Claude API pricing
What every Claude model costs per million tokens, how caching and thinking change the bill, and how to estimate yours.
Read more →GPT API pricing
What every GPT model costs per million tokens, how cached input and reasoning tokens are billed, and a worked example.
Read more →Gemini API pricing
What every Gemini model costs per million tokens, and how thinking tokens and context caching are billed.
Read more →The cheapest way to use the Claude API
Seven ways to cut a Claude API bill, ordered by how much they save, from model choice to prompt caching.
Read more →How much does Claude Code cost?
What a Claude Code session costs on an API key, what drives it, and how to bring it down.
Read more →Claude Pro vs the API: which is cheaper?
A subscription or pay-per-token: when each costs less for chat, coding agents and apps.
Read more →Opus vs Sonnet vs Haiku: which Claude model?
How to pick between Claude Opus, Sonnet and Haiku by task, with live prices side by side.
Read more →How to estimate LLM API cost before you build
Count tokens, price the four kinds of usage and size a monthly bill for a chatbot, a RAG app or an agent.
Read more →Use the OpenAI SDK with Claude and Gemini
Change base_url and call Claude, GPT and Gemini from one OpenAI client, with the limits of that shortcut.
Read more →