Rate limiting - Alibaba Cloud Model Studio

Rate limiting rules

Account-level rate limiting: Rate limits are applied at the root account level. The usage of all RAM users, workspaces, and API keys under the account is combined.
Model-specific rate limiting: Each model has its own rate limit. For more information, see the tables below.

FAQ

Why is rate limiting triggered?

You can identify the type of rate limit triggered based on the error message:

Requests rate limit exceeded or You exceeded your current requests list: This indicates that the requests per minute (RPM) limit was triggered.
Allocated quota exceeded or You exceeded your current quota: This indicates that the tokens per minute (TPM) limit was triggered.
Request rate increased too quickly: The request frequency surged in a short period, triggering system stability protection. This can occur even if the total number of calls has not reached the RPM or TPM limits.
For other errors, see Error codes to confirm the cause.

In addition to RPM and TPM, rate limiting may be enforced at the per-second level for requests per second (RPS), which is RPM/60, and tokens per second (TPS), which is TPM/60. Even if the total number of calls per minute does not exceed the limit, a burst of requests in a short time can still trigger rate limiting.

How to view model usage

One hour after you call a model, go to the Monitoring (Singapore or Beijing) page. Set the query conditions, such as the time range and workspace. Then, in the Models area, find the target model and click Monitor in the Actions column to view the model's call statistics. For more information, see the Monitoring document.

Data is updated hourly. During peak periods, there may be an hour-level latency.

How long does it take to recover from rate limiting?

Recovery usually occurs within one minute. If other errors occur, see Error codes for troubleshooting. Model response speed is not related to whether you use free quota or paid calls. Free quota and paid calls use the same model service infrastructure, so the generation speed for a given model is the same. Free quota only controls whether a request is accepted: once the free quota is exhausted, the request is rejected with a 403 error (if you have enabled stop when the free quota is used up). This does not reduce the generation speed of any request that has already been accepted.

What factors affect model response speed?

Model type: lightweight models (such as qwen-flash) generate responses faster than larger models (such as qwen-max).
Output length: the more tokens a response contains, the longer the total generation time.
Server load: response speed may fluctuate slightly during peak periods.

Does rate limiting reduce the generation speed of accepted requests?

No. Rate limiting (RPM/TPM) only rejects requests that exceed the limit, returning a 429 error. When the free quota is exhausted (if you have enabled stop when the free quota is used up), requests are rejected with a 403 error. Neither case affects the generation speed of requests that have already been accepted: 429 indicates rate limiting, and 403 indicates quota exhaustion — both are rejection mechanisms, not speed throttling.

How to avoid rate limiting

Choose models with higher rate limits: Stable or latest versions have higher rate limits than dated snapshot versions.
Optimize your call strategy
- Reduce call frequency: If you receive a Requests rate limit exceeded or You exceeded your current requests list error, lower the API call frequency.
- Reduce token consumption: If you receive an Allocated quota exceeded or You exceeded your current quota error, shorten the input or limit the output length.
- Smooth the request rate: If you receive a Request rate increased too quickly error, use uniform scheduling, exponential backoff, or a request queue to distribute requests evenly and avoid sudden peaks.

Add a backup model If rate limiting is triggered, you can switch to a backup model to continue generation. This can reduce the probability of failure and increase throughput. The following code automatically retries with qwen-plus-2025-07-14 after a rate limit is triggered for qwen-plus-2025-07-28. You can also choose a model from a different series (such as qwen-flash) as the backup model to further reduce the risk that the primary and backup models are rate limited at the same time.

Sample code

import os
import asyncio
from openai import AsyncOpenAI, APIStatusError

# Configuration
API_KEY = os.getenv("DASHSCOPE_API_KEY")
# Primary model
MODEL = "qwen-plus-2025-07-28"
# Backup model
BACKUP_MODEL = "qwen-plus-2025-07-14"
# Test question
QUESTION = "Who are you?"
# Concurrency setting
NUM_REQUESTS = 10

client = AsyncOpenAI(
    api_key=API_KEY,
    # When calling, replace {WorkspaceId} with your actual workspace ID.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

async def send_request(model):
    """Sends a single request."""
    try:
        await client.chat.completions.create(
            model=model,
            messages=[{"role": "user", "content": QUESTION}]
        )
        return True
    except APIStatusError as e:
        if e.status_code == 429:
            print(f"[Rate limit triggered] Model {model}")
            return False
        raise
    except Exception as e:
        print(f"[Request failed] Model {model}, Error: {e}")
        return False

async def task(i):
    # Try the primary model.
    if await send_request(MODEL):
        return True
    # If rate limited, try the backup model.
    return await send_request(BACKUP_MODEL)

async def main():
    results = await asyncio.gather(*(task(i) for i in range(NUM_REQUESTS)))
    print(f"Successful requests: {sum(results)}, Failed requests: {len(results) - sum(results)}")

if __name__ == "__main__":
    asyncio.run(main())

Split tasks: Long conversations or large documents can consume many tokens quickly. You can split large batch tasks into smaller batches and submit them at different times.
Use batch inference: For tasks that do not require real-time responses, you can use the Batch API. Batch requests are not subject to real-time rate limits, but you must consider queuing and processing time.
Increase rate limits: If the default rate limits are insufficient, you can increase the temporary TPM quota for a model on the Increase Rate Limits page in the Model Studio console. The increase takes effect immediately. For more information, see Increase temporary rate limits.

How to control token usage or costs

Rate limiting only restricts the request rate per unit of time; it does not cap cumulative usage. To control token usage or costs, use the following methods:

Set a spending limit and cost alerts: On the Billing card, configure Cost alerts to enable a monthly spending limit and threshold notifications. You are notified when the threshold is reached, which helps you avoid overspending. For more information, see Query bills and manage costs.
Enable stop when the free quota is used up: For models that offer a free quota, you can enable stop when the free quota is used up so that calls stop automatically once the free quota is exhausted, which prevents additional charges. For more information, see Free quota.
Monitor model usage: Regularly check the token usage of each model to detect abnormal growth in time. See How to view model usage above.

Will I still be rate limited after I top up my account?

Topping up your account does not change the default RPM and TPM rate limits of a model. Rate limits are configured at the Alibaba Cloud account level and are independent of billing. Topping up (pay-as-you-go) only ensures that your account is not suspended for overdue payments; it does not raise your rate limits. To obtain higher rate limits, see the How to avoid rate limiting section in this topic, or apply for an increase on the Increase Rate Limits page in the Model Studio console. For more information, see Increase temporary rate limits.

Increase temporary rate limits

If the default rate limits are insufficient, you can increase a model's temporary TPM quota in the Model Studio console. The increase takes effect immediately and is valid for 30 days. After it expires, the quota automatically reverts to the system default. This feature is currently available in the China (Beijing) and Singapore regions.

Log on to the Model Studio console and go to the Increase Rate Limits page.
Click Increase Temporary Rate Limit in the upper-right corner.
In the dialog box that appears, select a Model and enter the desired value for Token Account Limit (Token/60 seconds). The dialog box displays the current quota and the maximum configurable limit.
Click Confirm. The increased quota takes effect immediately.

After the quota increase takes effect, you can confirm it in the following ways:

On the Increase Rate Limits page, view the models with increased quotas and their corresponding rate limit data in the list.
In the Model List, go to the details page of the corresponding model to view the updated rate limit data.

The models for which you can temporarily increase quotas are listed in the dialog box on the Increase Rate Limits page.
Submitting another request for a model that already has an increased quota is considered a new application, and the validity period is reset to 30 days.
Request a quota based on your actual needs. If the provisioned capacity significantly exceeds actual usage for a long time, the system may restore it to the default value after prior notification.
If the available rate limit quota still does not meet your needs, contact your account manager to request a further increase.

