Rate limits

Limits are enforced per-account and per-key. Every response carries X-RateLimit-Remaining headers.

Per-plan limits

Plan	RPM	TPM
Starter	60	30K
Builder	300	150K
Team	600	300K
Creative	300	150K
Business	Custom	Custom

RPM = requests/min; TPM = tokens/min (input + output). Need higher? Email hello@sealink.asia.

Response headers

Header	Meaning
X-RateLimit-Limit-Requests	Per-minute RPM ceiling
X-RateLimit-Remaining-Requests	Remaining for this minute
X-RateLimit-Reset-Requests	Seconds until reset
Retry-After	Returned on 429; wait at least this many seconds

Recommended retry pattern

Exponential backoff with jitter, capped at 5-6 attempts. Retries on 429 don't count against your quota.

Python

import time, random
from openai import OpenAI, APIStatusError

client = OpenAI(base_url="https://api.sealink.asia/v1", api_key="<your-sealink-key>")

def call_with_backoff(messages, model="claude-haiku-4-5", max_attempts=6):
    for attempt in range(max_attempts):
        try:
            return client.chat.completions.create(model=model, messages=messages)
        except APIStatusError as e:
            if e.status_code != 429 or attempt == max_attempts - 1:
                raise
            sleep_s = min(60, 2 ** attempt) + random.random()
            time.sleep(sleep_s)