing Time / 4:00 PM – 12:00 AM UTC).

## 2026-4-3 Token Plan New Release

- Offers four tiers of packages, a unified Credit quota system, calculates consumption based on Token usage, and supports package upgrades and usage queries 

- Flexibly call MiMo-V2-Pro / Omni / TTS, sharing quota

- Compatible with mainstream AI programming tools: OpenClaw | Claude Code | OpenCode | Kilocode | Cline... 

## 2026-03-03 MiMo-V2-Flash Update

**Model Plugin Capabilities**

- MiMo-V2-Flash supports Web Search tool to access real-time public network information

## 2026-02-10 Real-name authentication of enterprises and corporate payment functions are launched 

**Real-name authentication of enterprise accounts and  domestic non-mainland users**

- Added real-name authentication for enterprises

- Added real-name authentication for domestic non-mainland users

- Changed the account that supports real-name authentication to an enterprise account

**B2B corporate online banking top-up**

- Corporate accounts support payment through corporate online banking

- Support corporate order refunds and invoicing

## 2026-01-26 Billing Function Launched

**Model inference service billing**

- The model inference service is billed based on token consumption, and supports viewing and downloading bills and checking real-time balance.

## 2026-01-20 The Recharge Function Launched

**Recharge and invoicing**

- Domestic users: Personal real-name authentication.

- Global users: Recharge, refund, invoicing, balance alerts, metering and billing, and billing.

**Bill details**

- Existing users' free credit will be automatically credited, and new users will receive free credit upon registration.

## 2025-12-16 Xiaomi MiMo API Open Platform Released

**API Key Management and Usage Tracking**

- Supports quick creation and configuration of API keys in the console to achieve model call authentication.

- Real-time viewing and export of usage data such as token consumption and call count.

**One-stop developer documentation center**

- Provides a quick guide to getting started with the platform, model API documentation, and integration extension methods

- Includes model introduction, debugging examples, and troubleshooting scenarios


--- DOCUMENT: Service Agreement ---
URL: https://platform.xiaomimimo.com/static/docs/terms/user-agreement.md

# Xiaomi MiMo Open Platform Service Agreement 

Our Service Agreement was updated on January 20, 2026.

The Xiaomi MiMo Open Platform Service Agreement (hereinafter referred to as the "Agreement") is the agreement between you (or "User", which refers to the individual or organization that registers, logs in, uses, and browses the Xiaomi MiMo Open Platform) and Xiaomi Technology Netherlands B.V., Xiaomi Technologies Singapore Pte. Ltd. (the Platform Operator) and its affiliates (hereinafter referred to as "Xiaomi") regarding the Xiaomi MiMo Open Platform and the products, programs and services provided by the Xiaomi MiMo Open Platform (hereinafter referred to as the "Service"). 

**Xiaomi hereby reminds users to carefully read and fully understand the provisions of this Agreement, especially the provisions of exemption or limitation of liability, the application of law and dispute resolution provisions, especially those clauses that will be presented in bold form.** 

 

If you agree to this Agreement and complete all registration procedures, it means that you have fully read, understood and accepted all the contents of this Agreement, and have reached an agreement with Xiaomi to become a user of the Xiaomi MiMo Open Platform. If you do not agree to this Agreement or any of its provisions, please do not register, log in, or use the Xiaomi MiMo Open Platform Services. 

## 1. Scope of the Agreement

 

1.1 Xiaomi MiMo Open Platform is a website operated by Xiaomi Technologies Singapore Pte. Ltd. to provide API products and services based on artificial intelligence technology. Xiaomi will conduct data processing in compliance with the requirements of applicable laws and regulations. If you wish to select data storage regions or restrict the provision of services in certain regions, you may contact us via the Platform. You acknowledge and agree that, selecting data storage regions shall be subject to compliance with relevant legal requirements and may incur additional service fees.This Agreement applies to your use of the Open Platform services outside the territory of the People's Republic of China (PRC). If you access the services within the territory of the PRC, you acknowledge and agree that both parties shall be governed by the relevant service terms applicable to in-PRC services and published on the Open Platform.Under this Agreement, the operating entity of the Xiaomi MiMo Open Platform may change according to the adjustment of the platform business, and the changed Xiaomi MiMo Open Platform Operator will jointly perform this Agreement and provide you with services. The change of the operating entity will not affect your rights and interests under this agreement. 

1.2 The [Xiaomi's General Privacy Policy](https://privacy.mi.com/all/en_US) and the [Xiaomi Account User Agreement](https://static.account.xiaomi.com/html/agreement/user/en_US.html) are an integral part of this Agreement and have the same legal effect as this Agreement. Considering the development of Internet business, the terms of this agreement do not fully cover all the rights and obligations of you and Xiaomi, nor can it guarantee that it fully meets the needs of development. The legal notices, privacy policies, platform specifications, rules, notices, announcements, operating rules, documents, and reminders of the Xiaomi MiMo Open Platform are supplementary agreements to this Agreement, which are inseparable from this Agreement and have the same legal effect. If you use the services of this platform, you are deemed to have agreed to the above supplementary agreement. 

