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: Pieces
providerId: pieces
created: '2026-06-20'
modified: '2026-06-20'
reconciled: false
tags:
- AI
- Developer Tools
- On-Device
- Local API
- Long-Term Memory
- Rate Limiting
- Quotas
- Throttling
description: >-
  The Pieces OS API is served on-device over the loopback interface
  (http://localhost:1000) and does not impose conventional per-account
  HTTP rate limits the way a hosted cloud API would. Throughput for local
  model inference is bounded by the host machine's CPU, GPU, and memory.
  Where Copilot requests are routed to cloud models, usage limits follow the
  account's plan tier (Free has limited cloud usage; Pro is unlimited), and
  the upstream cloud model provider's own limits apply. Specific numeric
  limits are not documented for the local API and are not reconciled here.
notes: >-
  Because the transport is on-device, the practical limit is local hardware,
  not a published RPM/TPM quota. Cloud-routed Copilot usage is gated by plan
  tier rather than a documented rate-limit table. Verify any cloud-side limits
  against the Pieces paid-plans page on reconciliation.
sources:
- https://docs.pieces.app/products/core-dependencies/pieces-os
- https://docs.pieces.app/products/paid-plans
responseCodes:
  throttled: 429
limits:
- name: Local API Requests
  scope: device
  metric: requests
  limit: bounded by local hardware
  notes: No documented HTTP rate limit; throughput depends on the host machine.
- name: Local Model Inference
  scope: device
  metric: tokens
  limit: bounded by local CPU/GPU/memory
  notes: On-device LLM throughput is hardware-bound, not quota-bound.
- name: Cloud Model Usage (Free)
  scope: account
  metric: requests
  limit: limited (see plan)
  notes: Free tier includes limited usage of select cloud models.
- name: Cloud Model Usage (Pro)
  scope: account
  metric: requests
  limit: unlimited (per plan)
  notes: Pro tier provides unlimited premium cloud model usage; upstream provider limits may still apply.
policies:
- name: On-Device Transport
  description: The API binds to localhost; it is not exposed to the network, so limits are local rather than tenant-based.
- name: Plan-Gated Cloud Usage
  description: Cloud-routed Copilot usage is governed by the account plan (Free limited, Pro unlimited) rather than a documented rate-limit table.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com