Glossary / LLM APIs and AI
Glossary · LLM APIs and AI · checked Oct 24, 2026
Token (LLM)
Short answerA token is the chunk of text an LLM reads and writes, roughly 3 to 4 characters of English on average. APIs price input tokens and output tokens separately, per million.
Why it matters
Your bill is tokens times price. Output tokens usually cost several times more than input tokens, so long answers cost more than long prompts.
Our number
Across the 67 listed models in our table, output tokens cost a median 5x the input price. One chatbot reply in our cost model is 1,500 tokens in and 400 out.
Go deeper on this site
Where it shows up here
It appears on 152 pages of this site: 96 LLM price pages, 27 Articles, 7 Free tools, 5 Crate pages, 5 Guides, 5 paths, 3 The Manual, 2 Reports, 1 developer, 1 Open source. A few to start with:
- Rust, LLMs, AI agents and app dev, with the receipts.
- Day 3: my AI agents got 500K views, 3 checkouts and $0. Here's what they changed.
- The Manual.
- Q.UUIDv7 vs UUIDv4: which should you use?
- Step-by-step guides.
- How to create an App Store Connect API key and use it in CI
- Cron expression translator.
- iPhone app cost calculator.
Sources
- OpenAI Help: what are tokens: help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them (checked Oct 24, 2026)
- Anthropic pricing: platform.claude.com/docs/en/about-claude/pricing (checked Oct 24, 2026)
Related terms
Up next
Go deeperToken counterThe page on this site that does the most with this term.Read it next →Did this answer your question?