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: Not Diamond
providerId: notdiamond
created: '2026-06-20'
modified: '2026-06-20'
reconciled: false
tags:
- AI
- LLM
- Model Routing
- Router
- Orchestration
- Rate Limiting
- Quotas
- Throttling
description: >-
  Not Diamond does not publicly document specific request or token rate limits
  for its REST API. Access is gated by API key and account tier (Early Access vs.
  Enterprise). The router adds roughly 100-200 ms of latency per routing decision.
  Specific per-account RPM/TPM values are not reconciled in this artifact.
notes: >-
  No published rate-limit table was found on the Not Diamond docs or pricing
  pages. Confirm per-account limits and throttling behavior with Not Diamond on
  reconciliation.
sources:
- https://docs.notdiamond.ai
- https://www.notdiamond.ai/pricing
responseCodes:
  throttled: 429
limits:
- name: Requests Per Minute (RPM)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Not publicly documented; varies by account tier.
- name: Tokens Per Minute (TPM)
  scope: account
  metric: tokens
  limit: see provider documentation
  notes: Not publicly documented; routing billed per 1M tokens.
- name: Router Latency
  scope: request
  metric: milliseconds
  limit: ~100-200 ms per routing decision
  notes: Average additional latency added by the router, not a throttling limit.
policies:
- name: Tiered Access
  description: Limits and capabilities differ between Early Access and Enterprise tiers.
- 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