**1.3 This Service is only available for adults. You must be at least 18 years of age or have reached the age of majority in your applicable jurisdiction, whichever is higher, to access and use this Service.** 

## 2. Xiaomi Accounts and Registration

 

2.1 If you log in to the Xiaomi MiMo Open Platform, you need to register a Xiaomi account. Your application and use of your Xiaomi Account shall comply with the Xiaomi Account User Agreement and the specifications amended and published by Xiaomi from time to time. 

2.2 Before you start the registration process to use the services of this platform, you should have the legal authority to execute and perform this Agreement. The operation under your account represents you. If you need to use relevant products or services on the Xiaomi MiMo Open Platform on behalf of a specific organization, you must provide relevant certificate materials and authorization materials as required by Xiaomi. In addition, you must ensure that you are not subject to trade restrictions, sanctions, or other laws or rules imposed by any country, international organization, or region, otherwise you may not be able to register and use the Xiaomi MiMo Open Platform services. 

2.3 Your account is limited to your own use, and it is prohibited to give, borrow, rent, transfer, sell or otherwise license others in any form without our written consent. We especially remind you to keep your account and password safe. The API key you create through your Xiaomi account is the essential credential required when you use the APIs of the Xiaomi MiMo Open Platform. Please keep the API key you create properly to prevent any kind of leakage, do not share or disclose your API key with others, and do not expose it to browsers or other client code. You will be responsible for any unauthorized use or other security issues caused by the sharing or disclosure of API keys.

## 3. Platform Services and Disclaimer 

3.1 Xiaomi MiMo Open Platform is only a neutral technical service provider, providing you with various technical products and services in accordance with the agreement, and you shall abide by the relevant provisions of this Agreement when using the services of this Open Platform, and shall not violate any applicable provisions of laws and regulations, and shall not use this service to infringe on the legitimate rights and interests of others and seek improper benefits.

3.2 You may use the Open Platform Services in accordance with this Agreement under the premise of complying with laws and this Agreement, and you shall not perform the following acts:

3.2.1 Delete all copyright information on the Service and other copies, and modify, delete or circumvent the technical measures set by the Service to protect intellectual property rights.

3.2.2 Reverse engineer the Service, such as disassembling, decompiling, or otherwise attempting to obtain the source code of the Service.

3.2.3 By modifying or forging running instructions and data, adding, deleting, or changing functions or operating effects, or operating or disseminating software and methods used for the above purposes or disseminating them to the public, regardless of whether these actions are for commercial purposes.

3.2.4 Use the Service to engage in any behavior that endangers network security, including but not limited to: using unauthorized data or accessing unauthorized servers or accounts; Entering public networks or other people's operating systems without permission and deleting, modifying, or adding stored information; Unauthorized attempts to probe, scan, test the weaknesses of the software system or network, or otherwise commit acts that undermine network security; Attempt to interfere with or disrupt the normal operation of the Service system or website, intentionally spread malicious programs or viruses, and other acts that damage and interfere with normal network information services; Forging TCP/IP packet names or partial names.

3.2.5 Use the Service to publish, transmit, disseminate, or store content that violates local laws and regulations.

3.2.6 Use the Service to publish, transmit, disseminate, or store content that infringes on the intellectual property rights, confidential information, and other legal rights of others.

3.2.7 Use this service to publish, transmit, and disseminate advertising information and spam information in batches.

3.2.8 Other use of the Service in any illegal way, for any illegal purpose, or in any way inconsistent with the use permitted by this Agreement.

3.3 You shall ensure that the content developed, produced, used, uploaded, commented, published, disseminated, stored, and shared using this product/services complies with relevant laws, has obtained legal authorization from relevant rights holders, and shall be responsible for its legality, accuracy, completeness, and reliability. You may not use the website or services to create the following information:

1. Opposing the basic social principles required by applicable law.

1. Endangering national security, leaking state secrets, subverting state power, or undermining national unity of any country or jurisdiction.

1. Harming national interests of any country or jurisdiction.

1. Inciting racial discrimination or hate crimes.

1. Undermining freedom of religion or inciting discrimination based on religious beliefs.

1. Creating or disseminating false information that may mislead or harm the public or any person.

1. Creating or disseminating obscene, pornographic, violent, murderous, terroristic, or criminal incitement content.

1. Insulting or slandering others, infringing upon the lawful rights and interests of others.

1. Including any other prohibited content by applicable laws or regulations.

If your behavior violates or may violate the above agreements, we have the right to deal with infringing information based on relevant evidence, and we have the right to refuse to provide you with relevant services or restrict your use of some functions. If Xiaomi suffers losses, or is claimed by a third party, or punished by regulatory authority, you shall compensate Xiaomi for the losses and/or expenses incurred as a result, including reasonable attorney's fees and investigation and evidence collection costs. 

3.4 This service is affected by differences in factors including but not limited to user reasons, network service quality, social environment and other factors, and may be invaded by various security issues.

