Diffbot Natural Language API

Diffbot Natural Language API allows users to extract and analyze textual content from websites. By utilizing advanced natural language processing algorithms, the API can automatically identify and extract valuable information such as article titles, authors, publication dates, and key entities mentioned in the text.

Operations 1

POST /v1/ Process Text

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/diffbot-natural-language-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

diffbot-natural-language-openapi.json Raw ↑
{
  "swagger": "2.0",
  "info": {
    "description": "Extracts entities (e.g., people, organizations, locations) and facts (e.g., educated at, founded by) about these entities from natural language text.\n",
    "version": "1.0.0",
    "title": "Natural Language API",
    "termsOfService": "https://www.diffbot.com/terms/",
    "contact": {
      "email": "support@diffbot.com"
    }
  },
  "host": "nl.diffbot.com",
  "basePath": "/",
  "schemes": [
    "https"
  ],
  "paths": {
    "/v1/": {
      "post": {
        "tags": [
          "Natural Language"
        ],
        "summary": "Process Text",
        "consumes": [
          "application/json",
          "application/x-www-form-urlencoded"
        ],
        "produces": [
          "application/json"
        ],
        "parameters": [
          {
            "in": "body",
            "name": "documents",
            "description": "documents to be processed",
            "required": true,
            "schema": {
              "$ref": "#/definitions/DocumentArray"
            }
          },
          {
            "name": "fields",
            "in": "query",
            "description": "Attributes to include in response",
            "required": false,
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "entities",
                "sentiment",
                "facts",
                "records",
                "categories",
                "sentences",
                "language",
                "summary"
              ]
            },
            "default": [
              "entities",
              "sentiment",
              "facts",
              "records",
              "sentences"
            ],
            "uniqueItems": true
          }
        ],
        "responses": {
          "200": {
            "description": "",
            "schema": {
              "$ref": "#/definitions/NaturalLanguageResponseArray"
            }
          },
          "400": {
            "description": "Invalid input",
            "schema": {
              "$ref": "#/definitions/ErrorResponse"
            }
          }
        },
        "security": [
          {
            "DiffbotToken": []
          }
        ]
      }
    }
  },
  "securityDefinitions": {
    "DiffbotToken": {
      "type": "apiKey",
      "name": "token",
      "in": "query"
    }
  },
  "definitions": {
    "Document": {
      "type": "object",
      "required": [
        "content"
      ],
      "properties": {
        "content": {
          "type": "string",
          "format": "blob",
          "description": "The text you'd like Diffbot Natural Language to process. \n",
          "minLength": 1,
          "maxLength": 100000
        },
        "lang": {
          "type": "string",
          "description": "Language of the text specified as an [ISO 639-1 code](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes). Review our supported languages for more information.\n",
          "default": "auto"
        },
        "format": {
          "type": "string",
          "description": "`plain text` for free text. `plain text with title` includes a title separated from the body by two line breaks (e.g. \"This is a title\\n\\nThis is the body\").\n",
          "default": "plain text",
          "enum": [
            "plain text",
            "plain text with title"
          ]
        },
        "documentType": {
          "type": "string",
          "description": "Optional. Provides context to the model and may produce better results.\n",
          "enum": [
            "organization bio",
            "person bio",
            "news article",
            "address",
            "discussion"
          ]
        },
        "customSummary": {
          "$ref": "#/definitions/CustomSummary"
        }
      },
      "example": {
        "content": "Diffbot is a startup based in Menlo Park."
      }
    },
    "DocumentArray": {
      "type": "array",
      "items": {
        "$ref": "#/definitions/Document"
      },
      "example": [
        {
          "content": "Diffbot is a startup based in Menlo Park."
        }
      ]
    },
    "EntityWithMentions": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "diffbotUri": {
          "type": "string"
        },
        "confidence": {
          "type": "number",
          "format": "float"
        },
        "salience": {
          "type": "number",
          "format": "float"
        },
        "sentiment": {
          "type": "number",
          "format": "float"
        },
        "allUris": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "allTypes": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/EntityType"
          }
        },
        "mentions": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Mention"
          }
        },
        "location": {
          "$ref": "#/definitions/Location"
        }
      }
    },
    "Mention": {
      "type": "object",
      "properties": {
        "text": {
          "type": "string"
        },
        "beginOffset": {
          "type": "integer"
        },
        "endOffset": {
          "type": "integer"
        },
        "isPronoun": {
          "type": "boolean"
        },
        "confidence": {
          "type": "number",
          "format": "float"
        }
      }
    },
    "Entity": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "diffbotUri": {
          "type": "string"
        },
        "confidence": {
          "type": "number",
          "format": "float"
        },
