Free quota for new users

When you first activate Alibaba Cloud Model Studio, the platform automatically grants you a free quota for various models.

Rules

Validity period

The free quota is valid for 90 days, starting from the date you activate Alibaba Cloud Model Studio, the model is released, or your model request is approved (whichever is later). After the quota expires or is exhausted, continued use of the model inference service will incur charges.

After the free quota expires, it automatically becomes invalid and cannot be reissued, extended, or reset:

• The validity period is not paused regardless of whether the quota is used.
• After the quota expires, the remaining portion is automatically voided and will not be reissued or extended.
• Re-registering a new account under the same identity verification entity does not grant the new user free quota again.

Scope

The free quota only covers charges generated by real-time inference (invocations) of models.

Notes

An Alibaba Cloud primary account and its RAM users share the free quota.

For example, the total free quota for qwen-max is 1,000,000 tokens. If the primary account consumes 100,000 tokens and a RAM user consumes 200,000 tokens, the remaining free quota for qwen-max is 700,000 tokens.

Free quotas for different models (including different snapshot versions of the same model) are independent of each other and cannot be interchanged or shared.

• Each model has an independent free quota (typically 1,000,000 tokens) that cannot be merged or transferred across models.
• A snapshot version with a date suffix (such as qwen-max-2026-05-17) and the latest version without a date suffix (such as qwen-max) are treated as two independent models, each with its own quota.
• When the free quota of a model is exhausted, the system does not automatically switch to another model that still has quota. To use the free quota of another model, you must manually change the model parameter in your code or tool configuration.

Get your free quota

You must complete identity verification before activating Alibaba Cloud Model Studio. Visit Alibaba Cloud Model Studio - China (Beijing) region. After reading and agreeing to the agreement, the system automatically activates Alibaba Cloud Model Studio and grants you a free inference quota.

If the service agreement is not displayed, you have already activated Alibaba Cloud Model Studio and received the free quota.

The free quota is automatically granted by the system after you activate Alibaba Cloud Model Studio for the first time. You do not need to manually claim it or purchase any product. To continue using pay-as-you-go billing after the free quota is exhausted, add funds to your account to continue calling models.

After activation, the free quota may be delayed and typically takes effect within two hours. If it is not displayed immediately after activation, wait patiently. Models with a free quota are marked with a blue quota bar in the model list.

For ASR models, you must enable access for each model in a business space in the Model Studio console before you can call the model and consume its free quota.

Check your remaining quota

You can check the free quota of models in the following three ways.

The remaining free quota is a combined total shared by input tokens and output tokens, and input and output are not calculated separately. The input tokens and output tokens generated by each invocation are deducted from this total together. The remaining amount displayed in the console is the total number of remaining tokens after the deduction.

Method 1: From the free quota page

In the console, go to the Free Quota page to view the remaining free quota and expiration time of all models. The top of the page provides a Buy Savings Plan button entry for quick access to the savings plan purchase page. Below, four metric cards summarize the overall free quota: Total models with quota, Models with usage over 50%, Models with usage over 80%, and Models with exhausted or expired quota, helping you quickly identify models that require attention. You can filter by model type or search for models.

The table at the bottom of the page lists the Model Code, Model type, Remaining quota, Expiration date, Status, and Stop when used up switch of each model.

Method 2: From the Model Gallery page

1. In the console, go to the Model Gallery page, find the target model series, and click to open its details page.

2. Select a model version under Model Code and view the remaining quota in the Free Quota area. If no free quota is displayed, it may have expired. For the specific validity period, see the model list.

   362,917/1,000,000 indicates that 362,917 of 1,000,000 total tokens remain.

   The free quota displayed in the console is updated on a minute-by-minute basis (you must manually refresh the page).

Method 3: From the model usage page

• In the console, go to the Model Usage page to view the usage and remaining free quota of each model.

Use your free quota

Real-time invocations of large models automatically deduct the free quota. For more information, see Get started with Alibaba Cloud Model Studio.

Free Quota Only

Free Quota Only (called "worry-free mode" by some users). When this feature is enabled, the service stops responding and returns an HTTP 403 error with the error code AllocationQuota.FreeTierOnly once the free quota is exhausted, and no further charges are incurred.

