Rate Limits & Quotas

# You're on Scale plan (500K/month), spend cap left at the $500 default
# Usage: 550,000 requests this month -- $20 of overage so far

# Request still works, and is metered:
curl https://api.promptguard.co/api/v1/chat/completions \
  -H "X-API-Key: your_api_key" \
  -H "Authorization: Bearer YOUR_OPENAI_KEY" \
  -d '{"model": "gpt-5-nano", "messages": [...]}'

# Returns: 200 OK (not 429)
# Past 1,750,000 requests the next $0.40/1k would cross $500: 429 spending_limit_exceeded

Dashboard → Usage → Current Period
- Requests Used: 105,234 / 100,000
- Status: Over Quota (5,234 overage)
- Next Reset: January 15, 2025

curl https://api.promptguard.co/api/v1/usage/stats \
  -H "X-API-Key: your_api_key"

{
  "requests_used": 105234,
  "requests_limit": 100000,
  "overage": 5234,
  "reset_at": "2025-01-15T00:00:00Z"
}

HTTP/1.1 200 OK
X-RateLimit-Limit: 300
X-RateLimit-Reset: 1708128060

{
  "error": {
    "message": "Rate limit exceeded: your plan allows 300 requests per minute. Please retry later.",
    "type": "rate_limit_exceeded",
    "code": "rate_limit_exceeded",
    "retry_after": 42
  }
}

import time
import openai

def make_request_with_retry(prompt, max_retries=3):
    for attempt in range(max_retries):
        try:
            response = openai.ChatCompletion.create(
                model="gpt-5-nano",
                messages=[{"role": "user", "content": prompt}]
            )
            return response
        except openai.RateLimitError as e:
            if attempt < max_retries - 1:
                # Exponential backoff
                time.sleep(2 ** attempt)
            else:
                raise

curl -X POST https://api.promptguard.co/api/v1/chat/completions \
  -H "X-API-Key: your_api_key" \
  -H "Idempotency-Key: unique-request-id-12345" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5-nano", "messages": [...]}'

async function makeRequestWithBackoff(prompt, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    try:
      return await openai.chat.completions.create({
        model: "gpt-5-nano",
        messages: [{ role: "user", content: prompt }]
      });
    } catch (error) {
      if (error.status === 429 && i < maxRetries - 1) {
        await new Promise(resolve =>
          setTimeout(resolve, Math.pow(2, i) * 1000)
        );
      } else {
        throw error;
      }
    }
  }
}

# Check usage before making request
usage = client.get_usage()
if usage['requests_used'] > usage['requests_limit'] * 0.9:
    send_alert("Approaching monthly quota limit")

for prompt in prompts:
    response = openai.ChatCompletion.create(...)  # 100 API calls

# Combine prompts where appropriate
combined_prompt = "\n".join(prompts)
response = openai.ChatCompletion.create(
    messages=[{"role": "user", "content": combined_prompt}]
)  # 1 API call

import hashlib
import redis

cache = redis.Redis()

def get_cached_response(prompt):
    cache_key = hashlib.sha256(prompt.encode()).hexdigest()
    cached = cache.get(cache_key)

    if cached:
        return json.loads(cached)

    response = openai.ChatCompletion.create(...)
    cache.setex(cache_key, 3600, json.dumps(response))  # 1 hour TTL
    return response

curl https://api.promptguard.co/api/v1/usage/stats \
  -H "X-API-Key: your_api_key"

{
  "daily_usage": [
    {"date": "2025-10-11", "requests": 5234},
    {"date": "2025-10-10", "requests": 4892},
    ...
  ],
  "total": 35789,
  "limit": 100000,
  "remaining": 64211
}