 

3.5 When you use the Service or request Xiaomi to provide specific services, the Service may use third-party systems or third-party services, and you shall comply with the relevant rules of this Agreement as well as the third-party agreements and relevant rules. You understand and agree that when using third-party services, third parties may read user data, and Xiaomi does not guarantee the safety, accuracy, validity and other uncertain risks of the results achieved through third-party systems or third-party software support. For example, the order process is condcuted by our online reseller & Merchant of Record, [Waffo.com](http://Waffo.com), who also handles order-related inquiries and returns.

3.6 Xiaomi reminds users that, Xiaomi has the right to modify or interrupt the service at any time without notifying the user, and Xiaomi is not responsible to the user or any third party for exercising the right to modify or interrupt the service.

3.7 Except as expressly provided by laws and regulations, Xiaomi will do its best to ensure that the software and its technology and information are safe, effective, accurate and reliable, but subject to prior art, users understand that Xiaomi cannot guarantee this. 

**3.8 Content Disclaimer**

**Artificial intelligence and machine learning are rapidly developing research fields. Xiaomi is also constantly working to improve this service to make it more accurate, reliable, safe and trustworthy. However, due to technical characteristics, Xiaomi cannot fully guarantee the legitimacy, authenticity, accuracy and completeness of the output obtained by users through this product under the premise of making reasonable efforts. For large model generated content that may be inaccurate or offensive, Xiaomi will not be responsible for any damage caused by the user's dependence on this platform:**

**3.8.1 The content generated by this product does not represent the product/service itself or the views of Xiaomi.** 

**3.8.2 Users should not rely on large models for advice on problems in specialized fields (e.g. medical, legal, financial, etc.).** 

 

**3.9 Technical Disclaimer**

**3.9.1 This product does not assume other responsibilities than those expressly provided by law, therefore, we do not guarantee the following situations:**

**(1) This product is not guaranteed to meet commercial purposes, specific purposes or fully meet the requirements of users, and any warranties arising from any transaction or trade use;**

**(2) Due to possible computer viruses, network communication failures, system maintenance and other factors and possible force majeure events or accidents, this product does not guarantee that the service will not be interrupted, accurate or error-free, nor does it guarantee that any content is safe or not lost or changed;**

**(3) This product does not guarantee the ability to correct all defects of this service at the current state of the art.** 

**3.9.2 We shall not be liable for tort liability or legal disputes between users and third parties when:**

**(1) Users harm others or have disputes with others in the process of using the product;**

**(2) The user infringes the intellectual property rights of others in the process of using the product. If Xiaomi is required to bear the liability for compensation, then Xiaomi has the right to recover from the user.** 

 

**3.10 When using the Xiaomi MiMo Open Platform Paid Service, you should complete the account recharge in advance. As long as the account balance is sufficient, you can use the services of this platform normally. If the account balance is insufficient, the platform has the right to suspend the service. You should pay attention to the status of your account balance and complete the recharge and renewal in a timely manner. All responsibilities and losses caused by your failure to renew the fee in time shall be borne by you.** You promise and warrant that the source of funds used to recharge your account is legal and compliant, otherwise Xiaomi has the right to take corresponding measures according to the requirements of the relevant competent authorities, including but not limited to account locking, restricting use, etc. 

**3.11 The billing rules, payment methods, free quotas, etc. related to the Xiaomi MiMo open platform are subject to the content published on the product page of this platform. You acknowledge and agree that Xiaomi has the right to adjust the billing rules and free quota issuance according to operational needs, and Xiaomi will notify you of the above changes in advance through reasonable means such as site notifications, official website announcements, email or text messages. If you continue to use the service after the billing rules are adjusted, you are deemed to have agreed to accept the adjusted billing plan.** 

 

**3.12** When you recharge your account, you should carefully check the recharge account, recharge amount, payment method and other information. If your rights and interests are damaged due to your own operational errors, you shall bear the relevant losses and responsibilities. If you need to apply for a refund, you can apply on the [Recharge Details] page and submit the application according to the refund process, conditions and requirements announced by the platform. For applications that meet the refund conditions, the platform will refund the remaining unconsumed recharge amount in the account, and the consumed amount will not be refunded. **Please note that there can only be one processing refund application for an account, and you will not be able to continue using the services under this platform after the refund is initiated. Due to possible delays in billing on the platform, the refund amount is subject to the actual amount received.** 

 **3.13 When using the Token Plan , you should carefully read the product description and usage restrictions on the subscription page. You acknowledge and agree that Token Plan services are non-refundable and non-cancellable upon purchase. Xiaomi reserves the right to modify or adjust Token Plan based on operational needs, including but not limited to activity rules, activity validity periods, and subscription service validity periods. Please refer to the latest content on the page and Xiaomi's notifications for the latest information. Subscription benefits purchased prior to any changes or adjustments to the activity rules will not be affected.** 

**3.14 Upon your activation of the automatic subscription service, you shall be deemed to have authorized Xiaomi MiMo to automatically deduct fees from your account upon each expiration of your subscribed service (Automatic deduction date) in accordance with the deduction rules of the payment method and extend the validity period corresponding to the subscription cycle.**  The specific subscription cycle shall be subject to the statement on the Xiaomi MiMo platform. Xiaomi MiMo shall notify you one day prior to the expiration of the service term via in-site message, email, or SMS. **If you do not explicitly cancel the automatic subscription service before the automatic service deduction date, you shall be deemed to have agreed to continue using the automatic subscription service provided by Xiaomi.You fully understand and acknowledge that any losses arising from the failure of automatic renewal due to insufficient balance in your account shall be borne by you. Provided that you have not canceled the automatic renewal service, Xiaomi MiMo will resume the automatic renewal service for you when/after your account balance is replenished (subject to the rules of third-party payment methods).**  After successful deduction, Xiaomi MiMo will resume your subscribed service.