Text generation - Qwen

Qwen language model

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.8-max	International	15,000	2,000,000
qwen3.8-flash	International	15,000	2,000,000
qwen3.7-max	International	600	1,000,000
qwen3.7-max-2026-06-08	International	60	1,000,000
qwen3.7-max-2026-05-20	International	60	1,000,000
qwen3.7-max-preview	International	600	1,000,000
qwen3.7-max-2026-05-17	International	600	1,000,000
qwen3.6-max-preview	International	600	1,000,000
qwen3-max	International	600	1,000,000
qwen3-max-2026-01-23	International	600	1,000,000
qwen3-max-2025-09-23	International	60	100,000
qwen3-max-preview	International	600	1,000,000
qwen-max Rate limiting does not apply to service calls made using the Batch API.	International	600	1,000,000
qwen3.7-plus	International	15,000	5,000,000
qwen3.7-plus-2026-05-26	International	60	1,000,000
qwen3.6-plus	International	15,000	5,000,000
qwen3.6-plus-2026-04-02	International	60	1,000,000
qwen3.7-flash	International	15,000	5,000,000
qwen3.7-flash-2026-07-15	International	15,000	5,000,000
qwen3.6-flash	International	15,000	5,000,000
qwen3.6-flash-2026-04-16	International	60	1,000,000
qwen3.5-plus	International	15,000	5,000,000
qwen3.5-plus-2026-04-20	International	600	1,000,000
qwen3.5-plus-2026-02-15	International	60	1,000,000
qwen-plus Rate limiting does not apply to service calls made using the Batch API.	International	600	1,000,000
qwen-plus-latest	International	600	1,000,000
qwen-plus-2025-12-01	International	120	1,000,000
qwen-plus-2025-09-11	International	120	1,000,000
qwen-plus-2025-07-28	International	60	100,000
qwen-plus-2025-07-14(qwen-plus-0714)	International	60	100,000
qwen-plus-2025-04-28(qwen-plus-0428)	International	60	1,000,000
qwen-plus-2025-01-25(qwen-plus-0125)	International	60	100,000
qwen3.5-flash	International	15,000	5,000,000
qwen3.5-flash-2026-02-23	International	60	1,000,000
qwen-flash Rate limiting does not apply to service calls made using the Batch API.	International	600	5,000,000
qwen-flash-2025-07-28	International	600	5,000,000
qwq-plus	International	60	100,000
qwen-turbo Rate limiting does not apply to service calls made using the Batch API.	International	600	5,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.8-max	Global	30,000	5,000,000
qwen3.8-flash	Global	30,000	5,000,000
qwen3.7-max	Global	30,000	5,000,000
qwen3.7-max-us	US	600	1,000,000
qwen3.7-max-2026-06-08	Global	600	1,000,000
qwen3.7-max-2026-05-20	Global	600	1,000,000
qwen3-max	Global	600	1,000,000
qwen3-max-preview	Global	600	1,000,000
qwen3-max-2025-09-23	Global	60	100,000
qwen3.7-plus	Global	30,000	5,000,000
qwen3.7-plus-us	US	15,000	5,000,000
qwen3.7-plus-2026-05-26	Global	600	1,000,000
qwen3.6-plus	Global	30,000	5,000,000
qwen3.6-plus-2026-04-02	Global	600	1,000,000
qwen3.7-flash	Global	15,000	5,000,000
qwen3.7-flash-2026-07-15	Global	60	1,000,000
qwen3.6-flash	Global	15,000	5,000,000
qwen3.6-flash-2026-04-16	Global	60	1,000,000
qwen3.6-flash-us	US	15,000	5,000,000
qwen3.5-plus	Global	30,000	5,000,000
qwen3.5-plus-2026-02-15	Global	600	1,000,000
qwen-plus	Global	15,000	5,000,000
qwen-plus-us	US	600	1,000,000
qwen-plus-2025-12-01	Global	60	1,000,000
qwen-plus-2025-09-11	Global	60	1,000,000
qwen-plus-2025-07-28	Global	60	1,000,000
qwen-plus-2025-12-01-us	US	60	1,000,000
qwen3.5-flash	Global	30,000	10,000,000
qwen3.5-flash-2026-02-23	Global	600	1,000,000
qwen-flash	Global	15,000	10,000,000
qwen-flash-us	US	600	5,000,000
qwen-flash-2025-07-28	Global	60	1,000,000
qwen-flash-2025-07-28-us	US	600	5,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3.8-max Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen3.8-flash Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen3.7-max Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen3.7-max-2026-06-08	600	1,000,000
qwen3.7-max-2026-05-20	600	1,000,000
qwen3.6-max-preview	600	1,000,000
qwen3-max Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen3-max-2026-01-23	600	1,000,000
qwen3-max-2025-09-23	60	100,000
qwen3-max-preview	600	1,000,000
qwen-max Rate limiting does not apply to service calls made using the Batch API.	1,200	1,000,000
qwen3.7-plus	30,000	5,000,000
qwen3.7-plus-2026-05-26	600	1,000,000
qwen3.6-plus Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen3.6-plus-2026-04-02	600	1,000,000
qwen3.7-flash Rate limiting does not apply when calling the service with the Batch API.	30,000	5,000,000
qwen3.7-flash-2026-07-15	30,000	5,000,000
qwen3.6-flash Rate limiting does not apply to service calls made using the Batch API.	30,000	10,000,000
qwen3.6-flash-2026-04-16	600	1,000,000
qwen3.5-plus Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen3.5-plus-2026-04-20	600	1,000,000
qwen3.5-plus-2026-02-15	600	1,000,000
qwen-plus Rate limiting does not apply to service calls made using the Batch API.	30,000	5,000,000
qwen-plus-latest Rate limiting does not apply to service calls made using the Batch API.	15,000	1,200,000
qwen-plus-2025-12-01	120	1,000,000
qwen-plus-2025-09-11	60	1,000,000
qwen-plus-2025-07-28(qwen-plus-0728)	60	1,000,000
qwen-plus-2025-07-14(qwen-plus-0714)	60	100,000
qwen-plus-2025-04-28(qwen-plus-0428)	60	1,000,000
qwen-plus-2025-01-25(qwen-plus-0125)	60	150,000
qwen-plus-2025-01-12(qwen-plus-0112)	60	150,000
qwen-plus-2024-12-20(qwen-plus-1220)	60	150,000
qwen3.5-flash Rate limiting does not apply to service calls made using the Batch API.	30,000	10,000,000
qwen3.5-flash-2026-02-23	600	1,000,000
qwen-flash Rate limiting does not apply to service calls made using the Batch API.	30,000	10,000,000
qwen-flash-2025-07-28	60	1,000,000
qwq-plus Rate limiting does not apply to service calls made using the Batch API.	600	1,000,000
qwen-turbo	1,200	5,000,000
qwen-long-latest Rate limiting does not apply to service calls made using the Batch API.	1,200	60,000
qwen-long-2025-01-25(qwen-long-0125)	3	7,500

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.8-max	Global	30,000	5,000,000
qwen3.8-flash	Global	30,000	5,000,000
qwen3.7-max	Global	30,000	5,000,000
qwen3.7-max-2026-06-08	Global	600	1,000,000
qwen3.7-max-2026-05-20	Global	600	1,000,000
qwen3-max	Global	600	1,000,000
qwen3-max	EU	600	1,000,000
qwen3-max-preview	Global	600	1,000,000
qwen3-max-2026-01-23	EU	60	100,000
qwen3-max-2025-09-23	Global	60	100,000
qwen3.7-plus	Global	30,000	5,000,000
qwen3.7-plus-2026-05-26	Global	600	1,000,000
qwen3.6-plus	Global	30,000	5,000,000
qwen3.6-plus-2026-04-02	Global	600	1,000,000
qwen3.7-flash	Global	15,000	5,000,000
qwen3.7-flash-2026-07-15	Global	15,000	5,000,000
qwen3.6-flash	Global	15,000	5,000,000
qwen3.6-flash-2026-04-16	Global	60	1,000,000
qwen3.5-plus	Global	30,000	5,000,000
qwen3.5-plus-2026-02-15	Global	600	1,000,000
qwen-plus	Global	600	1,000,000
qwen-plus	EU	600	1,000,000
qwen-plus-2025-12-01	Global	120	1,000,000
qwen-plus-2025-12-01	EU	120	1,000,000
qwen-plus-2025-09-11	Global	60	1,000,000
qwen-plus-2025-07-28	Global	60	1,000,000
qwen3.5-flash	Global	35,000	10,000,000
qwen3.5-flash	EU	35,000	10,000,000
qwen3.5-flash-2026-02-23	Global	600	1,000,000
qwen3.5-flash-2026-02-23	EU	600	1,000,000
qwen-flash	Global	30,000	10,000,000
qwen-flash-2025-07-28	Global	60	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.8-max	Hong Kong (China)	600	1,000,000
qwen3.8-flash	Global	30,000	5,000,000
qwen3-max	Hong Kong (China)	600	1,000,000
qwen3-max-2026-01-23	Hong Kong (China)	60	100,000
qwen3.6-plus	Global	30,000	5,000,000
qwen3.7-flash	Global	15,000	5,000,000
qwen3.7-flash-2026-07-15	Global	15,000	5,000,000
qwen3.6-flash	Global	30,000	10,000,000
qwen-plus	Hong Kong (China)	600	1,000,000
qwen-plus-2025-12-01	Hong Kong (China)	60	100,000
qwen3.5-flash	Hong Kong (China)	30,000	10,000,000
qwen3.5-flash-2026-02-23	Hong Kong (China)	600	1,000,000

