Skip to main content
Token Chunker
curl --request POST \
  --url https://api.example.com/v1/chunk/token
{
  "text": "<string>",
  "start_index": 123,
  "end_index": 123,
  "token_count": 123
}
The Token Chunker splits text into chunks based on token count, ensuring each chunk stays within specified token limits.

​
Examples

​
Text Input

from chonkie.cloud import TokenChunker

chunker = TokenChunker(
    tokenizer="gpt2",
    chunk_size=512,
    chunk_overlap=128
)

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

​
File Input

from chonkie.cloud import TokenChunker

chunker = TokenChunker(
    tokenizer="gpt2",
    chunk_size=512,
    chunk_overlap=128
)

# 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.
​
tokenizer
string
default:"gpt2"
Tokenizer to use for counting tokens. Options: “gpt2”, “character”, “word”, or any Hugging Face tokenizer.
​
chunk_size
integer
default:"512"
Maximum number of tokens per chunk.
​
chunk_overlap
integer
default:"0"
Number of tokens to overlap between consecutive chunks.

​
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.