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: Raycast
providerId: raycast
created: '2026-06-20'
modified: '2026-06-20'
reconciled: false
tags:
- Productivity
- Launcher
- Extensions
- SDK
- AI
- Rate Limiting
- Quotas
description: >-
  Raycast's developer surface is the @raycast/api SDK rather than a metered
  HTTP API, so there is no public per-request RPM/TPM rate-limit table. The
  practical limits that exist are subscription quotas - the number of AI
  messages included per plan - and AI model fair-use limits enforced inside
  the app. SDK modules (Storage, Cache, OAuth, etc.) run locally and are not
  network rate-limited by Raycast. Specific AI fair-use values are not
  reconciled in this artifact.
notes: >-
  Because the interface is an SDK and not a public REST API, classic API rate
  limiting (429 responses, RPM/TPM headers) does not apply. Verify current AI
  message allowances and any fair-use throttling on the pricing page and in
  the AI reference at reconciliation time.
sources:
- https://www.raycast.com/pricing
- https://developers.raycast.com/api-reference/ai
responseCodes:
  throttled: n/a (SDK, not HTTP REST)
limits:
- name: AI Messages (Free)
  scope: account
  metric: messages
  limit: 50 per month
  notes: Included AI message allowance on the Free plan; AI is accessed via the SDK AI.ask, not a public endpoint.
- name: AI Messages (Pro / Teams)
  scope: account
  metric: messages
  limit: see provider documentation
  notes: Paid plans raise AI allowances; Advanced AI add-on unlocks frontier models with higher fair-use limits.
- name: AI Model Fair Use
  scope: account
  metric: requests
  limit: fair-use, enforced in-app
  notes: Raycast applies fair-use throttling on AI model access; not exposed as documented per-request quotas.
- name: SDK Module Calls
  scope: device
  metric: calls
  limit: not network rate-limited
  notes: Storage, Cache, Clipboard, Preferences, OAuth and UI modules execute locally inside the extension process.
policies:
- name: Subscription Quotas
  description: AI usage is gated by plan tier (Free / Pro / Teams / Advanced AI) rather than per-request API limits.
- name: Fair Use
  description: AI model access is subject to in-app fair-use enforcement; abuse can be throttled at the account level.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com