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: Inflection AI
providerId: inflection
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: false
tags:
- AI
- LLM
- Personal AI
- Pi
- Foundation Models
- Rate Limiting
- Quotas
- Throttling
description: >-
  Inflection AI's Developer API exposes a usage dashboard at
  developers.inflection.ai/usage that surfaces account-level rate-limit
  consumption. The exact RPM / TPM values per model and tier are not
  publicly documented and are pending reconciliation; in practice they
  are set per contract.
notes: >-
  Verify in the Inflection developer console for the active account.
  On-premise enterprise servers are bounded by hardware capacity rather
  than shared-cloud limits.
sources:
- https://developers.inflection.ai/
- https://inflection.ai/
responseCodes:
  throttled: 429
limits:
- name: Requests Per Minute (RPM)
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Per-model RPM, varies by contract. Pending reconciliation.
- name: Tokens Per Minute (TPM)
  scope: account
  metric: tokens
  limit: see provider documentation
  notes: Per-model TPM, varies by contract. Pending reconciliation.
- name: On-Premise Throughput
  scope: deployment
  metric: requests
  limit: bounded by purpose-built server capacity
  notes: On-premise deployments are limited by the configured server hardware.
policies:
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor Retry-After.
- name: Tiered Limits
  description: Higher limits unlocked through Enterprise contract.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com