# Cosine Similarity & Vector Distance Calculator

> Paste embedding vectors and get every pairwise cosine, dot product, Euclidean and Manhattan distance, ranked.

This calculator takes embedding vectors and computes every pairwise cosine similarity, dot product, Euclidean distance and Manhattan distance, plus the angle in degrees, ranked by whichever metric you choose. It accepts labelled lines, bare number lists, JSON arrays and the {"data":[{"embedding":[…]}]} shape that embedding APIs return, and it flags dimension mismatches rather than producing a meaningless number.

**URL:** https://convertto.tech/t/embedding-similarity-calculator
**Category:** AI & LLM Tools (https://convertto.tech/c/ai-tools)
**Privacy:** Runs entirely in the browser; no upload
**Cost:** Free, no sign-up
**Last updated:** 2026-08-01

## Key facts

- **Cosine range:** −1 to 1 — the angle between vectors, ignoring magnitude
- **Unit vectors:** Cosine and dot product are identical when both vectors have length 1
- **Privacy:** Runs entirely in your browser — nothing is uploaded
- **Cost:** Free, unlimited, no sign-up

## How to use

1. Enter or paste your vectors.
2. Choose the rank by.
3. Turn "Normalise to unit length first" on or off as needed.
4. Set the show top pairs.
5. Press Run, then download the result when it is ready.

## FAQ

### Cosine or dot product?

If your vectors are unit length — and every major embedding API returns them that way — the two rank identically and dot product is faster. Use cosine when magnitudes vary, because then dot product rewards long vectors regardless of direction.

### What counts as a good similarity score?

There is no universal threshold, and this is the most common mistake in retrieval work. Different models compress the range differently: one may put unrelated text at 0.1 and another at 0.7. Calibrate against pairs from your own corpus that you know are related and unrelated, then set the threshold from that.

## Sources

- [OpenAI — embeddings](https://platform.openai.com/docs/guides/embeddings) — OpenAI

## Related tools

- [Semantic Search & Similarity](https://convertto.tech/t/semantic-search-tool): Embed a list of sentences with a real model and rank them by meaning — or find the near-duplicates in a list.
- [Text Chunker for RAG](https://convertto.tech/t/text-chunker-for-rag): Chunk by tokens, sentences, paragraphs, a separator ladder or markdown headings — with overlap, token counts and embedding cost.
- [Text Similarity Checker](https://convertto.tech/t/text-similarity-checker): Compare two texts with Levenshtein distance, Jaccard, cosine and Dice coefficients.
- [Chat with Any Document](https://convertto.tech/t/chat-with-document): Ask questions about a PDF, Word file, spreadsheet, CSV, Markdown or text file and get answers with the passage each came from.
- [Chat with PDF](https://convertto.tech/t/chat-with-pdf): Ask questions about any PDF and get answers with the page each one came from. The model runs in your browser — the file is never uploaded.
- [AI API Cost Calculator](https://convertto.tech/t/ai-api-cost-calculator): Work out what a prompt costs per call, per day and per month, and compare the same workload across every major model.
- [AI Writing Pattern Checker](https://convertto.tech/t/ai-writing-pattern-checker): Measure sentence-length variance, vocabulary richness, marker phrases and typographic tells, with per-sentence scoring.
- [Chat Export Formatter](https://convertto.tech/t/chat-export-formatter): Drop in an exported conversations file and get clean Markdown, HTML or plain text — one document per conversation.