CloudRouter 文档

English

简体中文

English

简体中文

Appearance

Concurrency Settings ​

Applies to: Organization (top-level user) Updated: 2026-07-02

The concurrency count determines how many parallel requests can be sent to models at the same moment; it is an important parameter for controlling usage and ensuring service stability. This article explains the concept of concurrency and clarifies that in the new console the organization-level concurrency limit is configured uniformly by the platform and requires contacting the platform to adjust.

1. What Is Concurrency ​

"Concurrency count" refers to the number of parallel requests allowed at the same moment. The higher the concurrency, the more requests can be processed instantaneously, but the greater the instantaneous resource usage; requests exceeding the limit are rate-limited.

In the new console, concurrency is managed in the form of an organization-level concurrency limit: it constrains the organization's parallel request capacity. For security and resource-control reasons, this limit is a platform-level configuration; the organization cannot modify it itself, and it is set and adjusted uniformly by the platform.

Regarding the fine-grained capability of "allocating a separate concurrency count to each subuser": concurrency is currently simplified to a unified organization level, and user-level fine-grained concurrency allocation is not yet supported.

2. Organization-Level Concurrency Limit (Configured Uniformly by the Platform) ​

TermMeaning
Organization-level concurrency limitThe maximum parallel request capacity the organization is allowed to reach, set uniformly by the platform
  • The organization-level concurrency limit is configured uniformly by the platform, and the organization cannot self-serve modifications within the console.
  • When an adjustment is needed, please contact CloudRouter officially to apply for a quota adjustment (see the next section).

Whether the console currently displays the specific value of the concurrency limit follows the actual interface; if it is not shown, you can confirm the current limit with the platform when applying.

3. When You Need to Apply for an Adjustment ​

Consider applying to raise the organization-level concurrency limit when:

  • Business requests are frequently rate-limited, affecting normal use
  • You are about to onboard new business and expect concurrency to rise significantly
  • Peak-period parallel call demand exceeds the current limit

4. How to Apply for an Adjustment (Contact the Platform) ​

  1. Organize your request and prepare the following information:
    • Organization name
    • Current limit (if known)
    • The target value you want to adjust to
    • A brief business background (e.g. "new customer, expecting dozens of parallel calls per second at peak")
  2. Contact CloudRouter through any channel: submit a ticket / contact your business liaison / send an email to the official customer service email / the contact info published on the official site.
  3. Wait for processing: after verification, the platform adjusts the concurrency limit for your organization.
  4. Once effective, it runs at the new limit and calls benefit immediately, with no need to log in again or recreate Keys.

Please confirm there is a genuine concurrency bottleneck before submitting, to avoid over-applying. Each adjustment requires a separate request.

5. FAQ ​

Q: I can't find anywhere in the console to change the concurrency limit? A: The organization-level concurrency limit is a platform-level configuration, managed uniformly by the platform, and the organization interface has no self-service modification entry. To adjust it, contact CloudRouter as described above.

Q: Can I assign different concurrency counts to different subusers? A: Currently concurrency is simplified to a unified organization level, and subuser-level fine-grained allocation is not yet supported. If you have such a need, you can mention it when contacting the platform.

Q: Do I need to log in again or recreate Keys after the concurrency limit is adjusted? A: No. Once the adjustment takes effect, subsequent requests run at the new limit.

Q: Is higher concurrency always better? A: No. The higher the concurrency, the greater the instantaneous resource usage; we recommend applying reasonably based on actual business needs to avoid waste.

Q: Is concurrency rate-limiting the same thing as insufficient balance/quota? A: No. Concurrency rate-limiting is too many parallel requests at the same moment; insufficient balance/quota is a funds or quota issue (see Balance Alerts & Arrears). The two have different errors and handling.

Contact Us ​