Free quota

​

Rules

​

Validity period

Free quota is typically valid for 90 days, but the start date depends on the quota type:

• New user free quota: When you activate your account, all existing models receive a free quota. The 90-day period starts from your account activation date.
• New model free quota: For models released after you sign up, the 90-day period starts from the model's release date.

After expiration or depletion, continued model inference will incur charges. Once your free quota expires, it becomes invalid immediately, regardless of whether it has been fully used:

• The countdown is not paused by inactivity — unused quota still expires when the validity period ends.
• After expiration, any remaining quota is void and will not be reissued or extended.
• Signing up for a new account does not grant an additional free quota.

​

Scope of application

Free quota only offsets costs from real-time model inference (invocation). It does not offset:

• Batch calls
• Built-in tool call fees (web search, image search, etc.)
• Model fine-tuning
• Model deployment
• Custom models (fine-tuned models, deployed models)

​

Applicable region

Free quota is available only in the Singapore region. It offsets only real-time calls to models in Singapore, made with an API key created in Singapore and sent to the Singapore endpoint. Calls in other regions are billed on a pay-as-you-go basis from the first token. Switching regions in the console does not grant a new free quota. See Regions and endpoints.

​

Per-model quota

Free quota is independent for each model and cannot be shared or transferred across models:

• Each model (for example, qwen-plus or qwen3.6-plus) has its own free quota, typically 1,000,000 tokens. Quota cannot be merged or transferred between models.
• A dated snapshot (for example, qwen3.6-plus-2026-04-02) and the latest version without a date suffix (for example, qwen3.6-plus) are treated as separate models, each with its own free quota.
• When one model's free quota is exhausted, requests are not automatically routed to another model that still has quota. You must manually change the model parameter in your code or tool configuration.

​

Get the free quota

Sign up for QwenCloud and complete your payment information to activate your free quota. Once your information is verified, you can try models immediately. After your free quota is exhausted, you continue on a pay-as-you-go basis.

​

View your remaining quota

Free quota is shown for the Singapore region. Make sure Singapore is selected in the region selector in the upper-right corner of the console, then go to the Free Tier page to view and manage your free quota across all models. You can also open it from the console home page: in the Benefits card, click View Benefits. The page has two tabs, Model Invocation Quota and Coupon. The Model Invocation Quota tab provides:

• Eligible models: Number of models with available free quota
• Models expiring soon: Models with quota expiring within 7 days
• Low balance models: Models with 80% or more of quota consumed
• Unavailable models: Models with free quota expired or exhausted (data from past 180 days)

Filter by Task Type (Multimodal, Text & Code, Image, Video, Audio, Embedding, Reranking), Status, or search by model name. The table shows:

• Model Code, Free Quota, Consumed, Remaining, Expiration, Status
• Toggle Free quota only switch in the Actions column to enable auto-stop when quota ends

If the console is set to a region other than Singapore, the Free Tier page shows "No free quota is available for the current region and service mode. Please switch to Singapore to view and use your free quota." with Singapore listed. Click Switch to view the page in Singapore. The states described above apply in Singapore: the table shows models with available quota, quota expiring soon, low balance, and expired or used-up quota.

​

Use the free quota

When you make real-time calls to a model, free quota is automatically deducted. For more information, see Get started with QwenCloud. You do not need a separate API key for free quota: the same pay-as-you-go API key calls all models, and free quota is deducted before pay-as-you-go charges. Token Plan API keys (sk-sp-) do not consume free quota.

​

Free quota only

When Free quota only is enabled, model calls are blocked after quota exhaustion and no charges are incurred. Free quota only is disabled by default. You can enable or disable it on the Free Tier page.

​

How to enable

Go to the Free Tier page:

• Single model: Toggle on the Free quota only switch for the target model
• All models: Click Enable all models at the top-right of the table
• Selected models: Check the desired models (or use the Select all on page checkbox in the table header), then click Enable selected in the bottom action bar that appears; you can also click Select all to select all models across pages

If the switch is not displayed for a model, it means the free quota for that model has been exhausted or has expired, or the model does not offer a free quota. If the switch is disabled (greyed out) for a model, it means the model's free quota has been exhausted or expired, or the model does not offer a free quota. You can check the Status column or search for a model by name to quickly locate it.

​

How to disable

If enabled, you can disable it on the Free Tier page by toggling off the switch for a single model, clicking Disable all models at the top-right, or selecting models and clicking Disable selected in the bottom action bar.

