Glossary

LLM Costs

What is LLM Costs?

The costs of large language models are usually billed per token, i.e. text units roughly the size of a syllable to a word; input and output tokens are priced separately, with output generally more expensive. Larger models cost more per token than small, fast models such as Claude Haiku, which are often sufficient for simple tasks. Prompt caching lowers costs when the same long context is sent repeatedly. Concise instructions and carefully selected knowledge help as well.

How KI.ordo helps

KI.ordo displays tokens and costs per model, caps usage with a monthly token limit and an AI credit per plan, and uses prompt caching.

Learn more →

Topics

Costs
Tokens
Model choice

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Token

A token is the smallest unit of text a language model processes, usually part of a word, a short word or a punctuation mark. Models read inputs and generate answers token by token, and the size of the context window is also measured in tokens. Because providers charge for input and output tokens, tokens directly determine costs and limits: long instructions and extensive background knowledge increase consumption.

LLM
Costs
+1

Large language model (LLM)

A large language model (LLM) is a neural network trained on very large amounts of text, enabling it to understand and generate language. It works by calculating the most likely next token, step by step. LLMs write, summarise, translate, answer questions and generate code; well-known examples include Claude, GPT, Gemini and Llama. Without access to current sources, they only know what was in their training data.

Language models
Generative AI
+1

Claude Haiku

Claude Haiku is the fastest and least expensive of Anthropic's three Claude model families, alongside Sonnet and Opus. It suits high-volume tasks that need short response times, such as sorting emails, extracting data from texts or routing requests to the right place. The current generation is Claude Haiku 5.5 (as of October 2026).

Claude
Anthropic
+1

Return on AI (ROAI)

Return on AI describes the economic return of an AI deployment relative to its costs. A simple rough calculation is: hours saved per month × hourly rate, minus the costs of licences, model usage, set-up and support. If a team handling 200 requests needs 4 instead of 10 minutes per request, it saves 20 hours a month. Such calculations remain estimates; quality, error rates and onboarding time should also be taken into account.

cost-effectiveness
cost-benefit
+1

Template