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: Retell AI
providerId: retell
created: '2026-07-01'
modified: '2026-07-01'
reconciled: false
tags:
- AI
- Voice
- Voice Agents
- Telephony
- Rate Limiting
- Concurrency
- Quotas
- Throttling
description: >-
  Retell AI's primary throttling mechanism is call concurrency - the maximum
  number of simultaneous calls an organization can run. Each org has a base
  (free) concurrency limit plus optionally purchased concurrency, and an
  optional burst mode. When concurrency is exhausted, new outbound calls
  (including batch-call jobs) queue or are rejected until a slot frees up.
  Current and maximum concurrency are readable via GET /get-concurrency. The
  management REST endpoints (agents, LLMs, phone numbers, calls) are also
  subject to standard per-account request rate limits; exact per-endpoint RPS
  values are not published and are not reconciled in this artifact.
notes: >-
  Verify base and purchased concurrency for the account via GET /get-concurrency
  and the Retell dashboard on reconciliation. Concurrency limits scale with plan
  and can be increased by purchasing additional slots or via Enterprise
  agreements.
sources:
- https://docs.retellai.com/api-references/get-concurrency
- https://docs.retellai.com/
- https://www.retellai.com/pricing
responseCodes:
  throttled: 429
limits:
- name: Call Concurrency (Base)
  scope: account
  metric: concurrent_calls
  limit: '20'
  notes: Default free concurrency allotment per organization; readable as base_concurrency.
- name: Call Concurrency (Purchased)
  scope: account
  metric: concurrent_calls
  limit: see provider documentation
  notes: Additional concurrent-call slots purchased on top of the base allotment; readable as purchased_concurrency.
- name: Concurrency Burst
  scope: account
  metric: concurrent_calls
  limit: see provider documentation
  notes: Optional burst mode allowing a temporary higher concurrency ceiling (concurrency_burst_limit) when enabled.
- name: Reserved Inbound Concurrency
  scope: account
  metric: concurrent_calls
  limit: see provider documentation
  notes: Portion of concurrency reserved specifically for inbound calls so campaigns do not starve incoming traffic.
- name: Management API Requests
  scope: account
  metric: requests
  limit: see provider documentation
  notes: Standard per-account request limits on REST management endpoints (agents, LLMs, phone numbers, calls); not publicly enumerated.
policies:
- name: Concurrency-Gated Calling
  description: Outbound and batch calls consume concurrency slots; when the limit is reached, jobs queue until slots free.
- name: Tiered Limits
  description: Concurrency raises with plan tier and via purchased slots or Enterprise agreements.
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter on 429 responses and honor Retry-After where present.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com