Model name	Service deployment scope	Rate limit conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limits. The service may also enforce per-second limits at RPS (RPM/60) and TPS (TPM/60)
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen3.8-max	Global	30,000	5,000,000
qwen3.8-flash	Global	30,000	5,000,000
qwen3.7-max	Global	600	1,000,000
qwen3.7-max-2026-05-20	Global	60	1,000,000
qwen3.7-plus	Global	15,000	5,000,000
qwen3.7-plus-2026-05-26	Global	60	1,000,000
qwen3.7-plus	Japan	15,000	5,000,000
qwen3.7-plus-2026-05-26	Japan	60	1,000,000
qwen3.6-plus	Global	15,000	5,000,000
qwen3.6-plus-2026-04-02	Global	60	1,000,000
qwen3.7-flash	Global	15,000	5,000,000
qwen3.7-flash-2026-07-15	Global	15,000	5,000,000
qwen3.6-flash	Global	15,000	10,000,000
qwen3.6-flash-2026-04-16	Global	60	1,000,000

Qwen-VL (visual understanding/image-to-text)

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)
Hong Kong (China)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-plus	International	1,200	1,000,000
qwen3-vl-plus-2025-12-19	International	60	100,000
qwen3-vl-plus-2025-09-23	International	120	1,000,000
qwen3-vl-flash	International	1,200	1,000,000
qwen3-vl-flash-2026-01-22	International	60	100,000
qwen3-vl-flash-2025-10-15	International	120	1,000,000
qwen-vl-max	International	1,200	1,000,000
qwen-vl-plus	International	1,200	1,000,000
qvq-max	International	60	100,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-plus	Global	6,000	10,000,000
qwen3-vl-plus-2025-09-23	Global	60	100,000
qwen3-vl-flash	Global	1,200	1,000,000
qwen3-vl-flash-us	US	1,200	1,000,000
qwen3-vl-flash-2025-10-15	Global	60	100,000
qwen3-vl-flash-2026-01-22-us	US	120	1,000,000
qwen3-vl-flash-2025-10-15-us	US	120	1,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-vl-plus Rate limiting does not apply to service calls made using the Batch API.	3,000	5,000,000
qwen3-vl-plus-2025-12-19	60	100,000
qwen3-vl-plus-2025-09-23	60	100,000
qwen3-vl-flash Rate limiting does not apply to service calls made using the Batch API.	3,000	5,000,000
qwen3-vl-flash-2026-01-22	60	100,000
qwen3-vl-flash-2025-10-15	60	100,000
qwen-vl-max Rate limiting does not apply to service calls made using the Batch API.	1,200	1,000,000
qwen-vl-plus Rate limiting does not apply to service calls made using the Batch API.	1,200	1,000,000
qvq-max	60	100,000
qvq-plus	60	100,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-plus	Global	2,000	1,000,000
qwen3-vl-plus	EU	2,000	1,000,000
qwen3-vl-plus-2025-09-23	Global	60	100,000
qwen3-vl-flash	Global	12,000	10,000,000
qwen3-vl-flash	EU	12,000	10,000,000
qwen3-vl-flash-2026-01-22	EU	60	100,000
qwen3-vl-flash-2025-10-15	Global	600	1,000,000
qwen3-vl-flash-2025-10-15	EU	600	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-plus	Hong Kong (China)	6,000	1,000,000
qwen3-vl-plus-2025-12-19	Hong Kong (China)	6,000	1,000,000

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.5-omni-flash	International	60	100,000
qwen3.5-omni-flash-2026-03-15	International	60	100,000
qwen3.5-omni-plus	International	60	100,000
qwen3.5-omni-plus-2026-03-15	International	60	100,000
qwen3-omni-flash	International	60	100,000
qwen3-omni-flash-2025-12-01	International	60	100,000
qwen3-omni-flash-2025-09-15	International	60	100,000
qwen-omni-turbo	International	60	100,000
qwen-omni-turbo-latest	International	60	100,000
qwen-omni-turbo-2025-03-26	International	60	100,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3.5-omni-flash	60	100,000
qwen3.5-omni-flash-2026-03-15	60	100,000
qwen3.5-omni-plus	60	100,000
qwen3.5-omni-plus-2026-03-15	60	100,000
qwen3-omni-flash	60	100,000
qwen3-omni-flash-2025-12-01	60	100,000
qwen3-omni-flash-2025-09-15	60	100,000
qwen-omni-turbo	60	100,000
qwen-omni-turbo-latest	60	100,000
qwen-omni-turbo-2025-03-26(qwen-omni-turbo-0326)	60	100,000
qwen-omni-turbo-2025-01-19(qwen-omni-turbo-0119)	60	100,000

Qwen-Omni-Realtime (real-time multimodal)

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.5-omni-plus-realtime	International	60	100,000
qwen3.5-omni-plus-realtime-2026-03-15	International	60	100,000
qwen3.5-omni-flash-realtime	International	60	100,000
qwen3.5-omni-flash-realtime-2026-03-15	International	60	100,000
qwen3-omni-flash-realtime	International	60	100,000
qwen3-omni-flash-realtime-2025-12-01	International	60	100,000
qwen3-omni-flash-realtime-2025-09-15	International	60	100,000
qwen-omni-turbo-realtime	International	60	10,000
qwen-omni-turbo-realtime-latest	International	60	10,000
qwen-omni-turbo-realtime-2025-05-08	International	60	10,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3.5-omni-plus-realtime	60	100,000
qwen3.5-omni-plus-realtime-2026-03-15	60	100,000
qwen3.5-omni-flash-realtime	60	100,000
qwen3.5-omni-flash-realtime-2026-03-15	60	100,000
qwen3-omni-flash-realtime	60	100,000
qwen3-omni-flash-realtime-2025-12-01	60	100,000
qwen3-omni-flash-realtime-2025-09-15	60	100,000
qwen-omni-turbo-realtime	60	100,000
qwen-omni-turbo-realtime-latest	60	100,000
qwen-omni-turbo-realtime-2025-05-08	60	100,000

Qwen-OCR (text extraction)

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-vl-ocr	International	600	6,000,000
qwen-vl-ocr-2025-11-20	International	1,200	6,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-vl-ocr	Global	600	6,000,000
qwen-vl-ocr-2025-11-20	Global	1,200	6,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3.5-ocr	6,000	30,000,000
qwen-vl-ocr Rate limiting does not apply to service calls made using the Batch API.	600	6,000,000
qwen-vl-ocr-latest	6,000	30,000,000
qwen-vl-ocr-2025-11-20	6,000	30,000,000
qwen-vl-ocr-2025-04-13	600	6,000,000
qwen-vl-ocr-2024-10-28	600	6,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-vl-ocr	Global	600	6,000,000
qwen-vl-ocr-2025-11-20	Global	1,200	6,000,000

Qwen math model

China (Beijing)

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen-math-plus	1,200	1,000,000
qwen-math-plus-latest	1,200	1,000,000
qwen-math-plus-2024-09-19(qwen-math-plus-0919)	60	100,000
qwen-math-plus-2024-08-16(qwen-math-plus-0816)	10	20,000
qwen-math-turbo	1200	1,000,000

Qwen-Coder

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-coder-plus	International	2,400	2,000,000
qwen3-coder-plus-2025-09-23	International	600	1,000,000
qwen3-coder-plus-2025-07-22	International	60	1,000,000
qwen3-coder-flash	International	600	5,000,000
qwen3-coder-flash-2025-07-28	International	600	5,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-coder-plus	Global	2,400	2,000,000
qwen3-coder-plus-2025-09-23	Global	60	1,000,000
qwen3-coder-plus-2025-07-22	Global	60	1,000,000
qwen3-coder-flash	Global	1,200	1,000,000
qwen3-coder-flash-2025-07-28	Global	60	1,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-coder-plus	5,000	5,000,000
qwen3-coder-plus-2025-09-23	60	1,000,000
qwen3-coder-plus-2025-07-22	60	1,000,000
qwen3-coder-flash	5,000	5,000,000
qwen3-coder-flash-2025-07-28	60	1,000,000
qwen-coder-plus	1,200	1,000,000
qwen-coder-turbo	1,200	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-coder-plus	Global	5,000	5,000,000
qwen3-coder-plus-2025-09-23	Global	60	1,000,000
qwen3-coder-plus-2025-07-22	Global	60	1,000,000
qwen3-coder-flash	Global	5,000	5,000,000
qwen3-coder-flash-2025-07-28	Global	60	1,000,000

