Skip to main content

Update a Check

PUT 

/api/v8/partner/checks/:document_id

Veryfi's Update a Document by ID endpoint allows you to change a Document that Veryfi's Machine Learning models have already processed. This feature will enable users to update Documents previously processed by Veryfi to ensure data extraction accuracy. Updating a Document is especially useful for correcting mistakes and updating information over time. By changing a processed Document, Veryfi's Machine Learning models can re-learn the updated information, allowing them to stay accurate and up-to-date.

Request

Path Parameters

    document_id int64required

    The unique identifier of the document.

Body

    external_id (string | null)deprecated

    Possible values: non-empty

    Deprecated 2025-01-09, use meta.external_id instead.

    meta CheckPUTMeta
    external_id (string | null)

    Possible values: non-empty

    tags string[]

    Possible values: non-empty

    Default value: ``

    amount_text_value (number | null)
    amount DetailedPUTPositiveFloatField
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (number | null)required

    Possible values: > 0

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • amount_text object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bank_address object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • bank_name object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • fractional_routing_number object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • micr PUTMICRData
    routing_number object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • account_number object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • serial_number object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • raw object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • check_number object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • date object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value daterequired
    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • is_signed object
    value booleanrequired
    memo object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • endorsement PUTEndorsementData
    is_signed object
    value booleanrequired
    is_mobile_or_remote_deposit_only object
    value booleanrequired
    payer_address object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • payer_name object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • receiver_address object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: >= 4 characters

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • receiver_name object
    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    value (string | null)required

    Possible values: non-empty

    The value to update

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • currency_code object

    The currency code in ISO 4217 format.

    value stringrequired

    Possible values: [BMD, RSD, AFN, LTL, XCD, ILS, BGN, JEP, QAR, GGP, NOK, HTG, CRC, NAD, EGP, SBD, YER, ARS, BHD, CAD, SOS, DKK, IMP, MKD, EEK, TWD, GNF, NZD, FKP, RON, LKR, SVC, BYR, MVR, TRY, USD, INR, LVL, GBP, AZN, GIP, SZL, UAH, KRW, UYU, BRL, KWD, SHP, JPY, KZT, ZAR, SGD, UGX, GTQ, HRK, NGN, LBP, ISK, BND, PAB, BSD, HUF, AUD, JMD, HNL, EUR, AED, IDR, LSL, ALL, TTD, MOP, TVD, RUB, TRL, BBD, GHC, SAR, PHP, BZD, VND, CZK, SEK, IQD, SRD, PYG, CUP, SCR, HKD, AMD, CNY, NIO, PKR, KGS, MXN, PLN, ZWD, MNT, NPR, DOP, LRD, COP, UZS, MUR, IRR, LAK, CLP, BWP, CHF, PEN, SYP, FJD, GEL, BOB, BAM, OMR, THB, VEF, KYD, KHR, AWG, GYD, MYR, MZN, ANG, KPW]

    custom_fields object

    A user-defined dictionary that contains all the custom fields generated by applying specific rules and regular expressions to the extracted data.

    anyOf

Responses

A processed Check response.

Schema
    external_id (string | null)

    Possible values: non-empty

    A custom identification value. Use this if you would like to assign your own ID to documents. This parameter is useful when mapping this document to a service or resource outside Veryfi.

    meta object
    duplicates object[]

    An array of duplicate documents found in the system.

  • Array [
  • id integerrequired

    The id of the duplicate document.

    url urirequired

    Possible values: non-empty and <= 2083 characters

    The url of the duplicate document.

    score numberrequired

    Possible values: <= 1

    How close is the match

  • ]
  • external_id (string | null)

    Possible values: non-empty

    A custom identification value. Use this if you would like to assign your own ID to documents. This parameter is useful when mapping this document to a service or resource outside Veryfi.

    pages object[]

    Pages meta details

  • Array [
  • ocr_score (number | null)

    Possible values: <= 1

    The average OCR score of the page.

    width (integer | null)

    The width of the page.

    height (integer | null)

    The height of the page.

    is_front (boolean | null)

    Specifies whether the image represents the front side of the check.

    is_blurry ClassNullableBoolField

    The processed page is blurry or not

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    value (boolean | null)required

    The extracted value.

    tiff_url uri

    Possible values: non-empty and <= 2083 characters

    The urls of the tiff file.

  • ]
  • tags string[]

    Possible values: non-empty

    Default value: ``

    Tags associated with the document.

    ocr_score (number | null)

    Possible values: <= 1

    The average OCR score of the whole document.

    model (string | null)

    Possible values: non-empty

    The version of the model used to process the document.

    fraud ChecksFraud

    An object that contains additional information to help check for fraud.

    score (number | null)

    Possible values: <= 1

    Confidence of Fraud Detector in it's prediction

    color (string | null)

    Possible values: [green, yellow, red]

    Color from Fraud Detector: green means legitimate, yellow means review needed and red means fraud

    types string[]

    Possible values: [LCD photo, not a document, duplicate, screenshot, generated document, aspect ratio mismatch]

    List of attributions which marked the document as fraud

    pages object[]

    An array containing fraud info about each extracted page

  • Array [
  • anyOf
    is_lcd ClassBoolField
    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    value booleanrequired

    The extracted value.

    flags object[]

    List of flags which marked the document as fraud

  • Array [
  • score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    value stringrequired

    Possible values: non-empty

  • ]
  • four_corners_detected (boolean | null)

    Indicates that all four corners of the check are visible and within the boundaries of the image.

