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-ai
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: partial
tags:
- AI
- Voice
- Agents
- Realtime
- Conversational
- Rate Limiting
- Quotas
- Throttling
description: >-
  Retell rate-limits primarily through concurrent call entitlements: 20 free concurrent calls
  with each additional concurrency slot priced at $8/month. Knowledge bases get the first 10
  free. Per-RPS HTTP rate limits are not publicly documented.
notes: Concurrency is the documented scaling lever; HTTP RPS quotas should be confirmed with Retell support.
sources:
- https://www.retellai.com/pricing
- https://docs.retellai.com/
responseCodes:
  throttled: 429
limits:
- name: Concurrent Calls (free tier)
  scope: account
  metric: concurrent_calls
  limit: 20
  notes: 20 free concurrent calls included by default.
- name: Concurrent Calls (add-on)
  scope: account
  metric: concurrent_calls
  limit: -1
  notes: Additional concurrency at $8.00/concurrency/month.
- name: Knowledge Bases (free)
  scope: account
  metric: knowledge_bases
  limit: 10
  notes: First 10 knowledge bases free.
- name: HTTP Requests
  scope: account
  metric: requests
  limit: not publicly documented
  notes: Verify with Retell support; standard 429 backoff applies.
policies:
- name: Backoff Strategy
  description: Clients should implement exponential backoff with jitter and honor any Retry-After header.
- name: Concurrency Provisioning
  description: Pre-purchase concurrency slots ahead of high-volume campaigns to avoid throttling.
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com