**You hereby confirm that the withholding behavior of Xiaomi shall remain valid before you successfully cancel the automatic renewal service, and Xiaomi shall not refund any fees deducted prior to your successful cancellation of the automatic renewal service.**  

You may cancel the automatic subscription service through Xiaomi MiMo Platform: Console → Subscription Management → Cancel Automatic Renewal.

 

## 4. Data Protection Terms

 

Xiaomi will collect, use, and process your personal information in accordance with the** Xiaomi MiMo Open Platform Privacy Policy**. Under applicable laws, you have the right to access, correct, delete your personal information, and to deactivate the service or your account. Specific procedures are detailed in the Privacy Policy. These Data Protection Terms apply to regions outside the Chinese Mainland. Both parties shall comply with the principles, procedures, and respective responsibilities set forth in this appendix.

**4.1 Definitions and Roles**

<table>
<thead>
<tr>
<th>Data Controller</th>
<th>the natural or public or private legal person who alone or jointly with others determines the purpose, content and use of the Personal Data.</th>
</tr>
</thead>
<tbody>
<tr>
<td>Data Processor</td>
<td>an entity that processes Personal Data on behalf of a Data Controller.</td>
</tr>
<tr>
<td>Personal Data</td>
<td>any numerical, alphabetical, graphic, photographic, acoustic or any other type of information relating to identified or identifiable natural persons shared between the Parties pursuant to the Agreement and this Addendum.</td>
</tr>
<tr>
<td>Transfer</td>
<td>the access by, transfer or delivery to, or disclosure of Personal Data to a person, entity or system located in a country or jurisdiction other than the country or jurisdiction from where the Personal Data originated.</td>
</tr>
<tr>
<td>Data Protection Legislation</td>
<td>any laws and regulations relating to the processing of Personal Data and privacy of the territory and, if applicable, the guidance and codes of practice issued by the relevant data protection or Supervisory Authority.</td>
</tr>
<tr>
<td>Data Breach</td>
<td>a breach of security leading to the accidental or unlawful destruction, loss, alteration, unauthorized disclosure of, or access to the Personal Data.</td>
</tr>
</tbody>
</table>

Xiaomi acts as a Processor in data processing activities, and you are the Data Controller. The data you upload, store, process, download, distribute, or otherwise handle through our services constitutes your business data, over which you retain full control.

**4.2 Purpose and Use**

You engage Xiaomi to process the personal information necessary for the Service for the reasonable purpose of using it. The types of personal information processed include registration information and usage information, among others.

**4.3 Rights and Obligations**

1. You shall ensure that your instructions comply with all applicable personal information protection laws.

1. You shall ensure that Xiaomi's processing of personal information under these Terms has a legal basis and complies with your agreements with the data subjects.

You have fulfilled the notification obligations towards data subjects as required by applicable personal information protection laws when collecting their information and have obtained authorization from the data subjects for the processing activities under the main agreement and this appendix, as well as for entrusting Xiaomi to process the information;

If you obtain personal information from a third party, you warrant that such third party has fulfilled the aforementioned notification and authorization requirements; and

If you transmit personal information to Xiaomi that was collected in violation of applicable personal information protection laws or without proper authorization from the data subjects, you shall provide written proof of such authorization upon Xiaomi's request.

1. You shall independently undertake claims or losses arising from its non-compliance with the obligations of Data Controller and applicable Data Protection Legislations.

**4.4 Data Storage**

Upon service expiration, completion of the agreed purpose, or at your request, unless prohibited by laws that Xiaomi must comply with, Xiaomi will cease processing or permanently delete the personal information within a reasonable period. When providing services outside the Chinese Mainland, Xiaomi will store the relevant data on servers located in Europe and Singapore.

**4.5 Security Measures**

1. Xiaomi shall implement appropriate technical and organizational measures in accordance with all applicable Data Protection Legislations to protect the Personal Data against accidental or unlawful destruction, loss or damage, alteration, unauthorized disclosure or access, and against all other unlawful forms of processing;

1. Xiaomi shall ensure that only authorized personnel requiring access to personal information for their duties have access thereto, and only to the necessary extent;

1. Xiaomi shall ensure that each authorized person with access to personal information is aware of and understands their obligations under personal information protection laws and these Terms;

1. Xiaomi shall ensure the reliability of authorized personnel who have access to personal information, and shall ensure that all such personnel have undergone relevant training on personal information protection and have signed confidentiality agreements.

