The Custom Document Parsing Async API from Eden AI — 2 operation(s) for custom document parsing async.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
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.curl "https://apis.io/api/v1/apis/eden-ai:eden-ai-custom-document-parsing-async-api"curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a 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: 3.2.0
info:
title: OCR Features Custom Document Parsing Async API
version: '2.0'
description: Your project description
servers:
- url: https://api.edenai.run/v2
tags:
- name: Custom Document Parsing Async
paths:
/ocr/custom_document_parsing_async/:
get:
operationId: ocr_custom_document_parsing_async_retrieve
description: 'Get a list of all jobs launched for this feature. You''ll then be able to use the ID of each one to get its status and results.
Please note that a **job status doesn''t get updated until a get request** is sent.'
summary: Custom Document Parsing List Job
tags:
- Custom Document Parsing Async
security:
- FeatureApiAuth: []
- {}
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/ListAsyncJobResponse'
examples:
ResponseExample:
value:
jobs:
- providers: '[''extracta'', ''amazon'']'
nb: 2
nb_ok: 2
public_id: a8d7c813-bcf5-4718-95af-d238dca00198
state: finished
created_at: '2026-09-06T03:58:32.131274'
- providers: '[''extracta'', ''amazon'']'
nb: 2
nb_ok: 2
public_id: f118ac78-7f71-4c7d-8ed2-adce4cf3b3ff
state: finished
created_at: '2026-09-06T02:58:32.131285'
- providers: '[''extracta'', ''amazon'']'
nb: 2
nb_ok: 2
public_id: bf66ba46-0381-4e08-aaf4-2f6ddfc39f66
state: finished
created_at: '2026-09-06T01:58:32.131289'
summary: Response Example
description: ''
post:
operationId: ocr_custom_document_parsing_async_create
description: 'Available Providers
|Provider|Version|Price|Billing unit|
|----|-------|-----|------------|
|**amazon**|`boto3 1.26.8`|15.0 (per 1000 page)|1 page
|**extracta**|`v1`|0.1 (per 1 page)|1 page
Supported Languages
|Name|Value|
|----|-----|
|**English**|`en`|
|**French**|`fr`|
|**German**|`de`|
|**Italian**|`it`|
|**Portuguese**|`pt`|
|**Spanish**|`es`|'
summary: Custom Document Parsing Launch Job
tags:
- Custom Document Parsing Async
requestBody:
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/CustomDocumentParsingAsyncRequest'
examples:
RequestExample:
value:
providers: extracta,amazon
file: /edenai/edenai/features/ocr/samples/data/resume.pdf
queries: '[{"query" : "What is the person full-name","pages" : "1-*"},{"query" : "What is the first Adult Care experience?","pages" : "1"}]'
summary: Request Example
application/json:
schema:
$ref: '#/components/schemas/CustomDocumentParsingAsyncRequest'
examples:
RequestExample:
value:
providers: extracta,amazon
queries: '[{"query" : "What is the person full-name","pages" : "1-*"},{"query" : "What is the first Adult Care experience?","pages" : "1"}]'
file_url: http://edenai-resource-example.pdf
summary: Request Example
required: true
security:
- FeatureApiAuth: []
- {}
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/LaunchAsyncJobResponse'
examples:
ResponseExample:
value:
public_id: 263a0b9b-5e8e-43c7-855f-00df2b92d7dd
summary: Response Example
description: ''
delete:
operationId: ocr_custom_document_parsing_async_destroy
description: 'Generic class to handle method GET all async job for user
Attributes:
feature (str): EdenAI feature
subfeature (str): EdenAI subfeature'
summary: Custom Document Parsing delete Jobs
tags:
- Custom Document Parsing Async
security:
- FeatureApiAuth: []
- {}
responses:
'204':
description: No response body
/ocr/custom_document_parsing_async/{public_id}/:
get:
operationId: ocr_custom_document_parsing_async_retrieve_2
description: Get the status and results of an async job given its ID.