Qwen translation model

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-mt-plus	International	60	100,000
qwen-mt-flash	International	60	100,000
qwen-mt-lite	International	60	100,000
qwen-mt-turbo	International	60	100,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-mt-plus	Global	60	25,000
qwen-mt-flash	Global	60	35,000
qwen-mt-lite	Global	60	100,000
qwen-mt-lite-us	US	60	100,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen-mt-plus	60	25,000
qwen-mt-flash	60	35,000
qwen-mt-lite	60	100,000
qwen-mt-turbo	60	35,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-mt-plus	Global	60	25,000
qwen-mt-flash	Global	60	35,000
qwen-mt-lite	Global	60	100,000

Qwen data mining model

China (Beijing)

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen-doc-turbo	600	3,000,000

Qwen deep research model

China (Beijing)

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen-deep-research	120	1,200,000

Text generation - Qwen - Open source

Qwen language model open source

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.8-2.4t-a95b	International	5,000	5,000,000
qwen3.8-27b	International	5,000	5,000,000
qwen3.6-35b-a3b	International	600	1,000,000
qwen3.6-27b	International	600	1,000,000
qwen3.5-397b-a17b	International	600	1,000,000
qwen3.5-122b-a10b	International	600	1,000,000
qwen3.5-27b	International	600	1,000,000
qwen3.5-35b-a3b	International	600	5,000,000
qwen3-next-80b-a3b-thinking	International	600	1,000,000
qwen3-next-80b-a3b-instruct	International	600	1,000,000
qwen3-235b-a22b-thinking-2507	International	600	1,000,000
qwen3-235b-a22b-instruct-2507	International	600	1,000,000
qwen3-30b-a3b-thinking-2507	International	600	5,000,000
qwen3-30b-a3b-instruct-2507	International	600	5,000,000
qwen3-235b-a22b	International	600	1,000,000
qwen3-32b	International	600	1,000,000
qwen3-30b-a3b	International	600	1,000,000
qwen3-14b	International	600	1,000,000
qwen3-8b	International	600	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.5-397b-a17b	Global	600	1,000,000
qwen3.5-122b-a10b	Global	600	1,000,000
qwen3.5-27b	Global	600	1,000,000
qwen3.6-35b-a3b	Global	600	1,000,000
qwen3.5-35b-a3b	Global	600	1,000,000
qwen3-next-80b-a3b-thinking	Global	600	1,000,000
qwen3-next-80b-a3b-instruct	Global	600	1,000,000
qwen3-235b-a22b-thinking-2507	Global	600	1,000,000
qwen3-235b-a22b-instruct-2507	Global	600	1,000,000
qwen3-30b-a3b-thinking-2507	Global	600	1,000,000
qwen3-30b-a3b-instruct-2507	Global	600	1,000,000
qwen3-235b-a22b	Global	600	1,000,000
qwen3-30b-a3b	Global	600	1,000,000
qwen3-32b	Global	600	1,000,000
qwen3-14b	Global	600	1,000,000
qwen3-8b	Global	600	1,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3.8-2.4t-a95b	5,000	5,000,000
qwen3.8-27b	5,000	5,000,000
qwen3.6-35b-a3b	600	1,000,000
qwen3.6-27b	600	1,000,000
qwen3.5-397b-a17b	600	1,000,000
qwen3.5-122b-a10b	600	1,000,000
qwen3.5-27b	600	1,000,000
qwen3.5-35b-a3b	600	1,000,000
qwen3-next-80b-a3b-thinking	600	1,000,000
qwen3-next-80b-a3b-instruct	600	1,000,000
qwen3-235b-a22b-thinking-2507	600	1,000,000
qwen3-235b-a22b-instruct-2507	600	1,000,000
qwen3-30b-a3b-thinking-2507	600	1,000,000
qwen3-30b-a3b-instruct-2507	600	1,000,000
qwen3-235b-a22b	600	1,000,000
qwen3-30b-a3b	600	1,000,000
qwen3-32b	2400	1,000,000
qwen3-14b	600	1,000,000
qwen3-8b	600	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3.5-397b-a17b	Global	600	1,000,000
qwen3.5-122b-a10b	Global	600	1,000,000
qwen3.5-27b	Global	600	1,000,000
qwen3.6-35b-a3b	Global	600	1,000,000
qwen3.5-35b-a3b	Global	600	1,000,000
qwen3-next-80b-a3b-thinking	Global	600	1,000,000
qwen3-next-80b-a3b-instruct	Global	600	1,000,000
qwen3-235b-a22b-thinking-2507	Global	600	1,000,000
qwen3-235b-a22b-instruct-2507	Global	600	1,000,000
qwen3-30b-a3b-thinking-2507	Global	600	1,000,000
qwen3-30b-a3b-instruct-2507	Global	600	1,000,000
qwen3-235b-a22b	Global	600	1,000,000
qwen3-30b-a3b	Global	600	1,000,000
qwen3-32b	Global	2,400	1,000,000
qwen3-14b	Global	600	1,000,000
qwen3-8b	Global	600	1,000,000

Qwen-VL (visual understanding/image-to-text)

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-32b-thinking	International	60	100,000
qwen3-vl-32b-instruct	International	60	100,000
qwen3-vl-30b-a3b-thinking	International	60	100,000
qwen3-vl-30b-a3b-instruct	International	60	100,000
qwen3-vl-8b-thinking	International	60	100,000
qwen3-vl-8b-instruct	International	60	100,000
qwen3-vl-235b-a22b-thinking	International	60	100,000
qwen3-vl-235b-a22b-instruct	International	60	100,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-235b-a22b-thinking	Global	60	100,000
qwen3-vl-235b-a22b-instruct	Global	60	100,000
qwen3-vl-32b-thinking	Global	600	1,000,000
qwen3-vl-32b-instruct	Global	600	1,000,000
qwen3-vl-30b-a3b-thinking	Global	600	1,000,000
qwen3-vl-30b-a3b-instruct	Global	600	1,000,000
qwen3-vl-8b-thinking	Global	600	1,000,000
qwen3-vl-8b-instruct	Global	600	1,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-vl-32b-thinking	600	1,000,000
qwen3-vl-32b-instruct	600	1,000,000
qwen3-vl-30b-a3b-thinking	600	1,000,000
qwen3-vl-30b-a3b-instruct	600	1,000,000
qwen3-vl-8b-thinking	600	1,000,000
qwen3-vl-8b-instruct	600	1,000,000
qwen3-vl-235b-a22b-thinking	60	100,000
qwen3-vl-235b-a22b-instruct	60	100,000
qwen2-vl-72b-instruct	1,200	1,000,000
qwen2-vl-7b-instruct	1,200	1,000,000
qwen2-vl-2b-instruct	1,200	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-vl-235b-a22b-thinking	Global	60	100,000
qwen3-vl-235b-a22b-instruct	Global	60	100,000
qwen3-vl-32b-thinking	Global	600	1,000,000
qwen3-vl-32b-instruct	Global	600	1,000,000
qwen3-vl-30b-a3b-thinking	Global	600	1,000,000
qwen3-vl-30b-a3b-instruct	Global	600	1,000,000
qwen3-vl-8b-thinking	Global	600	1,000,000
qwen3-vl-8b-instruct	Global	600	1,000,000

Qwen3-Omni

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen2.5-omni-7b	International	60	100,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen2.5-omni-7b	60	100,000

Qwen3-Omni-Captioner

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-omni-30b-a3b-captioner	International	60	100,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-omni-30b-a3b-captioner	60	100,000

Qwen-Coder

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-coder-next	International	600	1,000,000
qwen3-coder-480b-a35b-instruct	International	600	1,000,000
qwen3-coder-30b-a3b-instruct	International	600	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-coder-480b-a35b-instruct	Global	600	1,000,000
qwen3-coder-30b-a3b-instruct	Global	600	1,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-coder-next	600	1,000,000
qwen3-coder-480b-a35b-instruct	600	1,000,000
qwen3-coder-30b-a3b-instruct	600	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen3-coder-480b-a35b-instruct	Global	600	1,000,000
qwen3-coder-30b-a3b-instruct	Global	600	1,000,000
qwen3-coder-next	EU	600	1,000,000

