Subscription & Billing

Subscription Tiers

CTGT API offers two tiers designed for different needs:

Free Tier

Perfect for getting started

3 AI models
20 req/min, 100 req/hour
500 req/day
100K tokens/day
Pay-as-you-go only
No credit card required

Paid Tier

For production applications

All 10 AI models
100 req/min, 1,000 req/hour
10,000 req/day
10M tokens/day
$10/month + usage
Priority support

Rate Limits Comparison

Limit	Free Tier	Paid Tier	Increase
Requests per minute	20	100	5x
Requests per hour	100	1,000	10x
Requests per day	500	10,000	20x
Tokens per day	100,000	10,000,000	100x
Available models	3	10	3.6x

Rate limits reset at the start of each time period (minute, hour, day).

Check Your Subscription

View your current subscription status and limits:

curl https://api.ctgt.ai/v1/subscription/info \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Response (Free Tier):

{
  "user_id": "user_abc123",
  "email": "john@example.com",
  "subscription_tier": "free",
  "stripe_customer_id": "cus_abc123",
  "rate_limits": {
    "requests_per_minute": 20,
    "requests_per_hour": 100,
    "requests_per_day": 500,
    "tokens_per_day": 100000
  },
  "available_models": [
    {
      "model": "gemini-2.5-flash",
      "display_name": "Gemini 2.5 Flash",
      "description": "Fast and efficient model",
      "tier": "free",
      "pricing": {
        "input": 0.50,
        "output": 2.70
      }
    }
  ],
  "upgrade_url": "https://ctgt.ai/pricing"
}

Response (Paid Tier):

{
  "user_id": "user_abc123",
  "email": "john@example.com",
  "subscription_tier": "paid",
  "stripe_customer_id": "cus_abc123",
  "rate_limits": {
    "requests_per_minute": 100,
    "requests_per_hour": 1000,
    "requests_per_day": 10000,
    "tokens_per_day": 10000000
  },
  "available_models": [
    // All 10 models listed
  ],
  "upgrade_url": null
}

Upgrading to Paid Tier

Step 1: Initiate Upgrade

curl -X POST https://api.ctgt.ai/v1/subscription/upgrade \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Response:

{
  "message": "Checkout session created. Complete payment to upgrade.",
  "checkout_url": "https://checkout.stripe.com/c/pay/cs_test_abc123...",
  "session_id": "cs_test_abc123",
  "tier": "free"
}

Step 2: Complete Payment

Visit the checkout_url in your browser
Complete the Stripe checkout process
Your tier will be automatically upgraded to “paid”

The upgrade takes effect immediately after successful payment. No need to restart your application.

Step 3: Verify Upgrade

curl https://api.ctgt.ai/v1/subscription/info \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Look for:

{
  "subscription_tier": "paid",
  "rate_limits": {
    "requests_per_minute": 100,
    ...
  }
}

Downgrading to Free Tier

You can downgrade to free tier at any time:

curl -X POST https://api.ctgt.ai/v1/subscription/downgrade \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Response:

{
  "message": "Successfully downgraded to free tier",
  "tier": "free"
}

Downgrading will:

Reduce rate limits immediately
Restrict access to only 3 free-tier models
Cancel your monthly subscription
Billing remains pay-as-you-go for usage

Billing & Usage

View Current Usage

Monitor your token consumption and costs in real-time:

curl https://api.ctgt.ai/v1/billing/usage \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Response:

{
  "user_id": "user_abc123",
  "email": "john@example.com",
  "period": {
    "start": "2025-12-01T00:00:00Z",
    "end": "2025-12-31T23:59:59Z"
  },
  "usage": {
    "total_requests": 1234,
    "total_tokens": 567890,
    "total_cost_usd": 12.45,
    "by_model": {
      "gemini-2.5-flash": {
        "requests": 800,
        "prompt_tokens": 120000,
        "completion_tokens": 80000,
        "cost_usd": 4.20
      },
      "claude-sonnet-4-5-20250929": {
        "requests": 434,
        "prompt_tokens": 200000,
        "completion_tokens": 167890,
        "cost_usd": 8.25
      }
    }
  }
}

