Loading...
Cite Claude correctly in APA 7, MLA 9, Chicago 17, Harvard, IEEE and Vancouver. Anthropic and the tool's URL are already filled in; add the model version from the picker, the date and your prompt, and copy the reference entry with every in-text form. Built on the guidance the style manuals published for generative AI.
The version is in the product's model picker or settings. The prompt makes MLA, Chicago and Harvard entries complete; APA works without it.
Anthropic. (n.d.). Claude [Large language model]. https://claude.ai/
(Anthropic, n.d.)
The company is the author, so it carries the citation; the model is named in your sentence.
Anthropic (n.d.)
When prompted, Claude generated... (Anthropic, n.d.)
APA suggests describing the prompt in the text or method section; longer transcripts can go in an appendix.





Trusted by researchers publishing in
Open the model picker or settings in Claude and note the exact version you used. AI tools change weekly, so the version is what makes your citation reproducible, the same way an edition dates a book.
Record when the text was generated and what you asked. MLA and Chicago build the citation around the prompt itself, and every style dates the exchange somewhere.
Pick APA, MLA, Chicago, Harvard, IEEE or Vancouver and copy the entry with italics intact, plus the in-text forms and the note or disclosure wording the style expects.
APA, MLA and Chicago published real AI citation guidance in 2023. Each output here follows its manual: Anthropic as author for APA, prompt as title for MLA, footnote-only for Chicago.
Company and URL are filled in. You add the three things only you know: which model answered, on which date, to which prompt.
Claude versions read like Sonnet 4.5 or Opus 4.1 rather than dates. The version field takes the tier name exactly as the model menu shows it and places it per style.
Parenthetical and narrative citations, the Chicago footnote and shortened note, and the disclosure wording IEEE and ICMJE journals expect, each one copy away.
Claude occupies a particular corner of academic AI use: Anthropic pitches it at long documents and careful reasoning, which is exactly the territory of literature reviews, methods drafting and argument critique. That makes the citation question routine rather than exotic. The style manuals' 2023 guidance was written around ChatGPT, but the patterns transfer directly: the company in the author position for APA, the prompt as the title of the source for MLA, a footnote and nothing else for Chicago. Swap in Anthropic and Claude, and every rule lands the same way.
The Claude-specific detail is naming. Anthropic versions its models by tier, Haiku for speed, Sonnet in the middle, Opus at the top, each carrying a number, so the model menu reads Sonnet 4.5 rather than a date. That tier name is the version your citation needs: two Claude models can answer the same prompt quite differently, and the reader reconstructing your work has to know which one you asked. The date of the conversation does the rest, since models are updated inside a version's lifetime.
The boundaries are the same as for any AI tool. Claude cannot be an author: the ICMJE, COPE and publishers including Nature and Science all require authorship to carry responsibility no algorithm can hold, so Claude is cited as a source or disclosed as a tool. And references Claude suggests are leads, not citations: verify each against a real database before it enters your reference list, because language models invent convincing papers, plausible DOIs included.
The verification steps live in the hallucinated-citation audit. Comparing tools for research work? Our ChatGPT vs Claude comparison goes deep, and the AI citation generator covers ten model families, with ChatGPT and Gemini on their own pages.
One Claude conversation, taken apart in six styles. Hover any coloured part of the reference entry or the in-text variations to see what it is and the rule behind it.
Anthropic. (2026). Claude (Sonnet 4.5 version) [Large language model]. https://claude.ai/
The pattern the APA Style blog published for ChatGPT, applied to any AI model. Alphabetize under the company's name in the reference list.
(Anthropic, 2026)
Anthropic (2026)...
When prompted, Claude generated... (Anthropic, 2026)
APA recommends describing the prompt in the text or method section; a full transcript can go in an appendix.
(Anthropic, 2026)
AI output has no page numbers, so no p. locator is possible; make clear in the sentence that the words are the model's.
Hover or tap any coloured part for what it is and the rule behind it.
Six conventions that separate a correct Claude citation from an improvised one.
In APA and the styles that share its logic, the company takes the author position. Claude is the italicized title of the work, never the author of your paper.
Haiku, Sonnet and Opus are capability tiers, each numbered. The tier plus number, Sonnet 4.5 for instance, is the version a reader needs to know which Claude answered.
MLA builds the entry around what you asked, Chicago quotes it in the footnote and Harvard names it in the description. Keep your prompts; they are bibliographic data.
APA dates the version; MLA and Chicago date the exchange. The generator keeps both fields apart so every style picks the date it actually wants.
A Claude footnote gets no bibliography line in either Chicago system, the same personal-communication treatment the manual gives any AI exchange.
Citations cover Claude's words in your text; a disclosure statement covers its role in your process. Many journals now expect both, in the methods or acknowledgments.
The same exchange formatted for every style the generator supports. Note where the prompt appears, where it does not, and which styles keep Claude out of the reference list entirely.
Reference list entry
Anthropic. (2026). Claude (Sonnet 4.5 version) [Large language model]. https://claude.ai/
Works Cited entry
"Explain the difference between correlation and causation for a first-year statistics student" prompt. Claude, Sonnet 4.5 version, Anthropic, 14 July 2026, claude.ai.
Footnote (Chicago cites AI in notes only)
Claude, response to "Explain the difference between correlation and causation for a first-year statistics student," Anthropic, 14 July 2026.
In-text citation (no reference list entry)
(Claude, 14 July 2026)
Reference list entry
Anthropic Claude (2026) Claude response to prompt 'Explain the difference between correlation and causation for a first-year statistics student', 14 July.
Reference list entry
[1] Anthropic, Claude (Sonnet 4.5 version) [Large language model], 2026. [Online]. Available: https://claude.ai/ (accessed 14 July 2026).
Reference list entry
1. Claude (Sonnet 4.5 version) [Large language model]. Anthropic; 2026 [cited 14 July 2026]. Available from: https://claude.ai/
All seven come from the generator above. The prompt and dates are examples; substitute the details of your own conversation.
ProofreaderPro proofreads your full manuscript with tracked changes and never touches your citations: grammar, clarity and academic register, reviewable line by line. Built for researchers, free to try.
Proofread my writing free