This feature is disabled by default. To automatically stop the service when the free quota is exhausted to avoid unexpected charges, you can enable it in the console.

How to enable

Method 1: From the free quota page

Enable for a single model:

1. In the console, go to the Free Quota page.
2. Find the target model in the list and enable the Free Quota Only switch in the Actions column on the right (you cannot enable it for models without a free quota; after it is enabled, the switch shows the Enabled state).
3. If the Status column of the target model shows Enabling not supported, the model does not offer a free quota and you cannot enable this feature for it. You can enter the model name in the search box at the top of the page to quickly locate the model and view its status.

Enable in batches:

1. In the console, go to the Free Quota page.
2. Click Batch Settings and select Batch Enable from the drop-down menu.
3. Select the target models and click Batch Enable. To enable the feature for all supported models for which it is not enabled, click Enable All Models.
4. In the confirmation dialog box, click Enable Free Quota Only.

Method 2: From the Model Gallery page

Take qwen3.8-max as an example. Go to the qwen3.8-max model details page and enable the Free Quota Only switch.

If the switch is not displayed for a model, its free quota has been exhausted or has expired, or the model does not offer a free quota.

How to disable

After the feature is enabled, you can disable it at any time. You can turn off the Free Quota Only switch for a single model in the Actions column of the free quota page, or select Batch Disable from the batch operation drop-down menu.

The Model Studio mobile console does not currently support enabling or disabling this feature. Use a computer to access the console.

Enabling or disabling the configuration takes some time to take effect. Wait a moment before making invocations again. If you continue to make invocations while the configuration change is taking effect, the delay may cause charges even after the free quota is exhausted. You cannot enable this feature for a model whose free quota has been exhausted (see "How to enable" in this topic). In this case, to stop being charged, delete your API key (see "How do I avoid charges?" in this topic) or purchase a savings plan.

The Not enabled or Enabling not supported status displayed in the console is a protection status indication of Free Quota Only, not a feature malfunction, and no additional manual service enablement is required. After you turn off the switch, the status synchronization is delayed. Wait about 30 minutes and try again to resume pay-as-you-go invocations. This feature is not recommended for production environments, because the service may become unavailable once the quota is exhausted.

Removed free quotas

The free quotas of some models have been removed by the platform. After removal, new users will no longer receive a free quota for the model; quotas already issued to existing users remain available until they expire or are exhausted.

When new models are released, the platform will continue to grant free quotas for the new models.