  • ]
  • amount_text_value (number | null)

    The original amount_text found in the check converted to a float.

    handwritten_fields string[]

    Possible values: [amount, amount_text, bank_address, bank_name, fractional_routing_number, micr.raw, check_number, date, memo, payer_address, payer_name, receiver_address, receiver_name]

    Default value: ``

    Handwritten fields on check

    digital_tampering_fields string[]

    Possible values: [amount, amount_text, bank_address, bank_name, fractional_routing_number, micr.raw, check_number, date, memo, payer_address, payer_name, receiver_address, receiver_name]

    Default value: ``

    Digital tampering fields on check

    pdf_url uri

    Possible values: non-empty and <= 2083 characters

    A signed URL to access the auto-generated PDF created from the submitted document. This URL expires 15 minutes after the response object is returned and is resigned during every GET request.

    id integerrequired

    The unique number created to identify the document.

    created_date date-timerequired
    updated_date date-timerequired
    img_thumbnail_url uri

    Possible values: non-empty and <= 2083 characters

    A signed URL to access the auto-generated thumbnail created for the submitted document. This URL expires 15 minutes after the response object is returned and is resigned during every GET request.

    text (string | null)

    The text returned from converting the document into a machine-readable text format.

    custom_fields CustomFields

    A user-defined dictionary that contains all the custom fields generated by applying specific rules and regular expressions to the extracted data.

    amount objectrequired

    The numeric value representing the amount found on the document.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (number | null)required
    amount_text objectrequired

    The value as a string representing the amount found on the document.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    bank_address objectrequired

    The address of the bank.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    bank_name objectrequired

    The name of the bank.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    fractional_routing_number object

    The numbers appearing as the denominator of a fraction that is printed in the upper portion of a check.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    routing_from_fractional objectrequired

    The routing number from the found in the fractional_routing_number.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    check_number objectrequired

    The check number.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    date objectrequired

    The date in ISO 8601 format. Typically found on invoices.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value daterequired
    memo objectrequired

    The description found in the memo line of the check.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    payer_address objectrequired

    The address of the payer.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    payer_name objectrequired

    The name of the payer.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    receiver_address objectrequired

    The address of the receiver.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    receiver_name objectrequired

    The name of the receiver.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    is_signed objectrequired

    Presence of a signature on the check (front of check image)

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (boolean | null)required
    currency_code DetailedCurrencyChoicerequired
    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    value (string | null)required

    Possible values: [BMD, RSD, AFN, LTL, XCD, ILS, BGN, JEP, QAR, GGP, NOK, HTG, CRC, NAD, EGP, SBD, YER, ARS, BHD, CAD, SOS, DKK, IMP, MKD, EEK, TWD, GNF, NZD, FKP, RON, LKR, SVC, BYR, MVR, TRY, USD, INR, LVL, GBP, AZN, GIP, SZL, UAH, KRW, UYU, BRL, KWD, SHP, JPY, KZT, ZAR, SGD, UGX, GTQ, HRK, NGN, LBP, ISK, BND, PAB, BSD, HUF, AUD, JMD, HNL, EUR, AED, IDR, LSL, ALL, TTD, MOP, TVD, RUB, TRL, BBD, GHC, SAR, PHP, BZD, VND, CZK, SEK, IQD, SRD, PYG, CUP, SCR, HKD, AMD, CNY, NIO, PKR, KGS, MXN, PLN, ZWD, MNT, NPR, DOP, LRD, COP, UZS, MUR, IRR, LAK, CLP, BWP, CHF, PEN, SYP, FJD, GEL, BOB, BAM, OMR, THB, VEF, KYD, KHR, AWG, GYD, MYR, MZN, ANG, KPW]

    endorsement object

    An object containing the endorsement details

    is_endorsed object

    Presence of an endorsement (back of check image). True if there is a signature, or a name that matches the payee name

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (boolean | null)required
    is_signed object

    Presence of an endorsement signature (back of check image).

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (boolean | null)required
    receiver_name object

    Raw receiver name on endorsement.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    instructions object

    Raw instructions on endorsement.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    mobile_or_remote_deposit object

    Mobile or remote desposit endorsement.

    checkbox object

    Presence of checked box indicating that the deposit is for mobile or remote deposit only.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (boolean | null)required
    instructions object

    Presence of instructions stating that the deposit is for mobile or remote deposit only.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    value (boolean | null)required

    The extracted value.

    is_mobile_or_remote_deposit_only object

    deprecated and will be removed at 2025-07-10. Use endorsement.mobile_or_remote_deposit instead

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (boolean | null)required
    micr object

    An object containing the details for the Magnetic ink character recognition.

    routing_number object

    The Transit Field. It is always 8-9 digits, preceded by a ⑆, and followed by a ⑆.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    account_number objectrequired

    The bank account number.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    serial_number object

    The serial number on checks.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

    raw object

    The text returned from converting the document into a machine-readable text format.

    score (number | null)

    Possible values: <= 1

    The score shows how confident the model is that the predicted value belongs to the field. See confidence scores explained for more information.

    bounding_region number[]

    Possible values: >= 8, <= 8

    An array containing (x,y) coordinates in the format [x1,y1,x2,y2,x3,y3,x4,y4]` for skewed images and handwritten fields. The bounding region is more precise than bounding box, otherwise it's the same.

    bounding_box object[]

    Possible values: >= 5, <= 5

    An array containing relative coordinates in the format [page_number,x1,y1,x2,y2] for the extracted field from img_url before any rotation.

  • Array [
  • anyOf

    number

  • ]
  • ocr_score (number | null)

    Possible values: <= 1

    The score which shows how confident the model in recognizing value symbols. See confidence scores explained for more information.

    rotation (integer | null)

    Possible values: [0, 90, 180, 270]

    The angle of rotation of the document in degrees.

    value (string | null)required

    Possible values: non-empty

    The extracted value.

Loading...