Retell AI · Rate Limits
Retell Ai Rate Limits
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.
Retell Ai Rate Limits is the machine-readable rate-limit profile for Retell AI on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 4 rate-limit definitions, measuring concurrent_calls, knowledge_bases, and requests.
The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.
Tagged areas include AI, Voice, Agents, Realtime, and Conversational.
4 Limits
Throttle: 429
AIVoiceAgentsRealtimeConversationalRate LimitingQuotasThrottling
Limits
Concurrent Calls (free tier) account
20
20 free concurrent calls included by default.
Concurrent Calls (add-on) account
-1
Additional concurrency at $8.00/concurrency/month.
Knowledge Bases (free) account
10
First 10 knowledge bases free.
HTTP Requests account
not publicly documented
Verify with Retell support; standard 429 backoff applies.
Policies
Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Concurrency Provisioning
Pre-purchase concurrency slots ahead of high-volume campaigns to avoid throttling.