{
  "x402Version": 2,
  "id": 72519,
  "slug": "saylorinnovations-api-text-chunk",
  "resource": "https://saylorinnovations.com/api/text/chunk",
  "description": "Split text into sentence, paragraph or fixed-size chunks for RAG with optional overlap, character offsets and a rough token estimate per chunk",
  "type": "http",
  "serviceName": "Saylor Innovations Data Desk",
  "mimeType": "application/json",
  "resourceType": "API",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "eip155:137",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "eip155:42161",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0xaf88d065e77c8cC2239327C5EDb3A432268e5831",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "So11111111111111111111111111111111111111112",
      "amount": "95830",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    }
  ],
  "outputSchema": {
    "type": "object",
    "properties": {
      "mode": {
        "type": "string",
        "description": "Mode used"
      },
      "size": {
        "type": "number",
        "description": "Target characters per chunk"
      },
      "overlap": {
        "type": "number",
        "description": "Overlap between chunks in characters"
      },
      "total_characters": {
        "type": "number",
        "description": "Total characters"
      },
      "chunk_count": {
        "type": "number",
        "description": "Number of chunk"
      },
      "average_chunk_characters": {
        "type": "number",
        "description": "Average chunk characters"
      },
      "largest_chunk_characters": {
        "type": "number",
        "description": "Largest chunk characters"
      },
      "chunks": {
        "type": "array",
        "description": "Chunks with index, start and end offsets in the original text, character count, rough token estimate and text",
        "items": {
          "type": "object",
          "properties": {
            "start": {
              "description": "Start offset in the original text",
              "type": [
                "number",
                "null"
              ]
            },
            "end": {
              "description": "End offset in the original text",
              "type": [
                "number",
                "null"
              ]
            },
            "characters": {
              "description": "Characters in the chunk",
              "type": [
                "number",
                "null"
              ]
            },
            "index": {
              "description": "Index value"
            },
            "estimated_tokens": {
              "description": "Estimated tokens"
            },
            "text": {
              "description": "Text content"
            }
          }
        }
      },
      "note": {
        "type": "string",
        "description": "Caveat or context for reading the result"
      },
      "source": {
        "type": "string",
        "description": "Data source the values come from"
      }
    },
    "required": [
      "chunk_count",
      "chunks"
    ]
  },
  "extensions": {
    "bazaar": {
      "info": {
        "input": {
          "type": "http",
          "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."
          }
        },
        "output": {
          "type": "json",
          "example": {
            "mode": "sentence",
            "size": 100,
            "overlap": 0,
            "total_characters": 127,
            "chunk_count": 2,
            "average_chunk_characters": 63,
            "largest_chunk_characters": 78,
            "chunks": [
              {
                "index": 0,
                "start": 0,
                "end": 78,
                "characters": 78,
                "estimated_tokens": 20,
                "text": "First sentence here. Second sentence follows it. Third one ends the paragraph."
              },
              {
                "index": 1,
                "start": 80,
                "end": 127,
                "characters": 47,
                "estimated_tokens": 12,
                "text": "New paragraph starts now. It has two sentences."
