Vapi · Rate Limits
Vapi Rate Limits
Vapi documents concurrency limits per account and applies standard 429 throttling on the REST API. Concurrent call limits scale with plan/contract; specific RPS quotas are not publicly documented and should be confirmed with Vapi support.
Vapi Rate Limits is the machine-readable rate-limit profile for Vapi on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 2 rate-limit definitions, measuring concurrent_calls 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 CPaaS.
2 Limits
Throttle: 429
AIVoiceAgentsRealtimeCPaaSRate LimitingQuotasThrottling
Limits
Concurrent Calls account
scales by plan; contact support for higher concurrency
Vapi enforces a per-account concurrent active call cap.
API Requests account
not publicly documented
Standard 429 backoff applies; verify limits with Vapi support before high-volume integrations.
Policies
Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header on 429 responses.
Concurrency Planning
Provision concurrent call capacity in advance for outbound campaigns and high-volume inbound use cases.
Sources
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.