View Billing History

Get historical billing data for a date range:

curl "https://api.ctgt.ai/v1/billing/history?start_date=2025-11-01&end_date=2025-12-01" \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Generate Invoice

Request an invoice for your usage:

curl -X POST https://api.ctgt.ai/v1/billing/generate-invoice \
  -H "Authorization: Bearer sk-ctgt-YOUR_API_KEY"

Response:

{
  "message": "Invoice generated and sent",
  "usage": {
    "total_tokens": 567890,
    "total_cost_usd": 12.45
  },
  "invoice_id": "in_abc123",
  "amount_usd": 12.45
}

Rate Limit Headers

Every API response includes rate limit information in the headers:

X-RateLimit-Limit: 100
X-RateLimit-Remaining: 95
X-RateLimit-Reset: 1702847523

Headers explained:

X-RateLimit-Limit: Maximum requests allowed in the current window
X-RateLimit-Remaining: Requests remaining in current window
X-RateLimit-Reset: Unix timestamp when the limit resets

Example: Checking Rate Limits

import requests

response = requests.post(
    "https://api.ctgt.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {api_key}"},
    json={"model": "gemini-2.5-flash", "messages": [...]}
)

print(f"Limit: {response.headers.get('X-RateLimit-Limit')}")
print(f"Remaining: {response.headers.get('X-RateLimit-Remaining')}")
print(f"Resets at: {response.headers.get('X-RateLimit-Reset')}")

Handling Rate Limits

When you exceed your rate limits: Status Code: 429 Too Many Requests Response:

{
  "detail": "Rate limit exceeded. Please try again later."
}

Best Practices

Implement Exponential Backoff

import time
import requests

def make_request_with_retry(url, headers, data, max_retries=5):
    for attempt in range(max_retries):
        response = requests.post(url, headers=headers, json=data)
        
        if response.status_code == 429:
            wait_time = 2 ** attempt  # Exponential backoff
            print(f"Rate limited. Waiting {wait_time}s...")
            time.sleep(wait_time)
            continue
        
        return response
    
    raise Exception("Max retries exceeded")

Monitor Your Rate Limit Headers

def monitor_rate_limits(response):
    remaining = int(response.headers.get('X-RateLimit-Remaining', 0))
    
    if remaining < 10:
        print(f"Warning: Only {remaining} requests remaining!")
    
    if remaining == 0:
        reset_time = int(response.headers.get('X-RateLimit-Reset', 0))
        wait_seconds = reset_time - time.time()
        print(f"Rate limit exhausted. Waiting {wait_seconds}s")
        time.sleep(wait_seconds)

Cache Responses When Possible

from functools import lru_cache
import hashlib
import json

@lru_cache(maxsize=1000)
def cached_api_call(prompt_hash):
    # Make actual API call
    response = requests.post(...)
    return response.json()

def get_completion(prompt):
    # Create hash of prompt for caching
    prompt_hash = hashlib.md5(prompt.encode()).hexdigest()
    return cached_api_call(prompt_hash)

Batch Similar Requests

# Instead of 100 individual requests
for item in items:
    result = api_call(item)

# Batch into fewer requests with multiple items
for batch in chunks(items, 10):
    results = api_call_batch(batch)

Pro tip: Upgrade to paid tier for 5-100x higher rate limits if you’re consistently hitting limits.

Cost Management

Setting Budget Alerts

Monitor your spending with the usage endpoint:

import requests

def check_budget_alert(api_key, monthly_budget=100):
    url = "https://api.ctgt.ai/v1/billing/usage"
    headers = {"Authorization": f"Bearer {api_key}"}
    
    response = requests.get(url, headers=headers)
    usage = response.json()
    
    current_cost = usage['usage']['total_cost_usd']
    
    if current_cost > monthly_budget * 0.8:
        print(f"⚠️ Warning: Used ${current_cost:.2f} of ${monthly_budget} budget")
    
    if current_cost > monthly_budget:
        print(f"🚨 Alert: Budget exceeded! ${current_cost:.2f} / ${monthly_budget}")
        return False
    
    return True

Optimize Costs

Choose the Right Model

Use cheaper models for simple tasks:

Gemini Flash Lite: $0.30 input
GPT-5 Nano: $0.25 input

Control Token Limits

Set max_tokens to limit response length:

{"max_tokens": 500}

Optimize Prompts

Shorter prompts = lower costs:

Be concise
Remove unnecessary context
Use system prompts efficiently

Cache Common Responses

Store and reuse responses for:

FAQ answers
Common queries
Static content

Pricing Summary

Monthly Subscription

Tier	Monthly Fee	What’s Included
Free	$0	3 models, basic limits
Paid	$10	All 10 models, 100x limits

Usage Costs (Pay-as-you-go)

Both tiers pay for token usage at the same rates:

Model Category	Input (per 1M)	Output (per 1M)
Most Affordable	$0.25 -$ 0.50	$0.60 -$ 2.70
Mid-Range	$1.20 -$ 4.00	$5.20 -$ 14.00
Premium	$5.00 -$ 10.00	$17.00 -$ 30.00

See the Models & Pricing page for complete pricing details.

Example Cost Scenarios

Scenario 1: Small Project (Free Tier)

Usage:

500 requests/day
Average 100 input + 300 output tokens per request
Using Gemini 2.5 Flash

Monthly Cost:

Input: 500 × 30 × 100 tokens = 1.5M tokens = $0.75
Output: 500 × 30 × 300 tokens = 4.5M tokens = $12.15
Total: $12.90/month (usage only, no subscription)

Scenario 2: Medium Project (Paid Tier)

Usage:

5,000 requests/day
Average 200 input + 500 output tokens per request
Mix of Gemini Flash and GPT-5

Monthly Cost:

Subscription: $10
Usage: ~$150-200
Total: $160-210/month

Scenario 3: Large Project (Paid Tier)

Usage:

50,000 requests/day
Using advanced models (Claude Sonnet, GPT-5.2)
Complex queries with higher token counts

Monthly Cost:

Subscription: $10
Usage: ~$1,500-2,500
Total: $1,510-2,510/month

All scenarios assume normal usage patterns. Your costs may vary based on actual token consumption.

Next Steps

View All Models

Compare all 10 models and their pricing

API Features

Learn about streaming, temperature control, and more

Code Examples

See complete SDK implementations

Chat Completions

Full API reference documentation

Overview

API Features

Endpoints

​Subscription Tiers

Free Tier

Paid Tier

​Rate Limits Comparison

​Check Your Subscription

​Upgrading to Paid Tier

​Step 1: Initiate Upgrade

​Step 2: Complete Payment

​Step 3: Verify Upgrade

​Downgrading to Free Tier

​Billing & Usage

​View Current Usage

​View Billing History

​Generate Invoice

​Rate Limit Headers

​Example: Checking Rate Limits

​Handling Rate Limits

​Best Practices

​Cost Management

​Setting Budget Alerts

​Optimize Costs

Choose the Right Model

Control Token Limits

Optimize Prompts

Cache Common Responses

​Pricing Summary

​Monthly Subscription

​Usage Costs (Pay-as-you-go)

​Example Cost Scenarios

​Scenario 1: Small Project (Free Tier)

​Scenario 2: Medium Project (Paid Tier)

​Scenario 3: Large Project (Paid Tier)

​Next Steps

View All Models

API Features

Code Examples

Chat Completions

Subscription Tiers

Rate Limits Comparison

Check Your Subscription

Upgrading to Paid Tier

Step 1: Initiate Upgrade

Step 2: Complete Payment

Step 3: Verify Upgrade

Downgrading to Free Tier

Billing & Usage

View Current Usage

View Billing History

Generate Invoice

Rate Limit Headers

Example: Checking Rate Limits

Handling Rate Limits

Best Practices

Cost Management

Setting Budget Alerts

Optimize Costs

Pricing Summary

Monthly Subscription

Usage Costs (Pay-as-you-go)

Example Cost Scenarios

Scenario 1: Small Project (Free Tier)

Scenario 2: Medium Project (Paid Tier)

Scenario 3: Large Project (Paid Tier)

Next Steps