​

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
• wan2.7-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
• 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
• qwen3.5-livetranslate-flash-realtime
• qwen3.5-livetranslate-flash-realtime-2026-05-19
• 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
• deepseek-v3.2
• deepseek-v4-flash
• fun-asr-2025-08-25
• fun-asr-2025-11-07
• fun-asr-mtl
• fun-asr-mtl-2025-08-25
• fun-asr-realtime-2025-11-07
• glm-5.1
• glm-5.2
• qvq-max
• qvq-max-2025-03-25
• qvq-max-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
• qwen-image-edit-max
• qwen-image-edit-max-2026-01-16
• qwen-image-edit-plus
• qwen-image-edit-plus-2025-10-30
• qwen-image-edit-plus-2025-12-15
• qwen-image-max
• qwen-image-max-2025-12-30
• qwen-image-plus
• qwen-image-plus-2026-01-09
• qwen-max
• qwen-max-2025-01-25
• qwen-mt-turbo
• qwen-omni-turbo
• qwen-omni-turbo-2025-03-26
• qwen-omni-turbo-realtime
• qwen-omni-turbo-realtime-2025-05-08
• qwen-plus
• 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-turbo
• qwen-turbo-2025-04-28
• qwen-turbo-latest
• qwen-vl-max
• qwen-vl-max-2025-04-08
• qwen-vl-max-2025-08-13
• qwen-vl-max-latest
• qwen-vl-ocr-2025-11-20
• qwen-vl-plus
• 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
• qwen2.5-14b-instruct
• qwen2.5-14b-instruct-1m
• qwen2.5-32b-instruct
• qwen2.5-72b-instruct
• qwen2.5-7b-instruct
• qwen2.5-7b-instruct-1m
• qwen2.5-omni-7b
• qwen2.5-vl-32b-instruct
• qwen2.5-vl-3b-instruct
• qwen2.5-vl-72b-instruct
• qwen2.5-vl-7b-instruct
• 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-plus
• 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-t2i-flash
• wan2.2-t2i-plus
• 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

​

FAQ

​

Will I be notified when my free quota is running low or used up?

Yes. When your remaining quota drops to 20% or is fully exhausted, the system sends notifications through internal messages and email.

​

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

No. The free quota is a new user benefit that the platform grants automatically the first time you activate QwenCloud. It is unrelated to whether you purchased the model: you do not need to manually claim it or purchase any product. Each model has its own independent free quota, and a snapshot version with a date suffix and the latest version without one are treated as two independent models. An exhausted quota for one model therefore means only that this model's free tokens are used up. It does not mean that you lack permission to call that model. Whether you can continue making invocations after the free quota is exhausted depends on your account verification status and on whether Free quota only is enabled. For details, see What happens when my free quota is used up? below.

​

What happens when my free quota is used up?

If you have completed payment verification (the standard case):

• If Free quota only is enabled, model calls are blocked after free quota is used up. Disable this feature to switch to pay-as-you-go billing.
• If Free quota only is not enabled, model calls in progress complete without interruption. Tokens exceeding free quota are billed based on input/output costs in Model invocation pricing. Charges are automatically deducted on a pay-as-you-go basis, which may result in overdue payment.

If you opened your account before completing payment verification, you cannot continue calling models after free quota is used up. Click Set up payment on the Free Tier page to complete verification and switch to pay-as-you-go billing. Overdue-payment restrictions are isolated by commodity code. When a commodity code has an overdue payment, its services stop after the grace period and you cannot call those models even if they still have free quota. Services under other commodity codes are not affected. See Overdue payments. Before calling a model, check its free quota and set a spending alert.

​

Why was I charged?

Possible reasons:

• You used a model without free quota.
• The free quota cannot be used to offset costs from Batch calls.
• 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. As a result, a single exchange can consume thousands of tokens. In a test, a request that carried about 2,000 characters of code context consumed 1,758 tokens, whereas a short message consumed only 26 tokens — a 67-fold difference.
• Free quota data is subject to a delay of several minutes. The display might show remaining quota when it's actually exhausted, resulting in charges. Check status again later for latest data.

You can confirm the charge details on the Pay-as-you-go page.

​

How do I avoid charges?

Once you have completed payment verification, charges are automatically deducted from your payment method after free quota is exhausted. To manage charge risk:

• Delete API keys: Go to the QwenCloud API-Key page and delete created API keys. After you delete an API key, you can no longer call models using the API, which prevents further charges.
• Set spending alert: Configure a spending alert. You'll receive email notifications when spending reaches the alert threshold.

If you opened your account before completing payment verification, your usage stops automatically when free quota is exhausted — no charges are incurred.

​

I have a remaining quota, so why did my call fail?

Your account may have an overdue payment. Overdue-payment restrictions are isolated by commodity code: after the grace period expires, calls to services under the overdue commodity code are blocked, even if you have remaining free quota. See Overdue payment protection for details.

​

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

If the Free Quota column shows No free quota or the section is not displayed, one of the following applies:

• Free quota has expired or been exhausted: Free quota is valid for 90 days from activation or model release (see Validity period). Once it expires or is used up, it's no longer displayed, and further calls are billed as pay-as-you-go.
• The model does not offer a free quota: Some models do not participate in the free quota program.
• The console is set to another region: Free quota is available only in Singapore. Switch to Singapore in the region selector in the upper-right corner of the console.