List of models with free quotas removed

2026-10-29

• wan2.7-t2v
• wan3.0-video-prime
• wan2.7-i2v
• wan2.7-r2v
• wan2.7-videoedit
• wan2.2-dancer
• wan2.7-t2v-2026-04-25
• wan2.7-i2v-2026-04-25
• wan2.7-t2v-2026-06-12
• wan2.7-r2v-2026-06-12
• qwen3.5-omni-plus-realtime-2026-03-15
• qwen3.5-omni-flash-realtime
• qwen3.5-omni-flash-2026-03-15
• qwen3.5-omni-flash
• qwen3.5-omni-flash-realtime-2026-03-15
• qwen3.5-omni-plus-2026-03-15
• happyhorse-1.0-i2v
• happyhorse-1.0-t2v
• happyhorse-1.0-r2v
• happyhorse-1.5-t2v
• happyhorse-1.5-video-edit
• happyhorse-1.5-i2v
• happyhorse-1.5-r2v
• qwen3-asr-flash-realtime-2026-02-10
• qwen3-asr-flash-2026-02-10
• qwen3-tts-instruct-flash-realtime
• qwen3-tts-instruct-flash-realtime-2026-01-22
• qwen3-tts-instruct-flash
• qwen3-tts-instruct-flash-2026-01-26
• qwen3-tts-vc-2026-01-22
• qwen3-tts-vd-2026-01-26
• qwen-flash-character-2026-02-26
• qwen3.5-livetranslate-flash-realtime
• qwen3.5-livetranslate-flash-realtime-2026-05-19
• tongyi-embedding-vision-flash-2026-03-06
• tongyi-embedding-vision-plus-2026-03-06
• fun-asr-flash-8k-realtime-2026-01-28
• fun-asr-realtime-2026-02-28
• fun-music-preview
• qwen-audio-3.0-asr-flash
• qwen-audio-3.0-asr-flash-filetrans
• qwen-audio-3.0-asr-flash-streaming
• qwen-audio-3.0-realtime-flash
• qwen-audio-3.0-realtime-plus
• qwen-audio-3.0-tts-flash
• qwen-audio-3.0-tts-plus
• aitryon
• aitryon-parsing-v1
• aitryon-plus
• aitryon-refiner
• animate-anyone-detect-gen2
• animate-anyone-gen2
• animate-anyone-template-gen2
• avatar-dialog
• cosyvoice-clone-v1
• cosyvoice-v1
• cosyvoice-v2
• cosyvoice-v3
• cosyvoice-v3-flash
• cosyvoice-v3-plus
• deepseek-r1
• deepseek-r1-0528
• deepseek-r1-distill-qwen-14b
• deepseek-r1-distill-qwen-32b
• deepseek-r1-distill-qwen-7b
• deepseek-v3
• deepseek-v3.1
• deepseek-v3.2
• deepseek-v3.2-exp
• deepseek-v4-flash
• emo-detect-v1
• emo-v1
• emoji-detect-v1
• emoji-v1
• facechain-generation
• fun-asr-2025-08-25
• fun-asr-2025-11-07
• fun-asr-mtl
• fun-asr-mtl-2025-08-25
• fun-asr-mtl-realtime
• fun-asr-mtl-realtime-2025-12-10
• fun-asr-realtime-2025-09-15
• fun-asr-realtime-2025-11-07
• glm-4.5
• glm-4.5-air
• glm-4.6
• glm-4.7
• glm-5
• glm-5.1
• glm-5.2
• gte-rerank-v2
• gui-plus-2026-02-26
• gummy-chat-v1
• gummy-realtime-v1
• image-out-painting
• kimi-k2-thinking
• kimi-k2.5
• kimi-k2.6
• liveportrait
• liveportrait-detect
• MiniMax-M2.1
• Moonshot-Kimi-K2-Instruct
• multimodal-embedding-v1
• opennlu-v1
• paraformer-8k-lite-v1
• paraformer-8k-v1
• paraformer-mtl-v1
• paraformer-realtime-8k-v1
• paraformer-realtime-v1
• paraformer-v1
• qvq-72b-preview
• qvq-max
• qvq-max-2025-03-25
• qvq-max-2025-05-15
• qvq-max-latest
• qvq-plus
• qvq-plus-2025-05-15
• qvq-plus-latest
• qwen-coder-plus
• qwen-coder-plus-1106
• qwen-coder-plus-latest
• qwen-coder-turbo
• qwen-coder-turbo-0919
• qwen-coder-turbo-latest
• qwen-flash
