specification: API Commons Rate Limits
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/RateLimits
provider: Qwen
providerId: qwen
created: '2026-05-08'
# Provenance stamped 2026-08-11: this artifact was written by the API Evangelist
# bulk sweep dated 2026-05-08, not harvested from the provider. See roadmap#35.
method: generated
modified: '2026-05-08'
reconciled: true
tags:
- AI
- LLM
- Alibaba
- Rate Limiting
description: >-
  Alibaba Cloud Model Studio enforces per-model RPM/TPM and concurrent-task quotas. Limits
  are configurable per workspace and visible in the console; defaults vary by model and tier.
notes: >-
  Concurrent task quotas exist alongside RPM/TPM. Higher limits available via Alibaba Cloud
  ticketing or enterprise contracts.
sources:
- https://www.alibabacloud.com/help/en/model-studio
responseCodes:
  throttled: 429
limits:
- name: Default RPM
  scope: account
  metric: requests-per-minute
  limit: see workspace console
  notes: Per-model defaults; varies by Qwen variant.
- name: Default TPM
  scope: account
  metric: tokens-per-minute
  limit: see workspace console
- name: Concurrent Tasks
  scope: account
  metric: concurrent-tasks
  limit: see workspace console
  notes: Image/video generation has separate concurrency caps.
policies:
- name: Backoff Strategy
  description: Exponential backoff with jitter; honor Retry-After.
- name: Limit Increase
  description: Submit a quota request via Alibaba Cloud console for higher RPM/TPM.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com