LLM Cost Estimator
Compare API costs across models. Enter your usage and see which model fits your budget.
Sorted cheapest first · Prices per 1M tokens
| Model | Per req | Monthly total |
|---|---|---|
| Gemini 1.5 FlashGooglecheapest | $0.000225 | $0.2250 |
| Gemini 2.0 FlashGoogle | $0.000300 | $0.3000 |
| Llama 3.3 70BMeta/OSS | $0.000430 | $0.4300 |
| GPT-4o miniOpenAI | $0.000450 | $0.4500 |
| Claude Haiku 3.5Anthropic | $0.002800 | $2.80 |
| o1 miniOpenAI | $0.003300 | $3.30 |
| Gemini 1.5 ProGoogle | $0.003750 | $3.75 |
| Mistral LargeMistral | $0.005000 | $5.00 |
| GPT-4oOpenAI | $0.007500 | $7.50 |
| Claude Sonnet 4Anthropic | $0.0105 | $10.50 |
| GPT-4 TurboOpenAI | $0.0250 | $25.00 |
| o1OpenAI | $0.0450 | $45.00 |
| Claude Opus 4Anthropic | $0.0525 | $52.50 |
Prices are approximate and change frequently. Always verify with provider pricing pages before production use.
Deploy AI agents
Build and deploy production-ready AI agents.
About This Tool
Estimate the cost of using large language models (LLMs) based on various parameters such as model size, API calls, and usage duration.
Input details like model type, number of requests per day, and average response length to get an estimate of your monthly costs. The tool supports multiple LLM providers.
This utility runs entirely in your browser with no data stored or transmitted.