generated: '2026-07-17'
method: searched
source: https://www.alloovium.com/en/developers/rate-limits
model: token-bucket, tier-based
tiers:
- {tier: Free, tokens_per_minute: 10, burst_capacity: 20}
- {tier: Standard, tokens_per_minute: 60, burst_capacity: 120}
- {tier: Pro, tokens_per_minute: 300, burst_capacity: 600}
- {tier: Enterprise, tokens_per_minute: 1500, burst_capacity: 3000}
headers:
- {name: X-RateLimit-Limit, description: Maximum burst capacity}
- {name: X-RateLimit-Remaining, description: Tokens available after the call}
- {name: X-RateLimit-Reset, description: Unix timestamp for full bucket restoration}
- {name: X-RateLimit-Cost, description: Tokens deducted by this request}
- {name: Retry-After, description: Seconds to wait before retrying (429 only)}
throttled_response:
  status: 429
  code: rate_limited
  body:
    type: https://api.alloovium.com/errors/rate_limited
    title: Rate limit exceeded
    status: 429
    code: rate_limited
    retry_after_seconds: 12
retry_strategy: On 429, sleep for Retry-After seconds and retry, using an Idempotency-Key to avoid duplicate execution.
notes: >-
  Individual operations cost a variable number of tokens (e.g. vault_search 5, chat_ask 10,
  workflows_run 25) — see mcp/alloovium-mcp.yml for per-tool costs.