Text generation - Third-party models

DeepSeek

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
deepseek-v4-pro	International	10,000	1,200,000
deepseek-v4-pro-0813	International	10,000	1,200,000
deepseek-v4-flash-0731	International	15,000	1,200,000
deepseek-v4-flash	International	10,000	1,200,000
deepseek-v3.2	International	10,000	1,200,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
deepseek-v4-pro	Global	15,000	1,200,000
deepseek-v4-pro-0813	Global	15,000	1,200,000
deepseek-v4-pro-us	US	10,000	1,200,000
deepseek-v4-flash-0731	Global	15,000	1,200,000
deepseek-v4-flash	Global	15,000	1,200,000
deepseek-v4-flash-us	US	10,000	1,200,000
deepseek-v4-flash-0731-us	US	15,000	1,200,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
deepseek-v4-pro	15,000	1,200,000
deepseek-v4-pro-0813	15,000	1,200,000
deepseek-v4-flash-0731	15,000	1,200,000
deepseek-v4-flash	15,000	1,200,000
deepseek-v3.2 Rate limiting does not apply to service calls made using the Batch API.	15,000	1,000,000
deepseek-v3.2-exp	15,000	1,200,000
deepseek-v3.1	15,000	1,200,000
deepseek-r1-0528	60	100,000
deepseek-r1 Rate limiting does not apply to service calls made using the Batch API.	15,000	1,200,000
deepseek-v3 Rate limiting does not apply to service calls made using the Batch API.	15,000	1,200,000
deepseek-r1-distill-qwen-7b	15,000	1,200,000
deepseek-r1-distill-qwen-14b	15,000	1,200,000
deepseek-r1-distill-qwen-32b	15,000	1,200,000
deepseek-r1-distill-qwen-1.5b	60	100,000
deepseek-r1-distill-llama-8b	60	100,000
deepseek-r1-distill-llama-70b	60	100,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
deepseek-v4-pro	Global	15,000	1,200,000
deepseek-v4-pro-0813	Global	15,000	1,200,000
deepseek-v4-flash-0731	Global	15,000	1,200,000
deepseek-v4-flash	Global	15,000	1,200,000

Model name	Service deployment scope	Rate limit conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limits. The service may also enforce per-second limits at RPS (RPM/60) and TPS (TPM/60)
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
deepseek-v4-pro	Japan	10,000	1,200,000
deepseek-v4-pro-0813	Japan	15,000	1,200,000
deepseek-v4-flash	Japan	10,000	1,200,000
deepseek-v4-flash-0731	Japan	15,000	1,200,000
deepseek-v4-pro	Global	10,000	1,200,000
deepseek-v4-pro-0813	Global	15,000	1,200,000
deepseek-v4-flash-0731	Global	15,000	1,200,000
deepseek-v4-flash	Global	10,000	1,200,000

Tab 正文

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
deepseek-v4-flash-0731	Hong Kong (China)	15,000	1,200,000
deepseek-v4-pro-0813	Hong Kong (China)	15,000	1,200,000

Kimi

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
kimi-k3	15,000	1,200,000
kimi-k2.7-code	500	1,000,000
kimi-k2.6	500	1,000,000
kimi-k2.5	500	1,000,000
kimi-k2-thinking	500	1,000,000
Moonshot-Kimi-K2-Instruct	500	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
kimi-k3	Global	15,000	1,200,000
kimi-k3	International	10,000	1,200,000
kimi-k2.7-code	Global	500	1,000,000
kimi-k2.5	Global	500	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
kimi-k3	Global	15,000	1,200,000
kimi-k2.7-code	Global	500	1,000,000
kimi-k2.5	Global	500	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
kimi-k3	Global	15,000	1,200,000
kimi-k2.7-code	Global	500	1,000,000

Model name	Service deployment scope	Rate limit conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limits. The service may also enforce per-second limits at RPS (RPM/60) and TPS (TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
kimi-k3	Global	15,000	1,200,000
kimi-k2.7-code	Global	500	1,000,000
kimi-k2.5	Global	500	1,000,000

Model name	Service deployment scope	Rate limits (triggered if any value is exceeded) The following are the limits per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
kimi-k3	International	10,000	1,200,000
kimi-k2.7-code	International	500	1,000,000

MiniMax

China (Beijing)

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
MiniMax-M2.5	500	1,000,000

GLM

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
glm-5.2	Global	500	1,000,000
glm-5.2-us	US	500	1,000,000
glm-5.1	Global	500	1,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
glm-5.2	500	2,000,000
glm-5.1	500	1,000,000
glm-5	500	1,000,000
glm-4.7	500	1,000,000
glm-4.6	60	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
glm-5.2	Global	500	1,000,000
glm-5.1	Global	500	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
glm-5.2	International	500	1,000,000
glm-5.1	International	500	1,000,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
glm-5.2	Global	500	1,000,000

Model name	Service deployment scope	Rate limit conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limits. The service may also enforce per-second limits at RPS (RPM/60) and TPS (TPM/60)
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
glm-5.1	Global	500	1,000,000

GLM-Z.AI direct supply

Singapore

Model name	Rate limits (triggered if any value is exceeded) The following are the limits per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
ZHIPU/GLM-5.3	200	3,000,000
ZHIPU/GLM-5.2	200	3,000,000

Image generation

Qwen-Image

Singapore
China (Beijing)
Hong Kong (China)
Germany (Frankfurt)
Japan (Tokyo)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	Task submission API call limit	Number of concurrent tasks (concurrency)
qwen-image-3.0-pro	International	5 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-3.0	International	20 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-2.0-pro	International	2 times/minute	No limit for synchronous APIs
qwen-image-2.0-pro-2026-06-22	International	2 times/minute	No limit for synchronous APIs
qwen-image-2.0-pro-2026-04-22	International	2 times/minute	No limit for synchronous APIs
qwen-image-2.0-pro-2026-03-03	International	2 times/minute	No limit for synchronous APIs
qwen-image-2.0	International	2 times/second	No limit for synchronous APIs
qwen-image-2.0-2026-03-03	International	2 times/second	No limit for synchronous APIs
qwen-image-max	International	2 times/minute	No limit for synchronous APIs
qwen-image-max-2025-12-30	International	2 times/minute	No limit for synchronous APIs
qwen-image-plus	International	2 times/second	No limit for synchronous APIs / 2 for asynchronous APIs
qwen-image-plus-2026-01-09	International	2 times/second	No limit for synchronous APIs
qwen-image	International	2 times/second	No limit for synchronous APIs / 2 for asynchronous APIs
qwen-image-edit-max	International	2 times/minute	No limit for synchronous APIs
qwen-image-edit-max-2026-01-16	International	2 times/minute	No limit for synchronous APIs
qwen-image-edit-plus	International	2 times/second	No limit for synchronous APIs
qwen-image-edit-plus-2025-12-15	International	2 times/second	No limit for synchronous APIs
qwen-image-edit-plus-2025-10-30	International	2 times/second	No limit for synchronous APIs
qwen-image-edit	International	2 times/second	No limit for synchronous APIs
qwen-mt-image-2.0	International	60 times/minute	2

Model name	Rate limiting conditions (triggered if any value is exceeded)
Model name	Task submission API call limit	Number of concurrent tasks (concurrency)
qwen-image-3.0-pro	5 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-3.0	20 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-2.0-pro	2 times/minute	No limit for synchronous APIs
qwen-image-2.0-pro-2026-06-22	2 times/minute	No limit for synchronous APIs
qwen-image-2.0-pro-2026-04-22	2 times/minute	No limit for synchronous APIs
qwen-image-2.0-pro-2026-03-03	2 times/minute	No limit for synchronous APIs
qwen-image-2.0	2 times/second	No limit for synchronous APIs
qwen-image-2.0-2026-03-03	2 times/second	No limit for synchronous APIs
qwen-image-max	2 times/minute	No limit for synchronous APIs
qwen-image-max-2025-12-30	2 times/minute	No limit for synchronous APIs
qwen-image-plus	2 times/second	No limit for synchronous APIs / 2 for asynchronous APIs
qwen-image-plus-2026-01-09	2 times/second	No limit for synchronous APIs
qwen-image	2 times/second	No limit for synchronous APIs / 2 for asynchronous APIs
qwen-image-edit-max	2 times/minute	No limit for synchronous APIs
qwen-image-edit-max-2026-01-16	2 times/minute	No limit for synchronous APIs
qwen-image-edit-plus	2 times/second	No limit for synchronous APIs
qwen-image-edit-plus-2025-12-15	2 times/second	No limit for synchronous APIs
qwen-image-edit-plus-2025-10-30	2 times/second	No limit for synchronous APIs
qwen-image-edit	2 times/second	No limit for synchronous APIs
qwen-mt-image-2.0	60 times/minute	2
qwen-mt-image	1 time/second	2

