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: Openlayer
providerId: openlayer
created: '2026-06-20'
modified: '2026-06-20'
reconciled: false
tags:
- AI
- Evaluation
- Testing
- Observability
- LLM
- MLOps
- Rate Limiting
- Quotas
- Throttling
description: >-
  The Openlayer REST API authenticates with a Bearer API key and meters usage
  primarily through plan-level quotas, most notably the monthly cap on
  production inferences (rows published to inference pipelines) on the Basic
  plan. Openlayer does not publish explicit per-endpoint request-per-minute or
  token-per-minute limits in its public API reference; specific throttling
  thresholds are not reconciled in this artifact.
notes: >-
  Verify any per-endpoint or per-account request limits, retry guidance, and
  429 handling against current Openlayer documentation and account settings on
  reconciliation. The Basic plan's 20,000 production inferences per month acts
  as the primary public usage ceiling; Enterprise removes usage caps.
sources:
- https://www.openlayer.com/pricing
- https://www.openlayer.com/docs/api-reference/rest/overview
- https://www.openlayer.com/docs/monitoring/publishing-data
responseCodes:
  throttled: 429
limits:
- name: Production Inferences (Basic plan)
  scope: account
  metric: inferences
  limit: 20000 per month
  notes: Rows published to inference pipelines; Basic plan cap. Enterprise is unlimited.
- name: Requests Per Minute (RPM)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Per-endpoint request rate limits are not published in the public API reference.
- name: Data Stream Throughput
  scope: inference_pipeline
  metric: rows
  limit: see provider documentation
  notes: Batch size and ingestion throughput for the data-stream endpoint are not publicly specified.
policies:
- name: API Key Authentication
  description: All requests require a Bearer API key in the Authorization header; quotas apply per workspace/account.
- name: Tiered Limits
  description: Usage ceilings are governed by plan; Basic has a monthly inference cap, Enterprise removes caps.
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com