• qwen-flash-2025-07-28
• qwen-image
• qwen-image-2.0
• qwen-image-2.0-2026-03-03
• qwen-image-2.0-pro
• qwen-image-2.0-pro-2026-03-03
• qwen-image-2.0-pro-2026-04-22
• qwen-image-2.0-pro-2026-06-22
• qwen-image-edit-max-2026-01-16
• qwen-image-edit-plus-2025-10-30
• qwen-image-edit-plus-2025-12-01
• qwen-image-edit-plus-2025-12-15
• qwen-image-max-2025-12-30
• qwen-image-plus-2026-01-09
• qwen-long
• qwen-long-2025-01-25
• qwen-long-latest
• qwen-math-plus
• qwen-math-plus-0816
• qwen-math-plus-0919
• qwen-math-plus-latest
• qwen-math-turbo
• qwen-math-turbo-0919
• qwen-math-turbo-latest
• qwen-max
• qwen-max-0403
• qwen-max-0428
• qwen-max-0919
• qwen-max-1201
• qwen-max-2025-01-25
• qwen-max-latest
• qwen-mt-turbo
• qwen-omni-turbo
• qwen-omni-turbo-2025-01-19
• qwen-omni-turbo-2025-03-26
• qwen-omni-turbo-latest
• qwen-omni-turbo-realtime
• qwen-omni-turbo-realtime-2025-05-08
• qwen-omni-turbo-realtime-latest
• qwen-plus
• qwen-plus-0112
• qwen-plus-0723
• qwen-plus-0806
• qwen-plus-0919
• qwen-plus-1125
• qwen-plus-1127
• qwen-plus-1220
• qwen-plus-2025-01-25
• qwen-plus-2025-04-28
• qwen-plus-2025-07-14
• qwen-plus-2025-07-28
• qwen-plus-2025-09-11
• qwen-plus-2025-12-01
• qwen-plus-latest
• qwen-tts
• qwen-tts-2025-04-10
• qwen-tts-2025-05-22
• qwen-tts-latest
• qwen-tts-realtime
• qwen-tts-realtime-2025-07-15
• qwen-tts-realtime-latest
• qwen-tts-vc-realtime-2025-08-20
• qwen-turbo
• qwen-turbo-0624
• qwen-turbo-0919
• qwen-turbo-1101
• qwen-turbo-2025-02-11
• qwen-turbo-2025-04-28
• qwen-turbo-2025-07-15
• qwen-turbo-latest
• qwen-vl-max
• qwen-vl-max-0809
• qwen-vl-max-1030
• qwen-vl-max-1119
• qwen-vl-max-1230
• qwen-vl-max-2025-01-25
• qwen-vl-max-2025-04-02
• qwen-vl-max-2025-04-08
• qwen-vl-max-2025-08-13
• qwen-vl-max-latest
• qwen-vl-ocr-1028
• qwen-vl-ocr-2025-04-13
• qwen-vl-ocr-2025-08-28
• qwen-vl-ocr-2025-11-20
• qwen-vl-ocr-latest
• qwen-vl-plus
• qwen-vl-plus-0102
• qwen-vl-plus-0809
• qwen-vl-plus-2025-01-25
• qwen-vl-plus-2025-05-07
• qwen-vl-plus-2025-08-15
• qwen-vl-plus-latest
• qwen-voice-design
• qwen1.5-110b-chat
• qwen1.5-14b-chat
• qwen1.5-32b-chat
• qwen1.5-72b-chat
• qwen1.5-7b-chat
• qwen2-57b-a14b-instruct
• qwen2-72b-instruct
• qwen2-7b-instruct
• qwen2-vl-72b-instruct
• qwen2.5-14b-instruct
• qwen2.5-14b-instruct-1m
• qwen2.5-32b-instruct
• qwen2.5-3b-instruct
• qwen2.5-72b-instruct
• qwen2.5-7b-instruct
• qwen2.5-7b-instruct-1m
• qwen2.5-coder-14b-instruct
• qwen2.5-coder-32b-instruct
• qwen2.5-coder-7b-instruct
• qwen2.5-math-72b-instruct
• qwen2.5-math-7b-instruct
• qwen2.5-omni-7b
• qwen2.5-vl-32b-instruct
• qwen2.5-vl-3b-instruct
• qwen2.5-vl-72b-instruct
• qwen2.5-vl-7b-instruct
• qwen2.5-vl-embedding
• qwen3-0.6b
• qwen3-1.7b
• qwen3-14b
• qwen3-235b-a22b
• qwen3-235b-a22b-instruct-2507
• qwen3-235b-a22b-thinking-2507
• qwen3-30b-a3b
• qwen3-30b-a3b-instruct-2507
• qwen3-30b-a3b-thinking-2507