## 5. Intellectual Property

 

5.1 The intellectual property rights owned by both parties before using the Service shall remain with each party and will not be transferred as a result of the performance of this Agreement by both parties. For the avoidance of doubt, the ownership and intellectual property rights of the Xiaomi MiMo model belong to Xiaomi, including but not limited to model parameters, algorithms, code, framework structure, etc.

5.2 When you use the relevant services of the Xiaomi MiMo Open Platform, you shall not upload, publish, modify, disseminate or copy any copyrighted materials, trademarks, or proprietary information belonging to others or other content that may infringe on the legitimate rights and interests of third parties in any way without the prior written consent of the relevant right holders. If you believe that the information on the Xiaomi MiMo Open Platform infringes on your intellectual property rights or other legitimate rights and interests, please provide feedback according to the contact information published in this Agreement. 

5.3 Without the prior written consent of Xiaomi, you may not display or use the trademarks, service marks, trade names, brand names, domain names, website names or any other distinctive brand features ("Logos") owned by Xiaomi or its affiliates, alone and/or in conjunction with other means.

 

## 6. Limitation of Liability

 

**6.1 Xiaomi has the right to independently take measures against you for violating this Agreement or other terms of service, such as warnings, corrections within a time limit, restriction of account functions, suspension of use, closure of accounts, prohibition of re-registration, deletion of relevant content, etc. Xiaomi has the right to keep relevant records of suspected violations of laws and regulations and suspected illegal crimes, and report to the relevant competent authorities in accordance with the law and cooperate with the relevant competent authorities in investigation. You shall be responsible for any legal liabilities or claims, demands, or losses arising from or arising therefrom, and compensate Xiaomi for any losses caused by you (including litigation fees, arbitration fees, lawyer fees, notary fees, announcement fees, appraisal fees, travel expenses, investigation and evidence collection fees, compensation, liquidated damages, settlement costs, administrative penalties, fines, etc.).** 

 

**6.2 Unless otherwise agreed, neither party shall be liable for incidental, incidental, punitive, special, indirect loss or damage, including but not limited to loss of profits or goodwill, howsoever arising out of such loss or damage, on what theory of liability is based, and whether in an action for breach of contract, tort, compensation or any other cause of action, even if advised of the possibility of such loss.** 

 

## 7. Notice 

7.1 You are registering as a Xiaomi MiMo Open Platform user and accepting the Xiaomi MiMo Open Platform terms. You shall provide Xiaomi with real and valid contact information (including your email address, contact number, contact address, etc.), and you are obliged to update the relevant information in a timely manner and maintain a status that can be contacted if the contact information changes. Notifications such as pop-ups pushed by Xiaomi to you through the interface are also effective notifications sent to you. Xiaomi will send you various notices to one or more of your above contact information, and the content of such notices may have a material beneficial or adverse impact on your rights and obligations, so please pay attention to them in a timely manner. You should ensure that the contact details provided are accurate, valid, and updated in real time. If the notice cannot be delivered or is not delivered in time due to inaccurate contact information provided or failure to inform the changed contact information in time, you shall bear the legal consequences that may arise therefrom. 

## 8. Governing Law and Others

 

8.1 This Agreement is to be governed by and construed in accordance with the laws of Singapore (excluding conflict of law principles).

Any dispute arising out of or in connection with this Agreement, including any question regarding its existence, validity or termination, shall be referred to and finally resolved by arbitration administered by the Singapore International Arbitration Centre ("SIAC") in accordance with the Arbitration Rules of the Singapore International Arbitration Centre ("SIAC Rules") for the time being in force, which rules are deemed to be incorporated by reference in this clause. Undisputed portions of the Agreement shall continue to be performed.

8.2 If some provisions of the Agreement are unapplicable for any reason, the other provisions of this Agreement continue to apply and the inapplicable provisions will be modified so that they can be applied in accordance with the law. 

8.3 Other rights not expressly authorized are reserved by Xiaomi and you must obtain written permission from Xiaomi when exercising these rights. Xiaomi's failure to exercise any of the foregoing rights shall not constitute a waiver of such rights. 

8.4 In order to provide you with better services, Xiaomi has the right to amend this Agreement, which constitutes an integral part of this Agreement. The updated Agreement will be published on the official website or service page, so please check the latest version of the terms of the Agreement on the official website. If you do not accept the revised Agreement, please stop using the Service immediately. Your continued use of the Service will be deemed your acceptance of the modified Agreement.

8.5 **If you find any violations of laws or regulations or violations of this Agreement, or if you have any comments or suggestions on the Services, you can provide your feedback by**

**(1) filing complaints and reports via the "Contact Us" on the website.** 

**(2) scanning the QR code for the "Developer Group" to join the WeChat group, and providing feedback in the chat group.** 

**(3) contacting our operation team by sending email to** **support-mimo@xiaomi.com.**


--- DOCUMENT: Privacy Policy ---
URL: https://platform.xiaomimimo.com/static/docs/terms/privacy-policy.md

# Xiaomi MiMo Platform Privacy Policy

Our Privacy Policy was updated on March 17, 2026.

Please take a moment to familiarize yourself with our privacy practices and let us know if you have any questions.