summary: Custom Document Parsing Get Job Results
parameters:
- in: path
name: public_id
schema:
type: string
required: true
- in: query
name: response_as_dict
schema:
type: boolean
default: true
- in: query
name: show_base_64
schema:
type: boolean
default: true
- in: query
name: show_original_response
schema:
type: boolean
default: false
tags:
- Custom Document Parsing Async
security:
- FeatureApiAuth: []
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/asyncocrcustom_document_parsing_asyncResponseModel'
examples:
ResponseExample:
value:
public_id: 0706ce7f-4f84-4143-a7a4-1a82df2a35a5
status: finished
error: null
results:
extracta:
error: null
id: 1594a51f-9f8d-449e-921c-5fc33309c7db
final_status: finished
items:
- confidence: 1.0
value: jwsmith@colostate.edu
query: What is the resume's email address?
bounding_box:
left: 0.0
top: 0.0
width: 0.0
height: 0.0
page: 0
- confidence: 1.0
value: Determined work placement for 150 special needs adult clients.
query: What is the first Adult Care experience?
bounding_box:
left: 0.0
top: 0.0
width: 0.0
height: 0.0
page: 0
amazon:
error: null
id: 78fb0dc7-26a0-4a24-8eb6-5da35f7142f5
final_status: finished
items:
- confidence: 97.0
value: jwsmith@colostate.edu
query: What is the resume's email address?
bounding_box:
left: 0.40480345487594604
top: 0.13232094049453735
width: 0.18646040558815002
height: 0.014690706506371498
page: 1
- confidence: 89.0
value: Determined work placement for 150 special needs adult clients.
query: What is the first Adult Care experience?
bounding_box:
left: 0.17573566734790802
top: 0.27843594551086426
width: 0.4986802041530609
height: 0.014926792122423649
page: 1
summary: Response Example
description: ''
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/BadRequest'
description: ''
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: ''
'403':
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: ''
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/NotFoundResponse'
description: ''
components:
schemas:
BadRequest:
type: object
properties:
error:
$ref: '#/components/schemas/NestedBadRequest'
required:
- error
NestedBadRequest:
type: object
properties:
type:
type: string
message:
$ref: '#/components/schemas/FieldError'
required:
- message
- type
CustomDocumentParsingAsyncBoundingBox:
properties:
left:
title: Left
type: integer
top:
title: Top
type: integer
width:
title: Width
type: integer
height:
title: Height
type: integer
required:
- left
- top
- width
- height
title: CustomDocumentParsingAsyncBoundingBox
type: object
NestedError:
type: object
properties:
type:
type: string
message:
type: string
required:
- message
- type
ocrcustom_document_parsing_asyncCustomDocumentParsingAsyncDataClass:
properties:
items:
items:
$ref: '#/components/schemas/CustomDocumentParsingAsyncItem'
title: Items
type: array
original_response:
default: null
description: original response sent by the provider, hidden by default, show it by passing the `show_original_response` field to `true` in your request
title: Original Response
id:
title: Id
type: string
final_status:
allOf:
- $ref: '#/components/schemas/FinalStatusEnum'
title: Final Status
error:
additionalProperties: true
default: null
title: Error
type: object
required:
- id
- final_status
title: ocrcustom_document_parsing_asyncCustomDocumentParsingAsyncDataClass
type: object
ListAsyncJobResponse:
type: object
properties:
jobs:
type: array
items:
$ref: '#/components/schemas/AsyncJobList'
required:
- jobs
AsyncJobList:
type: object
properties:
providers:
type: string
nb:
type: integer
nb_ok:
type: integer
public_id:
type: string
format: uuid
state:
$ref: '#/components/schemas/StateEnum'
created_at:
type: string
format: date-time
required:
- created_at
- nb
- nb_ok
- providers
- public_id
- state
NotFoundResponse:
type: object
properties:
details:
type: string
default: Not Found
FieldError:
type: object
properties:
<parameter_name>:
type: array
items:
type: string
required:
- <parameter_name>
FinalStatusEnum:
enum:
- sucess
- fail
type: string
Error:
type: object
properties:
error:
$ref: '#/components/schemas/NestedError'
required:
- error
ocrcustom_document_parsing_asyncModel:
properties:
amazon:
$ref: '#/components/schemas/ocrcustom_document_parsing_asyncCustomDocumentParsingAsyncDataClass'
default: null
extracta:
$ref: '#/components/schemas/ocrcustom_document_parsing_asyncCustomDocumentParsingAsyncDataClass'
