Source: Anthropic API rate limits docs
Anthropic's rate-limit reference: token-bucket RPM/ITPM/OTPM limits per tier, cache-aware ITPM, ramp limits, spend caps, and the 429 / retry-after / anthropic-ratelimit-* header contract.
Contents
- What: official API documentation
- Publisher: Anthropic
- Date: living docs, read 2026-11-14
- Original: platform.claude.com/docs/en/api/rate-limits
Summary
Explains how Claude API limits are enforced and signalled, which is the contract any gateway retry or fallback policy has to respect.
Key claims
- Limits are per organisation and per model class: requests per minute, input tokens per minute (ITPM) and output tokens per minute (OTPM), enforced with a token bucket that refills continuously; short bursts can trip a per-minute limit.
- Exceeding a limit returns 429 naming the limit; when a
retry-afterheader is present, wait that many seconds. - Cache-aware ITPM: tokens read from the prompt cache do not count toward ITPM (e.g. 2M ITPM at 80% cache hit rate allows about 10M total input tokens/min).
- Ramp limits: a sharp usage increase can 429 below the rate limit (
error_code: ramp_limit_exceeded); wait at least theretry-afterseconds, then ramp up by at most one step per minute. Cache reads do not count toward ramp limits, and the Message Batches API is exempt. - Monthly spend caps per tier also return 429
rate_limit_errorbut with noretry-afteranderror_code: enforced_spend_limit_reached; retrying does not help. A lower spend limit that the organisation sets itself returns HTTP 400invalid_request_errorinstead of 429. - OTPM counts only output tokens actually generated, evaluated in real time;
max_tokensdoes not factor into OTPM, so a highmax_tokenshas no rate-limit downside. - Fast mode (
speed: "fast", on Fable 5.2, Mythos 5.2, Opus 5.5 and some older Opus models) has dedicated rate limits and its own ramp limits, separate from standard usage. - Headers
anthropic-ratelimit-{requests,tokens,input-tokens,output-tokens}-{limit,remaining,reset}expose remaining capacity.