Model name	Service deployment scope	Rate limits (triggered if any value is exceeded)
Model name	Service deployment scope	Task submission API call limit	Number of concurrent processing tasks (concurrency)
qwen-image-3.0-pro	Global	5 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-3.0	Global	20 request/minute	No limit for sync APIs / 10 for async APIs

Model name	Service deployment scope	Rate limits (triggered if any value is exceeded)
Model name	Service deployment scope	Task submission API call limit	Number of concurrent processing tasks (concurrency)
qwen-image-3.0-pro	Global	5 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-3.0	Global	20 request/minute	No limit for sync APIs / 10 for async APIs

Model name	Service deployment scope	Rate limits (triggered if any value is exceeded)
Model name	Service deployment scope	Task submission API call limit	Number of concurrent processing tasks (concurrency)
qwen-image-3.0-pro	Global	5 request/minute	No limit for sync APIs / 10 for async APIs
qwen-image-3.0	Global	20 request/minute	No limit for sync APIs / 10 for async APIs

Text-to-image - Z-Image

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
z-image-turbo	International	2	No limit for synchronous APIs

Wanxiang

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan2.7-image-pro	International	5	5
wan2.7-image	International	5	5
wan2.6-image	International	5	5
wan2.6-t2i	International	5	5
wan2.5-t2i-preview	International	5	5
wan2.2-t2i-flash	International	2	2
wan2.2-t2i-plus	International	2	2
wan2.1-t2i-turbo	International	2	2
wan2.1-t2i-plus	International	2	2
wan2.5-i2i-preview	International	5	5

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan2.6-t2i	Global	5	5
wan2.6-image	Global	5	5

Model name	Rate limiting conditions (triggered if any value is exceeded)
Model name	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan2.7-image-pro	5	5
wan2.7-image	5	5
wan2.6-image	5	5
wan2.6-t2i	1	5
wan2.5-t2i-preview	5	5
wanx2.0-t2i-turbo	2	2
wanx2.1-t2i-turbo	2	2
wanx2.1-t2i-plus	2	2
wan2.2-t2i-flash	2	2
wan2.2-t2i-plus	2	2
wan2.5-i2i-preview	5	5
wanx2.1-imageedit	2	2

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan2.6-t2i	Global	1	5
wan2.6-image	Global	5	5

OutfitAnyone

China (Beijing)

Model name	Rate limiting conditions (triggered if any value is exceeded)
Model name	RPS limit for job submission API	Number of concurrent tasks
aitryon-plus	10	5
aitryon-parsing-v1	10	No limit for synchronous APIs

Video generation

HappyHorse series

Singapore
US (Virginia)
China (Beijing)
Germany (Frankfurt)
Japan (Tokyo)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
happyhorse-1.1-t2v	International	5	5
happyhorse-1.1-i2v	International	5	5
happyhorse-1.1-r2v	International	5	5
happyhorse-1.0-t2v	International	5	5
happyhorse-1.0-i2v	International	5	5
happyhorse-1.0-r2v	International	5	5
happyhorse-1.0-video-edit	International	5	5

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
happyhorse-1.1-t2v	Global	5	5
happyhorse-1.1-i2v	Global	5	5
happyhorse-1.1-r2v	Global	5	5
happyhorse-1.0-t2v	Global	5	5
happyhorse-1.0-i2v	Global	5	5
happyhorse-1.0-r2v	Global	5	5
happyhorse-1.0-video-edit	Global	5	5

Model name	Rate limiting conditions (triggered if any value is exceeded)
Model name	RPS limit for task submission API	Number of concurrent tasks (concurrency)
happyhorse-1.1-t2v	5	5
happyhorse-1.1-i2v	5	5
happyhorse-1.1-r2v	5	5
happyhorse-1.0-t2v	5	5
happyhorse-1.0-i2v	5	5
happyhorse-1.0-r2v	5	5
happyhorse-1.0-video-edit	5	5

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
happyhorse-1.1-t2v	Global	5	5
happyhorse-1.1-i2v	Global	5	5
happyhorse-1.1-r2v	Global	5	5
happyhorse-1.0-t2v	Global	5	5
happyhorse-1.0-i2v	Global	5	5
happyhorse-1.0-r2v	Global	5	5
happyhorse-1.0-video-edit	Global	5	5

Wanxiang series

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan3.0-video-prime	International	5	5
wan3.0-video	International	5	5
wan2.7-r2v-2026-06-12	Global	5	5
wan2.7-t2v-2026-06-12	International	5	5
wan2.7-t2v-2026-04-25	International	5	5
wan2.7-t2v	International	5	5
wan2.6-t2v	International	5	5
wan2.5-t2v-preview	International	5	5
wan2.2-t2v-plus	International	2	2
wan2.1-t2v-turbo	International	2	2
wan2.1-t2v-plus	International	2	2
wan2.7-i2v-2026-04-25	International	5	5
wan2.7-i2v	International	5	5
wan2.6-i2v-flash	International	5	5
wan2.6-i2v	International	5	5
wan2.5-i2v-preview	International	5	5
wan2.2-i2v-flash	International	2	2
wan2.1-i2v-plus	International	2	2
wan2.1-i2v-turbo	International	2	2
wan2.2-i2v-plus	International	2	2
wan2.2-kf2v-flash	International	2	2
wan2.1-kf2v-plus	International	1	2
wan2.1-vace-plus	International	2	2
wan2.7-videoedit	International	5	5
wan2.7-r2v	International	5	5
wan2.6-r2v-flash	International	5	5
wan2.6-r2v	International	5	5
wan2.2-animate-move	International	5	1
wan2.2-animate-mix	International	5	1

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan3.0-video-prime	Global	5	5
wan3.0-video	Global	5	5
wan2.6-t2v	Global	5	5
wan2.6-i2v	Global	5	5
wan2.6-r2v	Global	5	5
wan2.6-t2v-us	US	5	5
wan2.6-i2v-us	US	5	5

Model name	Rate limiting conditions (triggered if any value is exceeded)
Model name	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan3.0-video-prime	5	5
wan3.0-video	5	5
wan2.7-r2v-2026-06-12	5	5
wan2.7-t2v-2026-06-12	5	5
wan2.7-t2v-2026-04-25	5	5
wan2.7-t2v	5	5
wan2.6-t2v	5	5
wan2.5-t2v-preview	5	5
wan2.2-t2v-plus	2	2
wanx2.1-t2v-turbo	2	2
wanx2.1-t2v-plus	2	2
wan2.7-i2v-2026-04-25	5	5
wan2.7-i2v	5	5
wan2.6-i2v-flash	5	5
wan2.6-i2v	5	5
wan2.5-i2v-preview	5	5
wan2.2-i2v-plus	2	2
wanx2.1-i2v-turbo	2	2
wanx2.1-i2v-plus	2	2
wan2.2-kf2v-flash	2	2
wanx2.1-kf2v-plus	2	2
wanx2.1-vace-plus	2	2
wan2.7-videoedit	5	5
wan2.7-r2v	5	5
wan2.6-r2v-flash	5	5
wan2.6-r2v	5	5
wan2.2-s2v-detect	5	No limit for synchronous APIs
wan2.2-s2v	5	1
wan2.2-animate-move	5	1
wan2.2-animate-mix	5	1

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded)
Model name	Service deployment scope	RPS limit for task submission API	Number of concurrent tasks (concurrency)
wan2.6-t2v	Global	5	5
wan2.6-i2v	Global	5	5
wan2.6-r2v	Global	5	5

AnimateAnyone

China (Beijing)

Model name

RPS limit for task submission API

Number of concurrent tasks

animate-anyone-detect-gen2

No limit for synchronous APIs

animate-anyone-template-gen2

Only one job runs at a time. Other jobs in the queue are in a waiting state.

animate-anyone-gen2

Only one job runs at a time. Other jobs in the queue are in a waiting state.

