About LLM Pricing Calc
LLM Pricing Calc is a free, independent toolkit for developers, founders and finance teams who need to know what an AI feature will cost before it ships.
Most pricing calculators multiply tokens by a price and stop there. Real bills depend on context that grows every turn, prompt cache hit rates, batch discounts, hidden reasoning tokens, and whether you'd be better off renting a GPU. We model all of that in one place:
- LLM API & Agent Cost Calculator: 35 models, multi-turn agents, caching and batch.
- GPU & VRAM Calculator: weights + KV cache + overhead, with hardware fit badges.
- Voice Agent Cost Calculator: STT + LLM + TTS + telephony per minute.
- API vs Self-Hosting Break-Even: when a dedicated GPU beats per-token pricing.
How we source prices
API prices come from each provider's official pricing page and are stored in an open, versioned data file. Every calculator shows when prices were last verified. Rates that are typical market estimates, such as GPU rental and voice providers, are labelled as estimates. Prices change often, so always confirm with the provider before committing to a budget.
Privacy by design
All calculations run in your browser. Your inputs are never sent to our servers; shareable links simply encode your inputs in the URL.
Independence
We are not affiliated with Anthropic, OpenAI, Google, DeepSeek, xAI, Meta, NVIDIA, Apple or any provider listed. The site may display advertising to cover hosting costs; advertisers have no influence over our numbers.
Spotted a wrong price or a missing model? Tell us.