kraken-rate-limits

kraken-rate-limits

Use this skill for:

• understanding Kraken's rate limit systems (Spot REST, trading engine, Futures)
• adapting agent behavior when rate limit errors occur
• choosing optimal request patterns (WebSocket vs REST, batch vs individual)

How Rate Limiting Works

The CLI does not pre-throttle or retry rate-limited requests. The Kraken API server enforces rate limits. When a limit is hit, the CLI returns the error immediately with structured fields:

{
  "error": "rate_limit",
  "message": "Spot REST API rate limit exceeded ...",
  "suggestion": "Wait 5-15 seconds before retrying. ...",
  "retryable": true,
  "docs_url": "https://docs.kraken.com/api/docs/guides/spot-rest-ratelimits/"
}

Read the suggestion field to understand what limit was hit and how to adapt.

Kraken's Rate Limit Systems

1. Spot REST Counter

Counter-decay model. Each call adds to a counter; the counter decays over time.

Tier	Max Counter	Decay Rate
Starter	15	0.33/s
Intermediate	20	0.5/s
Pro	20	1.0/s

Most calls cost 1 point. Ledgers, trade history, and query-ledgers cost 2. AddOrder and CancelOrder are excluded from this counter (they use the trading engine limiter instead).

Docs: https://docs.kraken.com/api/docs/guides/spot-rest-ratelimits/

2. Spot Trading Engine (per-pair)

Separate per-pair counter with penalties for short-lived orders:

Tier	Threshold	Decay Rate
Starter	60	1/s
Intermediate	125	2.34/s
Pro	180	3.75/s

Cancel within 5 seconds costs +8, amend within 5 seconds costs +3. Let orders rest longer to reduce cost.

Docs: https://docs.kraken.com/api/docs/guides/spot-ratelimits

3. Futures Cost Budget

Cost-based system with two separate pools:

• /derivatives endpoints: budget of 500 per 10 seconds. sendorder costs 10, editorder costs 10, cancelorder costs 10, batchorder costs 9 + batch size, cancelallorders costs 25, accounts costs 2.
• /history endpoints: pool of 100 tokens, refills at 100 per 10 minutes.