DictionaryToken Economics
Rate Limit
A speed limit on how many requests or tokens you can send per minute; go over it and you must wait.
Definition
A cap on how much an organization can use an API over time. The Claude API measures requests per minute (RPM), input tokens per minute (ITPM), and output tokens per minute (OTPM) per model with a continuously refilling token bucket; exceeding one returns a 429 error with a retry-after header. For most Claude models only uncached input tokens count toward ITPM, so prompt caching raises effective throughput.
Example
With a 2M ITPM limit and an 80% cache hit rate, you can process about 10M total input tokens per minute, since cache reads do not count.