Split text into sentence, paragraph or fixed-size chunks for RAG with optional o
Split text into sentence, paragraph or fixed-size chunks for RAG with optional overlap, character offsets and a rough token estimate per chunk
Answeringour last check, 2026-10-20
1 of 1checks answered this week
981 msmedian answer time
$0.01listed price per call
$0.01price it asked us
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
GET https://saylorinnovations.com/api/text/chunk
| Category | Market data |
|---|---|
| Provider host | saylorinnovations.com |
| Networks | eip155:137, eip155:42161, eip155:8453, solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp |
| Payment schemes | exact |
| Self-reported calls, 30 days | 0 from 0 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-20 | valid payment request | 402 | $0.01 | 981 ms |
Example input (from the provider)
{
"method": "GET",
"queryParams": {
"mode": "sentence",
"size": "100",
"text": "First sentence here. Second sentence follows it. Third one ends the paragraph.\n\nNew paragraph starts now. It has two sentences."
},
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"method": {
"enum": [
"GET"
],
"type": "string"
},
"queryParams": {
"properties": {
"mode": {
"description": "optional sentence (default), paragraph or fixed",
"type": "string"
},
"size": {
"description": "optional target characters per chunk 100-8000, default 1000",
"type": "string"
},
"text": {
"description": "Text to split, up to 30000 characters",
"type": "string"
}
},
"required": [
"text"
],
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"average_chunk_characters": {
"description": "Average chunk characters",
"type": "number"
},
"chunk_count": {
"description": "Number of chunk",
"type": "number"
},
"chunks": {
"description": "Chunks with index, start and end offsets in the original text, character count, rough token estimate and text",
"items": {
"properties": {
"characters": {
"description": "Characters in the chunk",
"type": [
"number",
"null"
]
},
"end": {
"description": "End offset in the original text",
"type": [
"number",
"null"
]
},
"estimated_tokens": {
"description": "Estimated tokens"
},
"index": {
"description": "Index value"
},
"start": {
"description": "Start offset in the original text",
"type": [
"number",
"null"
]
},
"text": {
"description": "Text content"
}
},
"type": "object"
},
"type": "array"
},
"largest_chunk_characters": {
"description": "Largest chunk characters",
"type": "number"
},
"mode": {
"description": "Mode used",
"type": "string"
},
"note": {
"description": "Caveat or context for reading the result",
"type": "string"
},
"overlap": {
"description": "Overlap between chunks in characters",
"type": "number"
},
"size": {
"description": "Target characters per chunk",
"type": "number"
},
"source": {
"description": "Data source the values come from",
"type": "string"
},
"total_characters": {
"description": "Total characters",
"type": "number"
}
},
"required": [
"chunk_count",
"chunks"
],
"type": "object"
},
"type": {
"const": "json",
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}