## Overview

1. Introduction 

1. What does personal information mean?

1. What information do we collect and for what purposes?

   1. Collection of personal information from you

   2. Collection of personal information from third-party sources 

   3. Non-personally identifiable information

1. How do we share your personal information with third parties?

1. What is the legal basis for processing your personal information?

1. How long will your personal information be stored?

1. How can you manage your privacy preferences? 

1. What are your data protection rights?

1. How to exercise your data protection rights and contact us?

1. How is your personal information transferred globally?

1. Are you obliged to provide your personal information?

1. Is your personal information the basis for automated decision-making, including profiling?

1. How do we update this Privacy Policy?

 

## 1. Introduction

This product and its related services, including account creation, sign-in, and management, are provided by Xiaomi Technology Netherlands B.V., Xiaomi Technologies Singapore Pte. Ltd., and/or their affiliated companies (hereinafter referred to as "Xiaomi", "we", "our", or "us").

We are committed to protecting your privacy. This Privacy Policy explains how we collect, use, store, transfer, protect and otherwise process any personal information that we collect from you or a third party when you use this product and its related services. You may consult the privacy policies of the relevant services for terms and conditions regarding processing of personal information when you use other services, or regarding other data protection matters. Terms and conditions regarding protection of minors or security measures can be found in [https://privacy.mi.com/all/languages/](https://privacy.mi.com/all/languages/).

Ultimately, what we want is the best for all our users. Should you have any questions about our data processing practices as summarized in this Privacy Policy, please contact us via [https://privacy.mi.com/support](https://privacy.mi.com/support) to address your specific queries. We will be happy to hear from you. 

## 2. What does personal information mean? 

Under this Privacy Policy, "**personal information**" means information that can be used to directly or indirectly identify an individual, either from that information alone or from that information combined with other information about that individual available to Xiaomi, except as otherwise specifically provided by applicable law in your region. It includes information such as name, contact details, identification numbers, location data or online identifiers (e.g., Xiaomi Account ID). We will use your personal information strictly following this Privacy Policy.

## 3. What information do we collect and for what purposes?

### 3. 1. Collection of personal information from you

The purpose of collecting personal information is to provide you with this product and its related services. For this reason, we will process the following personal information:  

- **Log in to your Xiaomi Account**. You need to log in to your Xiaomi Account to access the relevant functions of Xiaomi MiMo Platform. For this purpose, we will collect your account ID, mobile number, or email address, and create an API Key to verify and display your identity when providing API services.

- **API Services.** If you use the API services, we will collect your IP address and the content (text, audio, video, picture) you submit to analyze the relevant instructions based on the model you select and to generate the returned content. Xiaomi will not use the content you provide for model training or any other purposes. When you use prepaid API services, we will collect your top-up information and transaction records**.** 

- **Feedback**. When you provide us feedback, we will collect your contact information(phone number, email), and the information(including screenshots) you submit. 

- **Notification.** To provide you with balance alerts, message notifications services, we will send you notifications via the contact information you provide (e.g., mobile number,email).

### 3. 2. Collection of personal information from third-party sources

Xiaomi products and services may require a prior Xiaomi Account profile. For a faster signing-in or to easily complete Xiaomi Account personal information, you may also authorize the pairing of a third-party account with your Xiaomi Account (e.g., your Google, Facebook or Apple account). With your consent, you authorize the third-party account to import your profile picture, nickname, email and other information to your Xiaomi Account. 

Please note that we will ensure the security of your information through means such as encryption, but handling of your personal information by third parties is subject to the privacy policy of the relevant third party. For this reason, we recommend that you read third parties' privacy policies just like you read ours. You can cancel authorization for third parties at any time in "Accounts and permissions" on [https://account.xiaomi.com/](https://account.xiaomi.com/).

### 3. 3. Non-personally identifiable information

We also collect other types of information which are not directly or indirectly linked to an individual and which may not be defined as personal information according to applicable law. Such information is called non-personally identifiable information and we may collect, use, transfer, disclose and otherwise process such non-personally identifiable information. Such information may include statistical data generated when you use a specific service, such as interaction records like daily usage events, page access events, page access time events, session events (when not considered personal information) and error records when you use our services. The purpose of such collection is to improve the services we provide to you (e.g., for correcting web mistakes). The types and amount of information collected depend on how you use our services. We aggregate such information. In its aggregated form, the data is not personal information and cannot be used to identify you. However, if non-personally identifiable information is combined with personal information, such non-personally identifiable information will be processed as personal information under the ruling of this Privacy Policy.

## 4. How do we share your personal information with third parties?

To ensure that we provide you with the products and its related services described in this Privacy Policy, we may share necessary personal information with our Xiaomi affiliates, service providers, business partners and other third parties, including:

- Recharge and Refund.The order process is provided by Waffo Hong Kong Limited, or other affiliated companies. In order to provide you with recharge and refund service related to Xiaomi MiMo Open Platform, we will provide certain information to this service provider. This information includes Xiaomi account.

- Online Search. In order to provide you online search, we will provide your query and IP address to Google .

- Public Administrations in case of specific requirements made in accordance with the applicable regulations. 

- Courts and Tribunals, in case of specific requirements made in accordance with the applicable regulations.

