LLM pricing guides
Plain-English, provider-agnostic guides to understanding and lowering your AI costs. Every guide links back to the live calculator so you can check today's numbers.
AI agent costs
Why agents burn 5–30× more tokens than chatbots, a worked cost example, and how to cut the bill 50–70%.
Read →LLM API Pricing Guide
How per-token pricing works across the major providers, with example costs for common workloads.
Read →What is a token?
Tokens explained in plain English, how they map to words, and why input and output are priced differently.
Read →Cheapest LLM API in 2026
How the budget tier is priced, the trade-offs to watch, and how to find today's lowest cost per token.
Read →GPT vs Claude vs Gemini
How the three big families price their APIs, what moves your bill, and how to compare them live.
Read →How to cut your LLM API costs
Seven proven tactics, from controlling output length to caching and batching, to lower your bill.
Read →Subscriptions vs API
Compare ChatGPT, Claude and Gemini plans, and find whether a subscription or the API is cheaper for you.
Open tool →Token counter
Paste any text to estimate its token count and what it costs as input across live model prices.
Open tool →Image, audio & embeddings
Pricing beyond text tokens: image generation, speech, embeddings, fine-tuning and video, with official verify links.
Read →FAQ
Quick answers to the most common questions about AI model pricing, tokens and saving money.
Read →Compare two models
An interactive tool: put any two models head to head with prices and context, plus a cost estimate.
Open tool →