Rate Limit Calculator
Check if your usage fits within API rate limits for different LLM providers and tiers.
Your Expected Usage
How many requests you'll make per minute
Average tokens per request (input + output)
Total Tokens Per Minute: 100,000
Requests Per Day (24/7): 144,000
| Model | Provider | Tier | RPM Limit | TPM Limit | RPD Limit | Status |
|---|---|---|---|---|---|---|
GPT-4o | OpenAI | Free | 3 3333% used | 40,000 250% used | 200 | Exceeded |
GPT-4o | OpenAI | Tier 1 | 500 20% used | 800,000 13% used | 10,000 | OK |
GPT-4 Turbo | OpenAI | Tier 1 | 500 20% used | 300,000 33% used | 10,000 | OK |
GPT-3.5 Turbo | OpenAI | Tier 1 | 3,500 3% used | 200,000 50% used | 10,000 | OK |
GPT-4o | OpenAI | Tier 2 | 5,000 2% used | 2,000,000 5% used | 10,000 | OK |
Claude 3.5 Sonnet | Anthropic | Tier 1 | 50 200% used | 40,000 250% used | 1,000 | Exceeded |
Claude 3.5 Sonnet | Anthropic | Tier 2 | 1,000 10% used | 80,000 125% used | 10,000 | Exceeded |
Claude 3 Haiku | Anthropic | Tier 1 | 50 200% used | 50,000 200% used | 1,000 | Exceeded |
Gemini 1.5 Pro | Free | 2 5000% used | 32,000 313% used | 50 | Exceeded | |
Gemini 1.5 Flash | Free | 15 667% used | 1,000,000 10% used | 1,500 | Exceeded |
Understanding Rate Limits
- RPM: Requests Per Minute - Maximum number of API calls per minute
- TPM: Tokens Per Minute - Maximum number of tokens (input + output) per minute
- RPD: Requests Per Day - Maximum number of API calls per 24 hours
- Rate limits vary by provider tier - higher tiers have higher limits
- Implement exponential backoff and retry logic to handle rate limit errors