Glossary / LLM APIs and AI
Glossary · LLM APIs and AI · checked Oct 24, 2026
Inference (AI)
Short answerInference is running a trained model to get an output, as opposed to training it. Every API call to an LLM is an inference request, and API prices are inference prices.
Why it matters
For most products inference is the recurring cost that scales with users; training is a one-off someone else usually paid for.
Our number
Every price on our LLM API prices pages is a per-token inference price, checked against the provider pages.
Go deeper on this site
Where it shows up here
It appears on 31 pages of this site: 18 LLM price pages, 8 Articles, 4 paths, 1 The Manual. A few to start with:
- Rust, LLMs, AI agents and app dev, with the receipts.
- DeepSeek gave away its engine. The $38-an-hour parts stayed home
- Q.What is x402?
- Claude Haiku 3.5 API pricing
- Claude Fable 5.1 API pricing
- Reading paths.
- AI API costs, and how to cut them.
Sources
- Google Cloud: what is AI inference: cloud.google.com/discover/what-is-ai-inference (checked Oct 24, 2026)
Related terms
Up next
Go deeperLLM API pricesThe page on this site that does the most with this term.Read it next →Did this answer your question?