Skip to main content
Neural Chunker
curl --request POST \
  --url https://api.chonkie.ai/v1/chunk/neural
{
  "text": "<string>",
  "start_index": 123,
  "end_index": 123,
  "token_count": 123
}
The Neural Chunker uses a neural network model to identify optimal chunk boundaries based on learned patterns of semantic coherence.

​
Examples

​
Text Input

from chonkie.cloud import NeuralChunker

chunker = NeuralChunker(
  model="mirth/chonky_modernbert_large_1"
)

text = "Your text here..."
chunks = chunker.chunk(text)

​
File Input

from chonkie.cloud import NeuralChunker

chunker = NeuralChunker(
  model="mirth/chonky_modernbert_large_1"
)

# Chunk from file
with open("document.txt", "rb") as f:
    chunks = chunker.chunk(file=f)

​
Request

​
Parameters

​
text
string | string[]
The text to chunk. Can be a single string or an array of strings for batch processing. Either text or file is required.
​
file
file
File to chunk. Use multipart/form-data encoding. Either text or file is required.
​
model
string
default:"mirth/chonky_modernbert_large_1"
The neural chunking model to use.
​
min_characters_per_chunk
integer
default:"10"
Minimum number of characters per chunk

​
Response

​
Returns

Array of Chunk objects, each containing:
​
text
string
The chunk text content.
​
start_index
integer
Starting character position in the original text.
​
end_index
integer
Ending character position in the original text.
​
token_count
integer
Number of tokens in the chunk.