agentutility$ man semantic-chunk
/semantic-chunk
PRICE / CALL
$0.002
USDC · base mainnet · scheme: exact
METHOD
POST
CLUSTER
wordmintCATEGORY
uncategorized
STATUS
● live
NAME
semantic-chunk — semantic chunker / text splitter / rag chunker / chunking with overlap / sentence + paragraph aware
SYNOPSIS
POST https://x402.agentutility.ai/semantic-chunk
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Semantic chunker / text splitter / RAG chunker / chunking with overlap / sentence + paragraph aware. Splits long text into chunks with three modes: 'fixed' (hard char-count windows with overlap), 'sentence' (greedy pack of sentences up to chunk_size), 'paragraph' (split on blank lines, never pack across paragraphs). Returns each chunk's text, start/end character offsets, and char count. Pure local — no upstream call.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| text | string | Text to split. Up to 1,000,000 chars. | required |
| chunk_size | number | Target chunk size in characters. Range [50, 20000]. Default 500. | optional |
| overlap | number | Overlap between chunks in characters. Default 50. Capped at chunk_size - 1. | optional |
| mode | string | Splitting strategy. Default 'fixed'. enum: fixed · sentence · paragraph | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| chunks | string | Array of chunk objects, each with text, start offset, end offset, and char count. |
| chunk_count | string | Number of chunks produced from the input text. |
| mode | string | Chunking mode used: 'fixed', 'sentence', or 'paragraph'. |
| chunk_size | string | Target maximum character size per chunk as applied. |
| overlap | string | Character overlap between adjacent chunks (fixed mode) or 0 otherwise. |
| text_chars | string | Total character length of the input text before chunking. |
| source | string | Identifier for the chunker, e.g. 'semantic-chunk' / local splitter tag. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/semantic-chunk \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# MCP packages on npm under # @agentutility/mcp-* (one per cluster) # # Catalog + install: # https://mcp.agentutility.ai # # Or call semantic-chunk directly over HTTP — see above.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- wordminttext-splitterrag-chunkingsentence-awareparagraph-awarechunk-overlapsemantic-chunker
- methods
- POST
- cluster
- wordmint
- price
- $0.002 USDC per call
ADJACENT — other endpoints in wordmint
| endpoint | description | price |
|---|---|---|
| cron-explain | Cron expression explainer / cron parser / scheduling translator. | $0.002 |
| cron-parse | Cron parser. | $0.002 |
| dictionary-define | English dictionary / word definition / lookup word / pronunciation / part of speech / synonyms / etymology adjacent. | $0.002 |
| embedding-similarity | Embedding similarity / cosine similarity / semantic match / vector compare / are-these-strings-similar. | $0.002 |
| regex-test | Regex tester / pattern matcher / regex playground / verify-a-pattern / match-and-capture extractor. | $0.002 |
| text-embedding | Text embedding / vector embedding / semantic vector / Venice embeddings / Gemini embeddings / BGE-M3. | $0.002 |
| thesaurus | Thesaurus / synonyms / antonyms / similar words / rhymes / Datamuse / paraphrasing / query expansion. | $0.002 |
| content-simhash | SimHash / 64-bit content fingerprint / near-duplicate detection / dedup hashing / locality-sensitive hash. | $0.001 |
SEE ALSO