Claude
Anthropic's family of large language models, known for safety, long context, and instruction-following.
Full Definition
Claude is a family of large language models developed by Anthropic, designed around Constitutional AI principles to be helpful, harmless, and honest. The family spans capability tiers — Haiku (fast and cheap), Sonnet (balanced), and Opus (most capable) — allowing developers to choose cost-performance tradeoffs. Claude models feature industry-leading context windows (up to 200k tokens), strong instruction-following, and built-in resistance to jailbreaks and harmful content. Anthropic's safety-first research culture means Claude is one of the most extensively red-teamed commercial models. Claude 3.5 Sonnet and Claude 3 Opus consistently top LLM benchmarks.
Examples
Using Claude Sonnet via the API to power a document analysis pipeline that processes 150-page contracts in a single context window.
Using Claude Haiku as a low-latency classifier in a content moderation system handling thousands of requests per minute.
Apply this in your prompts
PromptITIN automatically uses techniques like Claude to build better prompts for you.
Related Terms
Constitutional AI
Anthropic's technique for training helpful, harmless AI using a set of written p…
View →Large Language Model
A neural network with billions of parameters trained on text to understand and g…
View →Instruction-Tuned Model
A model fine-tuned on instruction-response pairs to follow natural-language dire…
View →