- Law Enforcement agencies, in case of specific requirements made in accordance with the applicable regulations.

## 5. What is the legal basis for processing your personal information?

We need a lawful basis for processing your personal information in accordance with the law. Where applicable according to the law in your jurisdiction, the legal base for processing your personal information under this Privacy Policy is:

- **As a result of your consent**. You can provide also personal information to us on a voluntary basis for the purposes of providing you with this product and its related services.

## 6. How long will your personal information be stored?

As a general rule, we retain personal information for the period necessary for the purposes described in this Privacy Policy, or as required by applicable law. We will cease to retain and delete or anonymize personal information once the purpose of collection is fulfilled, or after we confirm your request for erasure, or after we terminate the operation of the corresponding services, except when required or permitted by applicable law, in which case, your personal information will be isolated and will not be further processed except for the attendance of legal responsibilities and other purposes permitted by applicable law. In such circumstances, your personal information could be made available exclusively to the parties permitted by applicable law. Once the corresponding retention periods have elapsed, such personal information will be deleted or anonymized.

## 7. How can you manage your privacy preferences? 

We recognize that privacy concerns differ from person to person. Therefore, we provide examples of ways for you to restrict the collection, use, disclosure, or other processing of your personal information and to control your privacy settings:

- *Log out your Xiaomi account via Personal Center > Log Out.*

- *View and update your account security information, personal information, permissions, and device management on your device in Settings > Xiaomi Account, or by signing in to *[*https://account.xiaomi.com*](https://account.xiaomi.com/)*;*

- *If you have previously agreed to us using your personal information for the aforementioned purposes, you may change your mind at any time by contacting us on *[*https://privacy.mi.com/support*](https://privacy.mi.com/support)*;*

- *Cancelling a service or account. If you wish to cancel your Xiaomi Account, you may do so by following the steps in Settings > Xiaomi Account > Help > Delete account, or by visiting *[*https://account.xiaomi.com*](https://account.xiaomi.com/)*.*

Please note that cancellation of your Xiaomi Account or profile will prevent you from using the full range of Xiaomi products and its related services. To protect you or others' legitimate rights and interests, we will evaluate whether or not to support your request for cancellation based on your use of various Xiaomi products and services. 

## 8. What are your data protection rights? 

You have certain rights in relation to personal information that we hold about you (referred here as the “**request**”). Please note that depending on where you are based, these rights will be subject to specific exclusions and exceptions under applicable local laws:

- **Right to access/obtain a report detailing the personal information we hold about you**. A copy of your personal information processed by us will be provided to you upon your request free of charge. For any extra requests for relevant information, we may charge a reasonable fee based on actual administrative costs according to the applicable laws. In any event, please note that you can log in to Xiaomi Account to check the personal information we hold from you. 

- **Right to correct your personal information**. If any information we are holding on you is incorrect or incomplete, you are entitled to have your personal information corrected or completed based on the purpose of use. Note that you can also log in to Xiaomi Account for correcting your data.  

- **Right to erase your personal information**. Based on the requirements of applicable law, you have the right to request the deletion or removal of your personal information where there is no compelling reason for us to keep using it. We shall consider the grounds regarding your erasure request and take reasonable steps, including technical measures, to proceed with the erasure of your personal information. Please note that we may not be able to immediately remove the information from the backup system due to applicable law (for instance, when necessary to preserve your personal information for potential claims which may arise out of or in relation to the processing of such personal information) and/or security technology limitations. If this is the case, we will securely store your personal information and isolate it from any further processing until the information can be deleted or be made anonymous. 

- **Right to object to the processing of your personal information.** You have the right to object, on grounds relating to your situation, to a processing of your personal data which is based on Xiaomi’s legitimate interest (e.g., direct marketing). If you object to such processing, we will no longer process your data for these purposes unless we can demonstrate compelling legitimate grounds for the processing or for the establishment, exercise or defense of legal claims.

- **Right to restrict the processing of your personal information**. You have the right to restrict the processing of your personal information by us, for instance when the processing is unlawful according to your understanding, but you oppose the erasure of your personal information. In such cases, your personal information will only be processed with your consent or for the exercise or defense of legal claims. Please note that Xiaomi Account settings allow you also to freeze and unfreeze your account, among other possibilities. 

- **Right to data portability**. Under some circumstances provided by law, you have the right to receive the personal information concerning you in a structured, commonly used and machine-readable format and/or transmit that personal information to another data controller. 

- **Right to withdraw consent**. In those cases where your consent is required for the processing of your personal information, you may at any time withdraw such consent. However, please note that if you withdraw your consent, you may not be able to continue to use the product and its related services, and/or access certain information, features or services. The withdrawal of your consent or authorization will not affect the validity of our collection and processing carried out on the basis of the consent up until the point of withdrawal.

Please, remember that you may also access, update, and delete the details relating to the personal information in your Xiaomi Account at [https://account.xiaomi.com](https://account.xiaomi.com) or by signing into your account on your device. For additional information, please write to us or contact us via [https://privacy.mi.com/support](https://privacy.mi.com/support).