              }
            ],
            "note": "Sentence and paragraph modes never split inside a unit unless it is longer than size; token counts are a rough characters/4 estimate.",
            "source": "Text chunking computed from the supplied text"
          }
        }
      },
      "schema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "input": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "http"
              },
              "method": {
                "type": "string",
                "enum": [
                  "GET"
                ]
              },
              "queryParams": {
                "type": "object",
                "properties": {
                  "mode": {
                    "type": "string",
                    "description": "optional sentence (default), paragraph or fixed"
                  },
                  "size": {
                    "type": "string",
                    "description": "optional target characters per chunk 100-8000, default 1000"
                  },
                  "text": {
                    "type": "string",
                    "description": "Text to split, up to 30000 characters"
                  }
                },
                "required": [
                  "text"
                ]
              }
            },
            "required": [
              "type",
              "method"
            ],
            "additionalProperties": false
          },
          "output": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "json"
              },
              "example": {
                "type": "object",
                "properties": {
                  "mode": {
                    "type": "string",
                    "description": "Mode used"
                  },
                  "size": {
                    "type": "number",
                    "description": "Target characters per chunk"
                  },
                  "overlap": {
                    "type": "number",
                    "description": "Overlap between chunks in characters"
                  },
                  "total_characters": {
                    "type": "number",
                    "description": "Total characters"
                  },
                  "chunk_count": {
                    "type": "number",
                    "description": "Number of chunk"
                  },
                  "average_chunk_characters": {
                    "type": "number",
                    "description": "Average chunk characters"
                  },
                  "largest_chunk_characters": {
                    "type": "number",
                    "description": "Largest chunk characters"
                  },
                  "chunks": {
                    "type": "array",
                    "description": "Chunks with index, start and end offsets in the original text, character count, rough token estimate and text",
                    "items": {
                      "type": "object",
                      "properties": {
                        "start": {
                          "description": "Start offset in the original text",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "end": {
                          "description": "End offset in the original text",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "characters": {
                          "description": "Characters in the chunk",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "index": {
                          "description": "Index value"
                        },
                        "estimated_tokens": {
                          "description": "Estimated tokens"
                        },
                        "text": {
                          "description": "Text content"
                        }
                      }
                    }
                  },
                  "note": {
                    "type": "string",
                    "description": "Caveat or context for reading the result"
                  },
                  "source": {
                    "type": "string",
                    "description": "Data source the values come from"
                  }
                },
                "required": [
                  "chunk_count",
                  "chunks"
                ]
              }
            },
            "required": [
              "type"
            ]
          }
        },
        "required": [
          "input"
        ]
      }
    }
  },
  "tags": [
    "split text into chunks",
    "rag chunking with overlap",
    "sentence aware text splitter",
    "chunk a document by paragraphs",
    "fixed size text chunks"
  ],
  "sourceHost": "saylorinnovations.com",
  "lastUpdated": "2026-10-26T22:14:01.956Z",
  "quality": {},
  "metadata": {
    "serviceName": "Saylor Innovations Data Desk",
    "method": "GET",
    "mimeType": "application/json",
    "inputSchema": {
      "type": "object",
      "properties": {
        "mode": {
          "type": "string",
          "description": "optional sentence (default), paragraph or fixed"
        },
        "size": {
          "type": "string",
          "description": "optional target characters per chunk 100-8000, default 1000"
        },
        "text": {
          "type": "string",
          "description": "Text to split, up to 30000 characters"
        }
      },
      "required": [
        "text"
      ]
    },
    "exampleResponse": {
      "mode": "sentence",
      "size": 100,
      "overlap": 0,
      "total_characters": 127,
      "chunk_count": 2,
      "average_chunk_characters": 63,
      "largest_chunk_characters": 78,
      "chunks": [
        {
          "index": 0,
          "start": 0,
          "end": 78,
          "characters": 78,
          "estimated_tokens": 20,
          "text": "First sentence here. Second sentence follows it. Third one ends the paragraph."
        },
        {
          "index": 1,
          "start": 80,
          "end": 127,
          "characters": 47,
          "estimated_tokens": 12,
          "text": "New paragraph starts now. It has two sentences."
        }
      ],
      "note": "Sentence and paragraph modes never split inside a unit unless it is longer than size; token counts are a rough characters/4 estimate.",
      "source": "Text chunking computed from the supplied text"
    },
    "parameterLocation": "query",
    "extensions": {
      "bazaar": {
        "info": {
          "input": {
            "type": "http",
            "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."
            }
          },
          "output": {
            "type": "json",
            "example": {
              "mode": "sentence",
              "size": 100,
              "overlap": 0,
              "total_characters": 127,
              "chunk_count": 2,
              "average_chunk_characters": 63,
              "largest_chunk_characters": 78,
              "chunks": [
                {
                  "index": 0,
                  "start": 0,
                  "end": 78,
                  "characters": 78,
                  "estimated_tokens": 20,
                  "text": "First sentence here. Second sentence follows it. Third one ends the paragraph."
                },
                {
                  "index": 1,
                  "start": 80,
                  "end": 127,
                  "characters": 47,
                  "estimated_tokens": 12,
                  "text": "New paragraph starts now. It has two sentences."
