Rime · Rate Limits

Rime Ai Rate Limits

Rime caps capacity primarily through concurrent generation slots tied to plan tier and via per-tier custom voice clone caps. HTTP 429 backoff applies; specific RPS limits not public.

Rime Ai Rate Limits is the machine-readable rate-limit profile for Rime on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 5 rate-limit definitions, measuring concurrent_generations, voice_clones, and requests.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, Voice, TTS, Realtime, and Conversational.

5 Limits Throttle: 429
AIVoiceTTSRealtimeConversationalRate LimitingQuotasThrottling

Limits

Concurrent Generations (Pay as You Go) account
concurrent_generations
5
Concurrent Generations (Growth) account
concurrent_generations
20
Concurrent Generations (Scale) account
concurrent_generations
-1
Unlimited / negotiated.
Custom Voice Clones (Growth) account
voice_clones
2
HTTP Requests account
requests
not publicly documented

Policies

Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Concurrency Provisioning
Upgrade tier when concurrent generation usage approaches plan cap.

Sources