• qwen3-32b
• qwen3-4b
• qwen3-8b
• qwen3-asr-flash-2025-09-08
• qwen3-asr-flash-filetrans-2025-11-17
• qwen3-asr-flash-realtime-2025-10-27
• qwen3-coder-30b-a3b-instruct
• qwen3-coder-480b-a35b-instruct
• qwen3-coder-flash
• qwen3-coder-flash-2025-07-28
• qwen3-coder-next
• qwen3-coder-plus
• qwen3-coder-plus-2025-07-22
• qwen3-coder-plus-2025-09-23
• qwen3-livetranslate-flash-2025-12-01
• qwen3-livetranslate-flash-realtime
• qwen3-livetranslate-flash-realtime-2025-09-22
• qwen3-max
• qwen3-max-2025-09-23
• qwen3-max-2025-10-30
• qwen3-max-2026-01-23
• qwen3-max-preview
• qwen3-next-80b-a3b-instruct
• qwen3-next-80b-a3b-thinking
• qwen3-omni-30b-a3b-captioner
• qwen3-omni-flash
• qwen3-omni-flash-2025-09-15
• qwen3-omni-flash-2025-12-01
• qwen3-omni-flash-realtime
• qwen3-omni-flash-realtime-2025-09-15
• qwen3-omni-flash-realtime-2025-12-01
• qwen3-tts-flash-2025-09-18
• qwen3-tts-flash-2025-11-27
• qwen3-tts-flash-realtime-2025-09-18
• qwen3-tts-flash-realtime-2025-11-27
• qwen3-tts-vc-realtime-2025-11-27
• qwen3-tts-vc-realtime-2026-01-15
• qwen3-tts-vd-realtime-2025-12-16
• qwen3-tts-vd-realtime-2026-01-15
• qwen3-vl-235b-a22b-instruct
• qwen3-vl-235b-a22b-thinking
• qwen3-vl-30b-a3b-instruct
• qwen3-vl-30b-a3b-thinking
• qwen3-vl-32b-instruct
• qwen3-vl-32b-thinking
• qwen3-vl-8b-instruct
• qwen3-vl-8b-thinking
• qwen3-vl-flash
• qwen3-vl-flash-2025-10-15
• qwen3-vl-flash-2026-01-22
• qwen3-vl-plus-2025-09-23
• qwen3-vl-plus-2025-12-19
• qwen3.5-122b-a10b
• qwen3.5-27b
• qwen3.5-35b-a3b
• qwen3.5-397b-a17b
• qwen3.5-flash
• qwen3.5-flash-2026-02-23
• qwen3.5-plus
• qwen3.5-plus-2026-02-15
• qwen3.5-plus-2026-04-20
• qwen3.6-27b
• qwen3.6-35b-a3b
• qwen3.6-flash
• qwen3.6-flash-2026-04-16
• qwen3.6-max-preview
• qwen3.6-plus
• qwen3.6-plus-2026-04-02
• qwen3.7-flash-2026-07-15
• qwen3.7-max-2026-05-17
• qwen3.7-max-2026-05-20
• qwen3.7-max-2026-06-08
• qwen3.7-max-preview
• qwen3.7-plus-2026-05-26
• qwq-32b
• qwq-32b-preview
• qwq-plus
• qwq-plus-2025-03-05
• qwq-plus-latest
• sensevoice-v1
• text-embedding-async-v1
• text-embedding-v1
• text-embedding-v2
• text-embedding-v3
• wan2.2-animate-mix
• wan2.2-animate-move
• wan2.2-i2v-flash
• wan2.2-i2v-plus
• wan2.2-kf2v-flash
• wan2.2-s2v
• wan2.2-s2v-detect
• wan2.2-t2i-flash
• wan2.2-t2i-plus
• wan2.2-t2v-flash
• wan2.2-t2v-plus
• wan2.5-i2i-preview
• wan2.5-i2v-preview
• wan2.5-t2i-preview
• wan2.5-t2v-preview
• wan2.6-i2v
• wan2.6-i2v-flash
• wan2.6-image
• wan2.6-r2v
• wan2.6-r2v-flash
• wan2.6-t2i
• wan2.6-t2v
• wanx-background-generation-v2
• wanx-v1
• wanx2.0-t2i-turbo
• wanx2.1-i2v-plus
• wanx2.1-i2v-turbo
• wanx2.1-imageedit
• wanx2.1-kf2v-plus
• wanx2.1-t2i-plus
• wanx2.1-t2i-turbo
• wanx2.1-t2v-plus
• wanx2.1-t2v-turbo
• wanx2.1-vace-plus
• wordart-semantic
• wordart-texture
• qwen-image-edit
• qwen-image-edit-max
• qwen-image-edit-plus
• qwen-image-max
• qwen-image-plus