EMO

China (Beijing)

Model name

RPS limit for task submission API

Number of concurrent tasks

emo-detect-v1

No limit for synchronous APIs

emo-v1

Only one job runs at a time. Other jobs in the queue are in a waiting state.

LivePortrait

China (Beijing)

Model name

RPS limit for task submission API

Number of concurrent tasks

liveportrait-detect

No limit for synchronous APIs

liveportrait

Only one job runs at a time. Other jobs in the queue are in a waiting state.

VideoRetalk

China (Beijing)

Model name

RPS limit for task submission API

Number of concurrent tasks

videoretalk

Only one job runs at a time. Other jobs in the queue are in a waiting state.

Emoji

China (Beijing)

Model name

RPS limit for task submission API

Number of concurrent tasks

emoji-detect-v1

No limit for synchronous APIs

emoji-v1

Only one job runs at a time. Other jobs in the queue are in a waiting state.

Video style transform

China (Beijing)

Model name

RPS limit for task submission API

Number of concurrent tasks

video-style-transform

Only one job runs at a time. Other jobs in the queue are in a waiting state.

Music generation

China (Beijing)

Model name	Requests per minute (RPM)
fun-music-preview	180
fun-music-v1	180

Voice chat

Realtime voice chat

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen-audio-3.0-realtime-plus	International	60	100,000
qwen-audio-3.0-realtime-flash	International	60	100,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen-audio-3.0-realtime-plus	60	100,000
qwen-audio-3.0-realtime-flash	60	100,000

Speech synthesis (text-to-speech)

Qwen-Audio-TTS

Singapore
China (Beijing)

Model name	Service deployment scope	Job submission API RPS limit
qwen-audio-3.0-tts-plus	International	3
qwen-audio-3.0-tts-flash	International	3

Qwen-TTS

Singapore
China (Beijing)

Qwen3-TTS-Instruct-Flash
Qwen3-TTS-VD
Qwen3-TTS-VC
Qwen3-TTS-Flash

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-tts-instruct-flash	International	180
qwen3-tts-instruct-flash-2026-01-26	International	180

Qwen3-TTS-Instruct-Flash
Qwen3-TTS-VD
Qwen3-TTS-VC
Qwen3-TTS-Flash
Qwen-TTS

Model name	Requests per minute (RPM)
qwen3-tts-instruct-flash	180
qwen3-tts-instruct-flash-2026-01-26	180

Model name	Rate limiting conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limiting conditions. The service may also enforce RPS (RPM/60) and TPS (TPM/60) limits
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen-tts	10	100,000
qwen-tts-latest
qwen-tts-2025-05-22
qwen-tts-2025-04-10

Qwen-TTS-Realtime

Singapore
China (Beijing)

Qwen3-TTS-Instruct-Flash-Realtime
Qwen3-TTS-VD-Realtime
Qwen3-TTS-VC-Realtime
Qwen3-TTS-Flash-Realtime

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-tts-instruct-flash-realtime	International	180
qwen3-tts-instruct-flash-realtime-2026-01-22	International	180

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-tts-flash-realtime	International	180
qwen3-tts-flash-realtime-2025-11-27	International	180
qwen3-tts-flash-realtime-2025-09-18	International	10

Qwen3-TTS-Instruct-Flash-Realtime
Qwen3-TTS-VD-Realtime
Qwen3-TTS-VC-Realtime
Qwen3-TTS-Flash-Realtime
Qwen-TTS-Realtime

Model name	Requests per minute (RPM)
qwen3-tts-instruct-flash-realtime	180
qwen3-tts-instruct-flash-realtime-2026-01-22	180

Model name	Rate limiting conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limiting conditions. The service may also enforce RPS (RPM/60) and TPS (TPM/60) limits
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen-tts-realtime	10	100,000
qwen-tts-realtime-latest
qwen-tts-realtime-2025-07-15

Qwen-TTS voice cloning

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per minute (RPM)
qwen-voice-enrollment	International	180

Qwen-TTS voice design

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per minute (RPM)
qwen-voice-design	International	180

CosyVoice

Singapore
China (Beijing)

Model name	Service deployment scope	Job submission API RPS limit
cosyvoice-v3-plus	International	3
cosyvoice-v3-flash	International	3

Qwen-Audio-TTS/CosyVoice voice cloning/design

Qwen-Audio-TTS/CosyVoice voice cloning/design models share a single model and a single rate limit quota.

Singapore
China (Beijing)

Model name	Service deployment scope	Job submission API RPS limit
voice-enrollment	International	10

Speech recognition (speech-to-text) and translation (speech to text in a specified language)

Qwen3-LiveTranslate-Flash

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limiting conditions. The service may also enforce RPS (RPM/60) and TPS (TPM/60) limits
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen3-livetranslate-flash	International	100	100,000
qwen3-livetranslate-flash-2025-12-01	International	100	100,000

Model name	Rate limiting conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limiting conditions. The service may also enforce RPS (RPM/60) and TPS (TPM/60) limits
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen3-livetranslate-flash	100	100,000
qwen3-livetranslate-flash-2025-12-01	100	100,000

Qwen-LiveTranslate-Flash-Realtime

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limiting conditions. The service may also enforce RPS (RPM/60) and TPS (TPM/60) limits
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen3.5-livetranslate-flash-realtime	International	10	100,000
qwen3.5-livetranslate-flash-realtime-2026-05-19	International
qwen3-livetranslate-flash-realtime	International
qwen3-livetranslate-flash-realtime-2025-09-22	International

Model name	Rate limiting conditions (rate limiting is triggered when any value is exceeded) The following are per-minute rate limiting conditions. The service may also enforce RPS (RPM/60) and TPS (TPM/60) limits
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Including input and output tokens
qwen3.5-livetranslate-flash-realtime	10	100,000
qwen3.5-livetranslate-flash-realtime-2026-05-19
qwen3-livetranslate-flash-realtime
qwen3-livetranslate-flash-realtime-2025-09-22

Qwen-Audio-3.0-ASR-Flash-Streaming

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per second (RPS)
qwen-audio-3.0-asr-flash-streaming	International	20

Qwen-Audio-3.0-ASR-Flash-Filetrans

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per minute (RPM)
qwen-audio-3.0-asr-flash-filetrans	International	600

Qwen-Audio-3.0-ASR-Flash

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per minute (RPM)
qwen-audio-3.0-asr-flash	International	600

Qwen-ASR

Singapore
US (Virginia)
China (Beijing)

Qwen3-ASR-Flash-Filetrans
Qwen3-ASR-Flash

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-asr-flash-filetrans	International	100
qwen3-asr-flash-filetrans-2025-11-17	International	100

Qwen3-ASR-Flash-Filetrans
Qwen3-ASR-Flash

Model name	Requests per minute (RPM)
qwen3-asr-flash-filetrans	100
qwen3-asr-flash-filetrans-2025-11-17	100

Qwen-ASR-Realtime

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per second (RPS)
qwen3-asr-flash-realtime	International	20
qwen3-asr-flash-realtime-2026-02-10	International
qwen3-asr-flash-realtime-2025-10-27	International

Paraformer

China (Beijing)

Model name	Job submission API RPS limit
paraformer-realtime-v2	20
paraformer-realtime-8k-v2	20

Model name	Requests per minute (RPM)
paraformer-v2	1,200

Model name	Job submission API RPS limit	Concurrent tasks (concurrency)
paraformer-8k-v2	20	100

Fun-ASR

Singapore
China (Beijing)

Model name	Service deployment scope	Requests per minute (RPM)
fun-asr	International	600
fun-asr-2025-11-07	International	600
fun-asr-2025-08-25	International	600
fun-asr-mtl	International	100
fun-asr-mtl-2025-08-25	International	100
fun-asr-flash-2026-06-15	International	600

Fun-ASR-Realtime

Singapore
China (Beijing)

Model name	Service deployment scope	Job submission API RPS limit
fun-asr-realtime	International	20
fun-asr-realtime-2025-11-07	International	20

Text embedding

Singapore
China (Beijing)
Hong Kong (China)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
text-embedding-v4	International	1,800	1,000,000
text-embedding-v3	International	6,000	24,000,000

Model name	Rate limiting conditions (triggered if any value is exceeded)
Model name	Requests per second (RPS)	Number of concurrent tasks (concurrency)
text-embedding-v4 Rate limiting does not apply to service calls made using the Batch API.	30	1,200,000

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
text-embedding-v4	Hong Kong (China)	1,800	1,200,000

Multimodal embedding

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Input tokens only.
tongyi-embedding-vision-plus	International	600	200,000
tongyi-embedding-vision-flash	International	600	200,000

Model name	Rate limiting conditions The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-vl-embedding	2,400	1,200,000
multimodal-embedding-v1	120	1,000,000

Sorting model

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Input tokens only.
qwen3-rerank	International	5,400	5,000,000,000

Model name	Rate limiting conditions The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen3-vl-rerank	600	9,000,000
gte-rerank-v2	5,040	4,980,000,000

Industry

Intention recognition

China (Beijing)

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
tongyi-intent-detect-v3	1,200	1,000,000

Role assumption

Singapore
China (Beijing)

Model name	Service deployment scope	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Service deployment scope	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
qwen-plus-character	International	120	500,000
qwen-flash-character	International	120	500,000
qwen-plus-character-ja	International	120	500,000

Model name	Rate limiting conditions (triggered if any value is exceeded) The following limits are per minute. The service may also enforce limits based on requests per second (RPS = RPM/60) and tokens per second (TPS = TPM/60).
Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens
qwen-plus-character	120	500,000
qwen-flash-character	120	500,000

Offline models

For more information, see Model unpublishing policy.

