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 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 and transaction history in Recharge Details.

How to set balance alerts?

Enable alerts in 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, 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 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.

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.

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 9 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-v2.5-asr: Speech Recognition 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: In conjunction with the comprehensive upgrade of TokenPlan this time, for all Token Plans still within their validity period, regardless of the current usage of the package, the consumed Credits quota will be fully reset, which will officially take effect at 00:00 on May 27, 2026 Beijing Time, with the validity period remaining unchanged.

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

• 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

• Usage and Quota

• Are the quotas of different models consumed independently?

No. The available models in the package are consumed in parallel according to different proportions, not independently. TTS all models are free for a limited time and do not consume package credits. ASR models deduct credits based on the duration of the input audio (duration is counted accurately to the second and finally converted to hours for statistics) The following table lists the package deduction points corresponding to each token for cache, input, and output of each model .

Language Model

ASR Model

TTS Series models are free for a limited time and do not consume package credits.

For example, if you have subscribed to the Lite Plan (4.1B Credits), you can call the MiMo-V2.5 series models individually or in combination. After you have used 10M input (cache miss) tokens of mimo-v2.5-pro, it is equivalent to consuming 3000M Credits.You can still enjoy 1100M Credits of mimo-v2.5.If you subscribe to the Lite plan and only use the ASR model, you can use 4100M ÷ 30M/hour = 136.6 hours per month (equivalent to processing 4.5 hours of audio per day for 1 consecutive month). You can check the quota and usage of your current plan in Subscription Management .

• 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.

  • 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 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 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.

• 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 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 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:

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 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).

2. 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).

3. 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:

• 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 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.