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: ByteDance Doubao
providerId: doubao
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
- ByteDance
- Rate Limiting
description: >-
  Volcano Engine enforces per-endpoint RPM/TPM and concurrent quotas, configurable per
  workspace/endpoint. Limits visible in the Ark console.
notes: >-
  Doubao endpoints are bound to per-deployment quotas; reserved-instance customers receive
  guaranteed throughput. Exponential backoff is recommended on 429.
sources:
- https://www.volcengine.com/docs/82379
- https://console.volcengine.com/ark/
responseCodes:
  throttled: 429
limits:
- name: Per-Endpoint RPM
  scope: endpoint
  metric: requests-per-minute
  limit: see Ark console
  notes: Configurable per deployed model/endpoint.
- name: Per-Endpoint TPM
  scope: endpoint
  metric: tokens-per-minute
  limit: see Ark console
- name: Concurrency
  scope: endpoint
  metric: concurrent-requests
  limit: see Ark console
policies:
- name: Backoff Strategy
  description: Exponential backoff with jitter; honor Retry-After.
- name: Reserved Capacity
  description: Reserved-instance subscriptions guarantee throughput beyond shared quotas.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com