---
title: "Sentence Chunk"
method: POST
path: "/v1/chunk/sentence"
tags: ["Chunking"]
---

# Sentence Chunk

`POST /v1/chunk/sentence`

Sentence chunking endpoint.

Chunks text at sentence boundaries while respecting token limits.

## Headers

- `authorization` string, nullable

## Request body

- SentenceChunkerRequest — Request model for sentence chunking.
  - `text` union — Text or list of texts to chunk
    - string
    - string[]
  - `file` FileReference — File reference for chunking with OCR.
    - `type` string, required — File type: 'document' or 'base64;extension'
    - `content` string, required — Filename (for document) or base64 data
  - `ocr` string — OCR provider (mistral or gemini)
  - `tokenizer` string — Tokenizer to use
  - `chunk_size` integer — Size of each chunk
  - `chunk_overlap` integer — Overlap between chunks
  - `min_sentences_per_chunk` integer — Minimum sentences per chunk
  - `min_characters_per_sentence` integer — Minimum characters per sentence
  - `approximate` boolean — Use approximate chunking
  - `delim` union — Sentence delimiters
    - string
    - string[]
  - `include_delim` 'prev' | 'next', nullable — Where to include delimiter

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.dev/chonkie/apis/chonkie-api.md) · [All operations](https://skmtc.dev/chonkie/apis/chonkie-api/llms.txt) · [OpenAPI document](https://skmtc.dev/chonkie/apis/chonkie-api/revisions/f40f036f941c?raw)