---
title: "Late Chunker"
method: POST
path: "/v1/chunk/late"
---

# Late Chunker

`POST /v1/chunk/late`

Implements the late chunking strategy. Encodes the entire text, then splits recursively, deriving chunk embeddings from the full document embedding.

## Response `200`

Successful Response: A list of `LateChunk` objects.

- LateChunkSchema[] — A list containing `LateChunk` objects, detailing segments, sentences, and an optional chunk-level embedding derived from the full document.
  - `text` string — The actual text content of the chunk.
  - `start_index` integer — The starting character index of the chunk within the original input text.
  - `end_index` integer — The ending character index (exclusive) of the chunk within the original input text.
  - `token_count` integer — The number of tokens in this specific chunk, according to the tokenizer used.
  - `embedding` number[], nullable — Optional embedding vector (list of floats) for the entire chunk, derived from the full document embedding.

## Changes

- **2025-05-22** `8a6665f478db` — 1 warning
  - removed the optional property `items/sentences` from the response with the `200` status
- **2025-04-27** `bc64e1775952` — 1 info
  - endpoint added
- **2025-04-27** `5c8e44804806` — 1 breaking
  - api removed without deprecation
- **2025-04-27** `1762a3ecb81b` — 1 info
  - the `embedding_model` request property default value changed from `sentence-transformers/all-minilm-l6-v2` to `all-MiniLM-L6-v2`
- **2025-04-27** `7e3cb743a9ed` — 1 warning
  - removed the request property `text`

[Full history](https://skmtc.dev/feyninc/apis/chonkie-api/changes/v1/chunk/late/post.md)

---

[API](https://skmtc.dev/feyninc/apis/chonkie-api.md) · [All operations](https://skmtc.dev/feyninc/apis/chonkie-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/feyninc/chonkie-api/revisions/8a6665f478db/schema)