FAQ

Will I be notified when my free quota is about to run out or has run out?

Yes. When the remaining quota drops to 20% or is fully exhausted, the system sends notifications through SMS, in-site messages, and email.

To enable or disable alerts, or to change the alert threshold, go to My Trials for configuration. Find the trial with the description Model Studio Large Model Inference Free Trial, click View Trial Details, and then configure the remaining quota expiry alert rule to make changes.

Does an exhausted free quota mean I have not purchased the model?

No. The free quota is a new user-exclusive benefit automatically granted by the system when you activate Alibaba Cloud Model Studio for the first time. You do not need to manually claim it or purchase any product, and it is unrelated to whether you have purchased the model. Each model (including different snapshot versions of the same model) has its own independent free quota. Therefore, an exhausted quota for a model only means that the granted tokens for that model have been used up, and does not mean that you do not have permission to call the model.

Whether you can continue to make invocations after the quota is exhausted depends on whether Free Quota Only is enabled. For details, see "What happens when my free quota runs out?" in this topic.

What happens when my free quota runs out?

• If you have enabled Free Quota Only, you cannot continue to make invocations after the free quota is exhausted. You must disable Free Quota Only to continue on a pay-as-you-go basis.
• If you have not enabled Free Quota Only, ongoing invocations are not interrupted. Tokens exceeding the quota are billed at the input/output prices in the console, and the charges are deducted from your Alibaba Cloud account on a pay-as-you-go basis, which may result in an overdue balance.

Overdue-payment restrictions are isolated by commodity code. When one commodity code has an overdue payment, the services under that commodity code become unavailable, and you cannot make invocations even if the model still has a free quota. Services are restored after you settle the overdue amount. Services under other commodity codes are not affected. You can query the commodity code in your bill.

Before making an invocation, we recommend that you check the remaining quota of the model and configure budget management or account balance alerts to ensure that your account has a sufficient balance. Unused balances support balance withdrawal.

How do I add funds after my free quota runs out?

Alibaba Cloud supports various top-up methods such as Alipay, UnionPay online payment, and online banking. The methods available to you are displayed on the account top-up page. For more information, see Top-up methods.

After the top-up is complete, the account balance may take a few minutes to update. Check your available balance later on the Billing & Costs page. Once the balance arrives and there is no overdue payment, you can call models normally.

How do I view free quota usage records or bills?

Usage records are generated within a few minutes after an invocation is complete. To query the records:

1. On the Billing Details page, select the billing month, select Model Studio for Product Name, and click Search.
2. Click the icon in the upper-right corner of the bill list, find Usage Information, select Usage, and click OK.
3. Find the bill item where the Cost Type is Free Quota. The Usage is the usage that has been covered by your free quota.

Why am I being charged?

Common reasons:

• The model you used no longer has a free quota.
• The free quota does not cover charges generated by OpenAI-compatible Batch (file input).
• The free quota data in the console is updated on a minute-by-minute basis and requires a manual page refresh. If the page is not refreshed in time, it may display a remaining quota when the quota has actually been exhausted, resulting in invocation charges. Refresh the page before operations and rely on the latest display.
• Auto-completion in IDE plugins consumes tokens rapidly. When you call models through IDE plugins such as Cline or CodeBuddy, the plugin automatically sends the full code context and conversation history, and a single conversation may consume thousands of tokens, far more than a typical short conversation.

You can confirm the charge details through How do I identify which model incurred charges? and How do I view model invocation records?.

Large models are billed based on the tokens actually consumed. As long as an invocation is made, quota is consumed regardless of whether the output contains hallucinations or factual errors, and used quota or fees cannot be restored or refunded due to output quality issues. Pay-as-you-go charges incurred after the free trial ends or the quota is exhausted are normal usage and cannot be reversed. We recommend enabling the Free Quota Only feature to prevent unexpected charges.

How do I identify which model incurred charges?

Within a few minutes after an invocation is complete, go to the Billing Details page, select the billing month, select Alibaba Cloud Model Studio Large Model Inference for Commodity Name, and click Search. View the models that incurred charges in the Asset/Resource Instance ID (billing granularity) column.

How do I view model invocation records?

Model invocations can be viewed in monitoring charts at the minute-level after they occur. Log on to the model monitoring page (Beijing or Singapore), select Operations > Model Monitoring in the left-side navigation pane to enter the monitoring overview page, set the query conditions (for example, select the time range and business space), then find the target model in the Model List area and click View Details to view the invocation statistics of the model. For more information, see the Monitoring and alerting document.

