---
title: "Neural Chunker"
method: POST
path: "/v1/chunk/neural"
---

# Neural Chunker

`POST /v1/chunk/neural`

Splits text using a fine-tuned BERT model to detect semantic shifts, creating topic-coherent chunks.

## Response `200`

Successful Response: A list of `Chunk` objects.

- Chunk[] — A list containing `Chunk` objects, representing segments split based on semantic shifts detected by the neural model.
  - `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.
  - `context` string, nullable — Chunk context.

## Changes

- **2025-05-04** `33dc37e4abcd` — 1 info
  - added the optional property `items/context` to the response with the `200` status
- **2025-04-29** `e12d0b1f23dc` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/feyninc/apis/chonkie-api/changes/v1/chunk/neural/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)