Rate Limits

Rate Limit Tiers

Tier	RPM (Requests/Min)	TPM (Tokens/Min)	Concurrency
Free (new signup)	20	50,000	2
Starter	60	200,000	5
Pro	300	1,000,000	20
Enterprise	Custom	Custom	Custom

Rate Limit Headers

Every response includes rate limit headers:

x-ratelimit-limit-requests: 60
x-ratelimit-remaining-requests: 58
x-ratelimit-reset-requests: 45s
x-ratelimit-limit-tokens: 200000
x-ratelimit-remaining-tokens: 189000
x-ratelimit-reset-tokens: 30s

Handling Rate Limits

When you hit a rate limit, the API returns 429 Too Many Requests. Implement exponential backoff:

import time
import random
from openai import OpenAI, RateLimitError

client = OpenAI(
    api_key="tsn_live_xxx",
    base_url="https://api.tokensupernova.com/v1",
)

def chat_with_retry(messages, model="deepseek-chat", max_retries=5):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model=model,
                messages=messages,
            )
        except RateLimitError:
            if attempt == max_retries - 1:
                raise
            delay = (2 ** attempt) + random.uniform(0, 1)
            time.sleep(delay)

Tips

Batch requests when possible instead of rapid-fire single requests
Cache responses for repeated prompts
Monitor headers to avoid hitting limits
Upgrade your tier for production workloads