        "allUris": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "allTypes": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/EntityType"
          }
        },
        "isCustom": {
          "type": "boolean"
        },
        "entityIndex": {
          "type": "integer",
          "description": "Index of this entity in the field \"entities\" (if requested)"
        }
      }
    },
    "Span": {
      "type": "object",
      "properties": {
        "beginOffset": {
          "type": "integer"
        },
        "endOffset": {
          "type": "integer"
        }
      }
    },
    "Fact": {
      "type": "object",
      "properties": {
        "humanReadable": {
          "type": "string"
        },
        "entity": {
          "$ref": "#/definitions/Entity"
        },
        "property": {
          "$ref": "#/definitions/Property"
        },
        "value": {
          "$ref": "#/definitions/Entity"
        },
        "qualifiers": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Qualifier"
          }
        },
        "confidence": {
          "type": "number",
          "format": "float"
        },
        "evidence": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Evidence"
          }
        }
      }
    },
    "Qualifier": {
      "type": "object",
      "properties": {
        "property": {
          "$ref": "#/definitions/Property"
        },
        "value": {
          "$ref": "#/definitions/Qualifier_value"
        },
        "confidence": {
          "type": "number",
          "format": "float"
        }
      },
      "description": "https://demo.nl.diffbot.com/schema/#qualifiers"
    },
    "Property": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "diffbotUri": {
          "type": "string"
        },
        "description": {
          "type": "string"
        }
      },
      "description": "https://demo.nl.diffbot.com/schema/#properties"
    },
    "EntityType": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "diffbotUri": {
          "type": "string"
        },
        "dbpediaUri": {
          "type": "string"
        }
      },
      "description": "https://demo.nl.diffbot.com/schema/#types"
    },
    "Evidence": {
      "type": "object",
      "properties": {
        "passage": {
          "type": "string",
          "description": "One or more sentences where the fact was extracted from"
        },
        "entityMentions": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Mention"
          }
        },
        "valueMentions": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Mention"
          }
        }
      }
    },
    "Location": {
      "type": "object",
      "properties": {
        "latitude": {
          "type": "number",
          "format": "float"
        },
        "longitude": {
          "type": "number",
          "format": "float"
        },
        "precision": {
          "type": "number",
          "format": "float"
        }
      }
    },
    "Category": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "path": {
          "type": "string"
        },
        "confidence": {
          "type": "number",
          "format": "float"
        },
        "isPrimary": {
          "type": "boolean"
        }
      }
    },
    "Categorization": {
      "type": "object",
      "properties": {
        "iabv1": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Category"
          }
        },
        "iabv2": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Category"
          }
        },
        "diffbot": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Category"
          }
        }
      },
      "description": "https://demo.nl.diffbot.com/schema/#categories"
    },
    "CustomSummary": {
      "type": "object",
      "properties": {
        "maxNumberOfSentences": {
          "type": "integer",
          "format": "int32",
          "description": "Maximum number of sentences for the generated summary.",
          "minimum": 1,
          "maximum": 10,
          "default": 3
        }
      },
      "description": "Define custom parameters for summary generation."
    },
    "NaturalLanguageResponse": {
      "type": "object",
      "properties": {
        "errors": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "entities": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/EntityWithMentions"
          }
        },
        "sentiment": {
          "type": "number",
          "format": "float"
        },
        "facts": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Fact"
          }
        },
        "records": {
          "type": "array",
          "description": "Array of entities with attributes extracted from inputDocument according to the KG schema (https://docs.diffbot.com/docs/ontology)",
          "items": {
            "type": "object",
            "properties": {}
          }
        },
        "categories": {
          "$ref": "#/definitions/Categorization"
        },
        "sentences": {
          "type": "array",
          "items": {
            "$ref": "#/definitions/Span"
          }
        },
        "language": {
          "type": "string",
          "description": "Language of the text specified as an [ISO 639-1 code](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes)."
        },
        "summary": {
          "type": "string",
          "description": "Generated summary."
        }
      }
    },
    "NaturalLanguageResponseArray": {
      "type": "array",
      "items": {
        "$ref": "#/definitions/NaturalLanguageResponse"
      },
      "example": [
        {
          "sentiment": 0.0,
          "entities": [
            {
              "name": "Diffbot",
              "diffbotUri": "https://diffbot.com/entity/EYX1i02YVPsuT7fPLUYgRhQ",
              "confidence": 0.99898225,
              "salience": 0.95394653,
              "sentiment": 0.0,
              "isCustom": false,
              "allUris": [
                "http://www.wikidata.org/entity/Q17052069"
              ],
              "allTypes": [
                {
                  "name": "organization",
                  "diffbotUri": "https://diffbot.com/entity/EN1ClYEdMMQCxB6AWTkT3mA",
