Glossary

Claude Haiku

What is 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).

How KI.ordo helps

In KI.ordo, Haiku can be selected for individual agents or AI steps in flows, for example for simple sorting tasks where low cost matters.

Learn more →

Topics

Claude
Anthropic
model choice

Try KI.ordo

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

Start demo

← All terms

Related terms

Claude

Claude is a family of large language models from the US AI company Anthropic. The models understand and write text in many languages, analyse documents, write code and can use tools, for example for research or automation. Best known are the model families Haiku, Sonnet and Opus, which differ in speed, cost and capability. Anthropic places particular emphasis on safety and reliable model behaviour.

Anthropic
language model
+1

Claude Sonnet

Claude Sonnet is the middle of Anthropic's three Claude model families, combining strong capability with short response times and moderate cost. It suits a wide range of everyday business tasks: drafting texts, analysing documents, answering knowledge questions or writing code. Anthropic releases new versions regularly; the current one is Claude Sonnet 5.5 (as of October 2026).

Claude
Anthropic
+1

Claude Opus

Claude Opus is the most capable of Anthropic's three Claude model families: Haiku, Sonnet and Opus. It is designed for demanding tasks that require multi-step reasoning, such as complex analyses, large programming projects or agents that work independently over longer periods. In return, it is slower and more expensive than the smaller families. The current version is Claude Opus 5.5 (as of October 2026).

Claude
Anthropic
+1

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.

Costs
Tokens
+1