cohere · Rate Limits
Cohere Rate Limits
Cohere API rate limits per API key, varies by trial vs production key.
Cohere Rate Limits is the machine-readable rate-limit profile for cohere on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 5 rate-limit definitions, measuring requests_per_minute.
The profile also includes response codes documented for throttled.
Tagged areas include Rate Limiting and AI.
5 Limits
Throttle: 429
Rate LimitingAI
Limits
Trial key (Chat) key
20
Trial key (Embed) key
100
Production (Chat) key
10000
Production (Embed) key
2000
Production (Rerank) key
10000