Monitoring data is updated on a minute-by-minute basis and is for reference only. It is not used as a billing basis.

How do I avoid charges?

After the free quota is exceeded, charges are automatically deducted from the account balance. You can reduce the risk of charges in the following ways:

• Delete created API keys: Go to the API Key (Beijing) or API Key (Singapore) page of Alibaba Cloud Model Studio and delete the created API keys. After deletion, models can no longer be called through the API, and no further invocation charges are incurred.

• Set up a high-spending alert: When a product's daily bill exceeds the alert threshold, you receive one SMS reminder per day (based on statistics as of 24:00 on the previous day).

  From the Alert Product drop-down list, select a specific product (such as Model Studio Model Deployment, Model Studio Large Model Inference, or Model Studio Model Training), enter an amount in the Alert Threshold input box (such as 0.01), and then click Add to add the alert rule.

Why do invocations fail when I still have remaining quota?

Check whether your Alibaba Cloud account has an overdue payment. Overdue-payment restrictions are isolated by commodity code. When one commodity code has an overdue payment, the services under that commodity code become unavailable, and you cannot make invocations even if the model still has a free quota. Services are restored after you settle the overdue amount. You can query the commodity code in your bill.

Why can't I see the free quota or validity period?

The Free Quota column shows No free quota or the Free Quota area is not displayed. This may be caused by one of the following reasons:

• The free quota has expired or been exhausted: The free quota is valid for 90 days, starting from the date you activate Alibaba Cloud Model Studio, the model is released, or your model request is approved (whichever is later). After the quota expires or is exhausted, it is no longer displayed, and continued model invocations will incur charges.
• The region or service deployment scope of the model does not offer a free quota: Only models in the China (Beijing) region are eligible for the free quota. Models in other regions and deployment scopes do not have a free quota.
• The model itself does not offer a free quota: Some models do not participate in the new user free quota program. To determine whether a model is eligible for a free quota, go to Model Gallery in the console and open the model details page to check whether the free quota area shows a remaining amount (see "Check your remaining quota > Method 2: From the Model Gallery page" in this topic). Models whose details page does not display a free quota are not eligible.

Which API key can consume the free quota?

An API key is not bound to a specific model. The same API key can call all models, and you do not need to create a separate API key to use the free quota.

During real-time invocations, the system automatically prioritizes the free quota for deduction, and no manual configuration is required. The deduction priority is: free quota > resource plan > savings plan > pay-as-you-go.

Token Plan/Coding Plan dedicated API keys do not consume the free quota. Invocations with a dedicated API key are billed directly on a pay-as-you-go basis. To use the free quota, use a general-purpose API key (not a dedicated API key) instead.

Why is the OAuth authentication free quota not displayed in the console?

OAuth authentication provides an independent free quota (2,000 calls per day), which is independent of the API key free quota system of the Model Studio console.

The free quota page in the console displays only the token quota of API keys, and does not display OAuth authentication call records or free quota consumption. The absence of related records on the page does not mean that the OAuth authentication free quota is invalid.

To view OAuth authentication call records, log on to the Model Studio console and choose Operations > Model Monitoring in the left-side navigation pane.

Why do I get a 400 error when calling image/video generation models with a Token Plan dedicated API key?

Image/video generation models (such as the wanx series and multimodal generation models like qwen-vl-max-latest) do not support direct calls through text generation Base URLs. If you use a Token Plan team edition dedicated API key to directly request such models through the text Base URL (https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1), an HTTP 400 error is returned.

Solution: Access multimodal generation models through the Skill or extension mechanism in Model Studio applications instead of calling them directly in a text conversation manner.

What is the relationship between the new user free quota and savings plans?

The new user free quota and savings plans are independent of each other. Purchasing a savings plan does not grant additional free quota. Each model has an independent free quota (typically 1,000,000 tokens) that cannot be merged or transferred across models.

Is it normal for large model invocations to be slow or delayed?

Yes. Response latency is affected by network conditions and model inference time, and is unrelated to whether the free quota is used.