default: null
title: ocrcustom_document_parsing_asyncModel
type: object
LaunchAsyncJobResponse:
type: object
properties:
public_id:
type: string
format: uuid
required:
- public_id
CustomDocumentParsingAsyncRequest:
type: object
properties:
settings:
type: string
default: {}
description: "A dictionnary or a json object to specify specific models to use for some providers. <br> It can be in the following format: {\"google\" : \"google_model\", \"ibm\": \"ibm_model\"...}.\n "
providers:
type: array
items:
type: string
minLength: 1
description: 'It can be one (ex: **''amazon''** or **''google''**) or multiple provider(s) (ex: **''amazon,microsoft,google''**) that the data will be redirected to in order to get the processed results.<br> Providers can also be invoked with specific models (ex: providers: **''amazon/model1, amazon/model2, google/model3''**)'
fallback_providers:
type: array
items:
type: string
default: []
description: "Providers in this list will be used as fallback if the call to provider in `providers` parameter fails.\n To use this feature, you must input **only one** provider in the `providers` parameter. but you can put up to 5 fallbacks.\n\nThey will be tried in the same order they are input, and it will stop to the first provider who doesn't fail.\n\n\n*Doesn't work with async subfeatures.*\n "
maxItems: 5
show_original_response:
type: boolean
default: false
description: "Optional : Shows the original response of the provider.<br>\n When set to **true**, a new attribute *original_response* will appear in the response object."
webhook_receiver:
type: string
format: uri
minLength: 1
description: 'Webhook receiver should be a valid https URL (ex : https://your.listner.com/endpoint). After the processing is done, the webhook endpoint will receive a POST request with the result.'
users_webhook_parameters:
description: 'Json data that contains of additional parameters that will be sent back to the webhook receiver (ex: api key for security or client''s data ID to link the result internally). Will only be used when webhook_receiver is set.'
send_webhook_data:
type: boolean
default: true
description: If set to false the webhook will not contain the result data. Use if your webhook receiver has a request size limit.
show_base_64:
type: boolean
default: true
file:
type: string
format: binary
description: 'File to analyse in binary format to be used with *content-type*: **multipart/form-data** <br> **Does not work with application/json !**'
file_url:
type:
- string
- 'null'
format: uri
description: 'File **URL** to analyse to be used with with *content-type*: **application/json**.'
file_password:
type:
- string
- 'null'
description: If your PDF file has a password, you can pass it here!
maxLength: 200
queries:
type: string
minLength: 1
description: 'Your queries need to be a list of dict containing the questions you want answered and the page to look for the information in : ''[{''query'':''your query'',''pages'':''your pages''},{''query'':''your query'',''pages'':''your pages''}]'''
convert_to_pdf:
type:
- boolean
- 'null'
default: false
description: Boolean value to specify weather to convert the doc/docx files to pdf format to be accepted by a majority of the providers
required:
- providers
- queries
asyncocrcustom_document_parsing_asyncResponseModel:
properties:
results:
$ref: '#/components/schemas/ocrcustom_document_parsing_asyncModel'
error:
title: Error
type: string
public_id:
format: uuid
title: Public Id
type: string
status:
title: Status
type: string
required:
- results
- error
- public_id
- status
title: asyncocrcustom_document_parsing_asyncResponseModel
type: object
StateEnum:
enum:
- finished
- failed
- Timeout error
- processing
type: string
description: '* `finished` - finished
* `failed` - failed
* `Timeout error` - Timeout error
* `processing` - processing'
CustomDocumentParsingAsyncItem:
properties:
confidence:
title: Confidence
type: integer
value:
title: Value
type: string
query:
title: Query
type: string
bounding_box:
$ref: '#/components/schemas/CustomDocumentParsingAsyncBoundingBox'
page:
title: Page
type: integer
required:
- confidence
- value
- query
- bounding_box
- page
title: CustomDocumentParsingAsyncItem
type: object
securitySchemes:
FeatureApiAuth:
type: http
scheme: bearer
bearerFormat: JWT