                }
              ],
              "note": "Sentence and paragraph modes never split inside a unit unless it is longer than size; token counts are a rough characters/4 estimate.",
              "source": "Text chunking computed from the supplied text"
            }
          }
        },
        "schema": {
          "$schema": "https://json-schema.org/draft/2020-12/schema",
          "type": "object",
          "properties": {
            "input": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "http"
                },
                "method": {
                  "type": "string",
                  "enum": [
                    "GET"
                  ]
                },
                "queryParams": {
                  "type": "object",
                  "properties": {
                    "mode": {
                      "type": "string",
                      "description": "optional sentence (default), paragraph or fixed"
                    },
                    "size": {
                      "type": "string",
                      "description": "optional target characters per chunk 100-8000, default 1000"
                    },
                    "text": {
                      "type": "string",
                      "description": "Text to split, up to 30000 characters"
                    }
                  },
                  "required": [
                    "text"
                  ]
                }
              },
              "required": [
                "type",
                "method"
              ],
              "additionalProperties": false
            },
            "output": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "json"
                },
                "example": {
                  "type": "object",
                  "properties": {
                    "mode": {
                      "type": "string",
                      "description": "Mode used"
                    },
                    "size": {
                      "type": "number",
                      "description": "Target characters per chunk"
                    },
                    "overlap": {
                      "type": "number",
                      "description": "Overlap between chunks in characters"
                    },
                    "total_characters": {
                      "type": "number",
                      "description": "Total characters"
                    },
                    "chunk_count": {
                      "type": "number",
                      "description": "Number of chunk"
                    },
                    "average_chunk_characters": {
                      "type": "number",
                      "description": "Average chunk characters"
                    },
                    "largest_chunk_characters": {
                      "type": "number",
                      "description": "Largest chunk characters"
                    },
                    "chunks": {
                      "type": "array",
                      "description": "Chunks with index, start and end offsets in the original text, character count, rough token estimate and text",
                      "items": {
                        "type": "object",
                        "properties": {
                          "start": {
                            "description": "Start offset in the original text",
                            "type": [
                              "number",
                              "null"
                            ]
                          },
                          "end": {
                            "description": "End offset in the original text",
                            "type": [
                              "number",
                              "null"
                            ]
                          },
                          "characters": {
                            "description": "Characters in the chunk",
                            "type": [
                              "number",
                              "null"
                            ]
                          },
                          "index": {
                            "description": "Index value"
                          },
                          "estimated_tokens": {
                            "description": "Estimated tokens"
                          },
                          "text": {
                            "description": "Text content"
                          }
                        }
                      }
                    },
                    "note": {
                      "type": "string",
                      "description": "Caveat or context for reading the result"
                    },
                    "source": {
                      "type": "string",
                      "description": "Data source the values come from"
                    }
                  },
                  "required": [
                    "chunk_count",
                    "chunks"
                  ]
                }
              },
              "required": [
                "type"
              ]
            }
          },
          "required": [
            "input"
          ]
        }
      }
    },
    "examples": [
      {
        "label": "Unpaid discovery call",
        "method": "GET",
        "url": "https://saylorinnovations.com/api/text/chunk?text=First%20sentence%20here.%20Second%20sentence%20follows%20it.%20Third%20one%20ends%20the%20paragraph.%0A%0ANew%20paragraph%20starts%20now.%20It%20has%20two%20sentences.&size=100&mode=sentence",
        "expectedStatus": 402
      }
    ],
    "cacheTtlSeconds": 0,
    "capabilities": [],
    "noAccountRequired": true,
    "noApiKeyRequired": true,
    "sideEffects": "Paid calls settle the advertised payment; see the provider contract for execution behavior.",
    "payment": {
      "protocol": "x402",
      "settlement": "direct-to-provider"
    },
    "provider": {
      "name": "Saylor Innovations",
      "host": "saylorinnovations.com",
      "manifestUrl": "https://saylorinnovations.com/.well-known/x402.json"
    }
  },
  "liveness": {
    "reliability": null
  },
  "verified": true,
  "featured": false,
  "provider": {
    "host": "saylorinnovations.com",
    "manifest_name": "Saylor Innovations Knowledge Base",
    "source": "submitted",
    "source_manifest_url": "https://saylorinnovations.com/.well-known/x402.json",
    "submitted_at": "2026-10-26T05:52:02.113Z"
  },
  "exampleResponse": {
    "mode": "string",
    "size": 0,
    "overlap": 0,
    "total_characters": 0,
    "chunk_count": 0,
    "average_chunk_characters": 0,
    "largest_chunk_characters": 0,
    "chunks": [
      {
        "start": 0,
        "end": 0,
        "characters": 0,
        "index": null,
        "estimated_tokens": null,
        "text": null
      }
    ],
    "note": "string",
    "source": "string"
  }
}