## 9. How to exercise your data protection rights and contact us?

If you have any comments or questions about this Privacy Policy or any questions relating to Xiaomi's collection, use or disclosure of your personal information, or you want to exercise your data protection rights according to the above Section, feel free to contact us by visiting [https://privacy.mi.com/support](https://privacy.mi.com/support) or at the below addresses (your request should be made in writing). When we receive questions about personal information or requests to download or access items, we have a professional team that addresses such concerns, including Data Protection Officers (DPOs), who can be contacted through [https://privacy.mi.com/support](https://privacy.mi.com/support), or in the below postal addresses. If your question itself involves a significant issue, we may ask you for more information. If you consult us, we will provide information on the relevant complaint channels that may be applicable based on your actual situation. 

- **For users located in the European Economic Area (EEA), UK and CH**:

Xiaomi Technology Netherlands B.V., Prinses Margrietplantsoen 39, 2595 AM, The Hague, The Netherlands

- **For users located in other countries/territories**:

Xiaomi Technologies Singapore Pte. Ltd. 1 Fusionopolis Link #04-02/03 Nexus@one-north, Singapore 138542

Please, make sure that you provide sufficient information to enable Xiaomi to verify your identity and ensure that you are the data subject or legally authorized to act on the data subject's behalf. Once we obtain sufficient information to confirm that your request can be processed, we shall proceed to respond to your request within any timeframe set out under your applicable data protection law. 

We have the right to refuse to process requests that are not meaningful, manifestly unfounded or excessive, requests that damage others' right to privacy, extremely unrealistic requests, and requests that require disproportionate technical work, as well as requests not required under local law, regarding information that has been made public, and regarding information given under confidential conditions. If we believe that certain aspects of the request to delete or access the information may result in our inability to legally use the information for the aforementioned anti-fraud and security purposes, it may also be rejected. We will inform you of any such decision not to process your request and the grounds of this decision if required by applicable law, in the event of which we will inform you within any timeframe set out under applicable law.

If you are not satisfied with the response you received, you can hand over the concern to the relevant regulatory authority in your jurisdiction. If you are located in the EEA/UK/CH, please find here the list of the main [EEA](https://www.edpb.europa.eu/about-edpb/about-edpb/members_en)/[UK](https://ico.org.uk/)/[CH](https://www.edoeb.admin.ch/edoeb/en/home.html) competent authorities.

## 10. How is your personal information transferred globally?

Xiaomi processes and backs up personal information through a global operating and control infrastructure. Currently, Xiaomi has data centers in the Netherlands, and Singapore. For the purposes described in the Privacy Policy, your information may be transferred to these data centers in accordance with applicable law. 

We may also transfer your personal information to third-party service providers and business partners and your data may therefore also be transmitted to other countries or regions. The jurisdictions in which these global facilities, third-party services providers and business partners are located may or may not protect personal information to the same standards as in your jurisdiction. There are different risks under different data protection laws and that we may transfer and store your personal information to overseas facilities, however, this does not change our commitment to comply with this Privacy Policy and to protect your personal information. 

If we need to transfer personal information outside of your jurisdiction, whether to our affiliates or third-party service providers or business partners, we will comply with related applicable law. We ensure that all such transfers meet the requirements of applicable local data protection laws by implementing uniform safeguards. You can find out about the safeguards that we have in place by contacting us at [https://privacy.mi.com/support](https://privacy.mi.com/support).

- If you use our services in the EEA, UK or CH, Xiaomi Technology Netherlands B.V. will act as the data controller and Xiaomi Technologies Singapore Pte. Ltd. will be responsible for processing some of your personal information. If Xiaomi shares personal information originating by you in the EEA, UK or CH to a Xiaomi Group entity, or a third-party service providers, or a business partner outside the EEA, UK or CH (please see Section 4 above, for further information), where local law may not protect personal information to the same standards as in your country or region, Xiaomi will use EU Standard Contractual Clauses or any other safeguards provided for in the GDPR or in applicable law of UK or CH to protect your information with the highest European standards.

## 11. Are you obliged to provide your personal information?

As stated above, if you do not provide some mandatory personal information, you may not be able to use this product or its related services, or we may not be able to respond to your queries. Please review the Section “*What information do we collect and for what purposes?*” for further information. 

## 12. Is your personal information the basis for automated decision-making, including profiling?

As a matter of principle, we do not use your personal information provided for fully automated decision-making process, including profiling. In the event that we should use such processes, we will specifically inform you in advance of this and your rights in this respect, including consent information. 

## 13. How do we update this Privacy Policy?

We review this Privacy Policy periodically based on changes in business, technology and applicable law and good practice, and we may update this Privacy Policy. If we make a material change to this Privacy Policy, we will notify you via pop-up window, or via email to the email address corresponding to your Xiaomi Account, or via other ways legal and available, so that you can learn about the information we collect and how we use it. Such changes to this Privacy Policy will apply from the effective date specified in the above notice. We encourage you to check this page regularly for the latest information on our privacy practices. Where required by applicable law, we will ask for your explicit consent when we collect additional personal information from you or when we use or disclose your personal information for new purposes.