AI model pricing calculator
Enter your monthly input and output token volume. Every tracked model is ranked by list-price monthly cost, cheapest first. Prices are the providers' standard API rates as of 2026-10-08; caching, batch and long-context tiers are not applied.
Paste your usage instead of typing
Paste a line from a provider invoice, a usage dashboard, or an API response. We look for input and output token counts (JSON keys like input_tokens, prompt_tokens, completion_tokens, or text like "1.2M in, 300k out"). Nothing leaves your browser.
Examples that work: {"usage":{"input_tokens":1200000,"output_tokens":300000}} · 1.2M in, 300k out · GPT-6.1 Sol: 2.4B input tokens, 310M output tokens
| # | Model | In / out per 1M | Per month | Per year | relative |
|---|
Rule of thumb: one million tokens is roughly 750,000 English words on older tokenizers, about 555,000 on Anthropic's current one. Reasoning models count their thinking as output tokens, which usually dominates the bill. Shareable: the URL updates with your numbers.