Offline on January 30, 2026
Offline on August 20, 2025

Category	Model name	Rate limiting conditions (triggered if any value is exceeded)
Category	Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
Qwen-Plus	qwen-plus-2024-11-27	0	0
	qwen-plus-2024-11-25
	qwen-plus-2024-09-19
	qwen-plus-2024-08-06
Qwen-Turbo	qwen-turbo-2024-09-19
Qwen-VL	qwen-vl-max-2024-10-30
	qwen-vl-max-2024-08-09
	qwen-vl-plus-2024-08-09

Category	Model name	Rate limiting conditions (triggered if any value is exceeded)
Category	Model name	Requests per minute (RPM)	Tokens per minute (TPM) Includes input and output tokens.
Text generation - Qwen	qwen2-72b-instruct	0	0
	qwen2-57b-a14b-instruct
	qwen2-7b-instruct
	qwen1.5-110b-chat
	qwen1.5-72b-chat
	qwen1.5-32b-chat
	qwen1.5-14b-chat
	qwen1.5-7b-chat

Model name	Service deployment scope	Rate limits (triggered if any value is exceeded)
Model name	Service deployment scope	Task submission API RPS limit	Number of concurrent processing tasks (concurrency)
happyhorse-1.0-video-edit	Global	5	5

Model name	Service region	Rate limiting conditions (triggered when any value is exceeded)
Model name	Service region	Task submission API RPS limit	Number of concurrent processing tasks
wan3.0-video-prime	Global	5	5
wan3.0-video	Global	5	5

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-tts-flash	International	180
qwen3-tts-flash-2025-11-27	International	180
qwen3-tts-flash-2025-09-18	International	10

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-tts-vd-realtime-2026-01-15	International	180
qwen3-tts-vd-realtime-2025-12-16	International	180

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-tts-vc-realtime-2026-01-15	International	180
qwen3-tts-vc-realtime-2025-11-27	International	180

Model name	Job submission API RPS limit
cosyvoice-v3.5-plus	3
cosyvoice-v3.5-flash
cosyvoice-v3-plus
cosyvoice-v3-flash
cosyvoice-v2

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-asr-flash	International	100
qwen3-asr-flash-2026-02-10	International
qwen3-asr-flash-2025-09-08	International

Model name	Service deployment scope	Requests per minute (RPM)
qwen3-asr-flash-us	United States	100
qwen3-asr-flash-2025-09-08-us	United States	100

Model name	Job submission API RPS limit
fun-asr-realtime	20
fun-asr-realtime-2026-02-28
fun-asr-realtime-2025-11-07
fun-asr-realtime-2025-09-15
fun-asr-flash-8k-realtime
fun-asr-flash-8k-realtime-2026-01-28

​Rate limiting rules

​FAQ

​Why is rate limiting triggered?

​How to view model usage

​How long does it take to recover from rate limiting?

​Is model response speed related to payment status?

​What factors affect model response speed?

​Does rate limiting reduce the generation speed of accepted requests?

​How to avoid rate limiting

​How to control token usage or costs

​Will I still be rate limited after I top up my account?

​Increase temporary rate limits

​Text generation - Qwen

​Qwen language model

​Qwen-VL (visual understanding/image-to-text)

​Qwen-Omni (omni-modal)

​Qwen-Omni-Realtime (real-time multimodal)

​Qwen-OCR (text extraction)

​Qwen math model

​Qwen-Coder

​Qwen translation model

​Qwen data mining model

​Qwen deep research model

​Text generation - Qwen - Open source

​Qwen language model open source

​Qwen-VL (visual understanding/image-to-text)

​Qwen3-Omni

​Qwen3-Omni-Captioner

​Qwen-Coder

​Text generation - Third-party models

​DeepSeek

​Kimi

​MiniMax

​GLM

​GLM-Z.AI direct supply

​Image generation

​Qwen-Image

​Text-to-image - Z-Image

​Wanxiang

​OutfitAnyone

​Video generation

​HappyHorse series

​Wanxiang series

​AnimateAnyone

​EMO

​LivePortrait

​VideoRetalk

​Emoji

​Video style transform

​Music generation

​Voice chat

​Realtime voice chat

​Speech synthesis (text-to-speech)

​Qwen-Audio-TTS

​Qwen-TTS

​Qwen-TTS-Realtime

​Qwen-TTS voice cloning

​Qwen-TTS voice design

​CosyVoice

​Qwen-Audio-TTS/CosyVoice voice cloning/design

​Speech recognition (speech-to-text) and translation (speech to text in a specified language)

​Qwen3-LiveTranslate-Flash

​Qwen-LiveTranslate-Flash-Realtime

​Qwen-Audio-3.0-ASR-Flash-Streaming

​Qwen-Audio-3.0-ASR-Flash-Filetrans

​Qwen-Audio-3.0-ASR-Flash

​Qwen-ASR

​Qwen-ASR-Realtime

​Paraformer

​Fun-ASR

​Fun-ASR-Realtime

​Text embedding

​Multimodal embedding

​Sorting model

​Industry

​Intention recognition

​Role assumption

​Offline models

Rate limiting rules

FAQ

Why is rate limiting triggered?

How to view model usage

How long does it take to recover from rate limiting?

Is model response speed related to payment status?

What factors affect model response speed?

Does rate limiting reduce the generation speed of accepted requests?

How to avoid rate limiting

How to control token usage or costs

Will I still be rate limited after I top up my account?

Increase temporary rate limits

Text generation - Qwen

Qwen language model

Qwen-VL (visual understanding/image-to-text)

Qwen-Omni (omni-modal)

Qwen-Omni-Realtime (real-time multimodal)

Qwen-OCR (text extraction)

Qwen math model

Qwen-Coder

Qwen translation model

Qwen data mining model

Qwen deep research model

Text generation - Qwen - Open source

Qwen language model open source

Qwen-VL (visual understanding/image-to-text)

Qwen3-Omni

Qwen3-Omni-Captioner

Qwen-Coder

Text generation - Third-party models

DeepSeek

Kimi

MiniMax

GLM

GLM-Z.AI direct supply

Image generation

Qwen-Image

Text-to-image - Z-Image

Wanxiang

OutfitAnyone

Video generation

HappyHorse series

Wanxiang series

AnimateAnyone

EMO

LivePortrait

VideoRetalk

Emoji

Video style transform

Music generation

Voice chat

Realtime voice chat

Speech synthesis (text-to-speech)

Qwen-Audio-TTS

Qwen-TTS

Qwen-TTS-Realtime

Qwen-TTS voice cloning

Qwen-TTS voice design

CosyVoice

Qwen-Audio-TTS/CosyVoice voice cloning/design

Speech recognition (speech-to-text) and translation (speech to text in a specified language)

Qwen3-LiveTranslate-Flash

Qwen-LiveTranslate-Flash-Realtime

Qwen-Audio-3.0-ASR-Flash-Streaming

Qwen-Audio-3.0-ASR-Flash-Filetrans

Qwen-Audio-3.0-ASR-Flash

Qwen-ASR

Qwen-ASR-Realtime

Paraformer

Fun-ASR

Fun-ASR-Realtime

Text embedding

Multimodal embedding

Sorting model

Industry

Intention recognition

Role assumption

Offline models