                  "dbpediaUri": "http://dbpedia.org/ontology/Organisation"
                }
              ],
              "mentions": [
                {
                  "text": "Diffbot",
                  "beginOffset": 0,
                  "endOffset": 7,
                  "confidence": 0.99898225
                }
              ],
              "location": {
                "latitude": 37.456104,
                "longitude": -122.1763,
                "precision": 0.1
              }
            },
            {
              "name": "Menlo Park",
              "diffbotUri": "https://diffbot.com/entity/EQiAUr370NpW1gvx-V4fTrQ",
              "confidence": 0.9996269,
              "salience": 0.9082091,
              "sentiment": 0.0,
              "isCustom": false,
              "allUris": [
                "http://www.wikidata.org/entity/Q74195"
              ],
              "allTypes": [
                {
                  "name": "location",
                  "diffbotUri": "https://diffbot.com/entity/EiCyWUm4lNziqgLHx47iAIQ",
                  "dbpediaUri": "http://dbpedia.org/ontology/Place"
                },
                {
                  "name": "administrative area",
                  "diffbotUri": "https://diffbot.com/entity/EcTIu1tWKPouIa6qZtSpc4A",
                  "dbpediaUri": "http://dbpedia.org/ontology/PopulatedPlace"
                },
                {
                  "name": "city",
                  "diffbotUri": "https://diffbot.com/entity/EzdJrGHiyMWu0XbSn101rFA",
                  "dbpediaUri": "http://dbpedia.org/ontology/City"
                }
              ],
              "mentions": [
                {
                  "text": "Menlo Park",
                  "beginOffset": 30,
                  "endOffset": 40,
                  "confidence": 0.9996269
                }
              ],
              "location": {
                "latitude": 37.454166,
                "longitude": -122.17861,
                "precision": 6.708204
              }
            },
            {
              "name": "startup company",
              "diffbotUri": "https://diffbot.com/entity/EfX0EeXroOmaXrLe-SylIuw",
              "confidence": 0.81958973,
              "salience": 0.6474858,
              "sentiment": 0.0,
              "isCustom": false,
              "allUris": [],
              "mentions": [
                {
                  "text": "startup",
                  "beginOffset": 13,
                  "endOffset": 20,
                  "confidence": 0.81958973
                }
              ]
            }
          ],
          "facts": [
            {
              "humanReadable": "[Diffbot] headquarters [Menlo Park]",
              "entity": {
                "name": "Diffbot",
                "diffbotUri": "https://diffbot.com/entity/EYX1i02YVPsuT7fPLUYgRhQ",
                "confidence": 0.99898225,
                "allUris": [
                  "http://www.wikidata.org/entity/Q17052069"
                ],
                "allTypes": [
                  {
                    "name": "organization",
                    "diffbotUri": "https://diffbot.com/entity/EN1ClYEdMMQCxB6AWTkT3mA",
                    "dbpediaUri": "http://dbpedia.org/ontology/Organisation"
                  }
                ],
                "isCustom": false,
                "entityIndex": 1
              },
              "property": {
                "name": "headquarters",
                "diffbotUri": "https://docs.diffbot.com/docs/ont-organization#location"
              },
              "value": {
                "name": "Menlo Park",
                "diffbotUri": "https://diffbot.com/entity/EQiAUr370NpW1gvx-V4fTrQ",
                "confidence": 0.9996269,
                "allUris": [
                  "http://www.wikidata.org/entity/Q74195"
                ],
                "allTypes": [
                  {
                    "name": "location",
                    "diffbotUri": "https://diffbot.com/entity/EiCyWUm4lNziqgLHx47iAIQ",
                    "dbpediaUri": "http://dbpedia.org/ontology/Place"
                  },
                  {
                    "name": "administrative area",
                    "diffbotUri": "https://diffbot.com/entity/EcTIu1tWKPouIa6qZtSpc4A",
                    "dbpediaUri": "http://dbpedia.org/ontology/PopulatedPlace"
                  },
                  {
                    "name": "city",
                    "diffbotUri": "https://diffbot.com/entity/EzdJrGHiyMWu0XbSn101rFA",
                    "dbpediaUri": "http://dbpedia.org/ontology/City"
                  }
                ],
                "isCustom": false,
                "entityIndex": 0
              },
              "qualifiers": [
                {
                  "property": {
                    "name": "is current"
                  },
                  "value": {
                    "name": "true"
                  },
                  "confidence": 0
                }
              ],
              "confidence": 0.95,
              "evidence": [
                {
                  "passage": "Diffbot is a startup based in Menlo Park.",
                  "entityMentions": [
                    {
                      "text": "Diffbot",
                      "beginOffset": 0,
                      "endOffset": 7,
                      "confidence": 0.99898225
                    }
                  ],
                  "valueMentions": [
                    {
                      "text": "Menlo Park",
                      "beginOffset": 30,
                      "endOffset": 40,
                      "confidence": 0.9996269
                    }
                  ]
                }
              ]
            }
          ]
        }
      ]
    },
    "ErrorResponse": {
      "type": "object",
      "properties": {
        "messages": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      }
    },
    "Qualifier_value": {
      "properties": {
        "name": {
          "type": "string"
        },
        "diffbotUri": {
          "type": "string"
        }
      }
    }
  }
}