---
title: "Neural Chunk"
method: POST
path: "/v1/chunk/neural"
tags: ["Chunking"]
---

# Neural Chunk

`POST /v1/chunk/neural`

Neural chunking endpoint using Modal.

Chunks text using a neural network model to identify optimal chunk boundaries.
This endpoint calls the Modal function directly for GPU-accelerated processing.

## Headers

- `authorization` string, nullable

## Request body

- NeuralChunkerRequest — Request model for neural chunking.
  - `text` union, required — Text or list of texts to chunk
    - string
    - string[]
  - `model` string — Neural model to use
  - `min_characters_per_chunk` integer — Minimum characters per chunk
  - `stride` integer, nullable — Stride for sliding window

## 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)