OCR

post

https://api.edenai.run/v2/ocr/ocr/

Available Providers

Provider	Version	Price	Billing unit
amazon	`boto3 (v1.15.18)`	1.5 (per 1000 page)	1 page
google	`v1`	1.5 (per 1000 page)	1 page
microsoft	`v3.2`	1.0 (per 1000 page)	1 page
sentisight	`v3.3.1`	0.75 (per 1000 file)	1 file
api4ai	`v1.0.0`	3.0 (per 1000 request)	1 request
mistral	`v1`	1.0 (per 1000 page)	1 page

Supported Languages

Name	Value
Abaza	`abq`
Adyghe	`ady`
Afrikaans	`af`
Albanian	`sq`
Angika	`anp`
Arabic	`ar`
Assamese	`as`
Asturian	`ast`
Avaric	`av`
Awadhi	`awa`
Azerbaijani	`az`
Bagheli	`bfy`
Basque	`eu`
Belarusian	`be`
Bengali	`bn`
Bhojpuri	`bho`
Bihari languages	`bh`
Bislama	`bi`
Bodo (India)	`brx`
Bosnian	`bs`
Braj	`bra`
Breton	`br`
Bulgarian	`bg`
Bundeli	`bns`
Buriat	`bua`
Camling	`rab`
Catalan	`ca`
Cebuano	`ceb`
Chamorro	`ch`
Chechen	`ce`
Chhattisgarhi	`hne`
Chinese	`zh`
Cornish	`kw`
Corsican	`co`
Crimean Tatar	`crh`
Croatian	`hr`
Czech	`cs`
Danish	`da`
Dargwa	`dar`
Dari	`prs`
Dhimal	`dhi`
Dogri (macrolanguage)	`doi`
Dutch	`nl`
English	`en`
Erzya	`myv`
Estonian	`et`
Faroese	`fo`
Fijian	`fj`
Filipino	`fil`
Finnish	`fi`
French	`fr`
Friulian	`fur`
Gagauz	`gag`
Galician	`gl`
German	`de`
Gilbertese	`gil`
Goan Konkani	`gom`
Gondi	`gon`
Gurung	`gvr`
Haitian	`ht`
Halbi	`hlb`
Hani	`hni`
Haryanvi	`bgc`
Hawaiian	`haw`
Hindi	`hi`
Hmong Daw	`mww`
Ho	`hoc`
Hungarian	`hu`
Icelandic	`is`
Inari Sami	`smn`
Indonesian	`id`
Ingush	`inh`
Interlingua (International Auxiliary Language Association)	`ia`
Inuktitut	`iu`
Irish	`ga`
Italian	`it`
Japanese	`ja`
Jaunsari	`jns`
Javanese	`jv`
K'iche'	`quc`
Kabardian	`kbd`
Kabuverdianu	`kea`
Kachin	`kac`
Kalaallisut	`kl`
Kangri	`xnr`
Kara-Kalpak	`kaa`
Karachay-Balkar	`krc`
Kashubian	`csb`
Kazakh	`kk`
Khaling	`klr`
Khasi	`kha`
Kirghiz	`ky`
Korean	`ko`
Korku	`kfq`
Koryak	`kpy`
Kosraean	`kos`
Kumarbhag Paharia	`kmj`
Kumyk	`kum`
Kurdish	`ku`
Kurukh	`kru`
Kölsch	`ksh`
Lak	`lbe`
Lakota	`lkt`
Latin	`la`
Latvian	`lv`
Lezghian	`lez`
Lithuanian	`lt`
Lower Sorbian	`dsb`
Lule Sami	`smj`
Luxembourgish	`lb`
Mahasu Pahari	`bfz`
Maithili	`mai`
Malay (macrolanguage)	`ms`
Maltese	`mt`
Manx	`gv`
Maori	`mi`
Marathi	`mr`
Marshallese	`mh`
Mongolian	`mn`
Montenegrin	`cnr`
Neapolitan	`nap`
Nepali (macrolanguage)	`ne`
Newari	`new`
Niuean	`niu`
Nogai	`nog`
Northern Sami	`se`
Norwegian	`no`
Occitan (post 1500)	`oc`
Old English (ca. 450-1100)	`ang`
Ossetian	`os`
Pali	`pi`
Panjabi	`pa`
Persian	`fa`
Polish	`pl`
Portuguese	`pt`
Pushto	`ps`
Romanian	`ro`
Romansh	`rm`
Russian	`ru`
Sadri	`sck`
Samoan	`sm`
Sanskrit	`sa`
Santali	`sat`
Scots	`sco`
Scottish Gaelic	`gd`
Serbian	`sr`
Sherpa	`xsr`
Sirmauri	`srx`
Skolt Sami	`sms`
Slovak	`sk`
Slovenian	`sl`
Somali	`so`
Southern Sami	`sma`
Spanish	`es`
Swahili (macrolanguage)	`sw`
Swedish	`sv`
Tabassaran	`tab`
Tagalog	`tl`
Tajik	`tg`
Tatar	`tt`
Tetum	`tet`
Thangmi	`thf`
Tonga (Tonga Islands)	`to`
Turkish	`tr`
Turkmen	`tk`
Tuvinian	`tyv`
Uighur	`ug`
Ukrainian	`uk`
Upper Sorbian	`hsb`
Urdu	`ur`
Uzbek	`uz`
Vietnamese	`vi`
Volapük	`vo`
Walser	`wae`
Welsh	`cy`
Western Frisian	`fy`
Yucateco	`yua`
Zhuang	`za`
Zulu	`zu`

Supported Detailed Languages

Name	Value
Auto detection	`auto-detect`
Arabic (Pseudo-Accents)	`ar-XA`
Belarusian	`be-cyrl`
Belarusian (Latin)	`be-latn`
Chinese (China)	`zh-CN`
Chinese (Simplified)	`zh-Hans`
Chinese (Taiwan)	`zh-TW`
Chinese (Traditional)	`zh-Hant`
Danish (Denmark)	`da-DK`
Dutch (Netherlands)	`nl-NL`
English (United States)	`en-US`
Finnish (Finland)	`fi-FI`
French (France)	`fr-FR`
German (Germany)	`de-DE`
Hungarian (Hungary)	`hu-HU`
Italian (Italy)	`it-IT`
Japanese (Japan)	`ja-JP`
Kara-Kalpak (Cyrillic)	`kaa-Cyrl`
Kazakh	`kk-cyrl`
Kazakh (Latin)	`kk-latn`
Korean (South Korea)	`ko-KR`
Kurdish (Arabic)	`ku-arab`
Kurdish (Latin)	`ku-latn`
Polish	`pl-PO`
Portuguese (Portugal)	`pt-PT`
Region: Czechia	`cz-CZ`
Region: Greece	`gr-GR`
Russian (Russia)	`ru-RU`
Serbian (Cyrillic, Montenegro)	`sr-Cyrl-ME`
Serbian (Latin)	`sr-latn`
Serbian (Latin, Montenegro)	`sr-Latn-ME`
Spanish (Spain)	`es-ES`
Swedish (Sweden)	`sv-SE`
Turkish (Türkiye)	`tr-TR`
Uzbek (Arabic)	`uz-arab`
Uzbek (Cyrillic)	`uz-cyrl`

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

settings

string

Defaults to [object Object]

A dictionnary or a json object to specify specific models to use for some providers.
It can be in the following format: {"google" : "google_model", "ibm": "ibm_model"...}.

providers

array of strings

required

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.
Providers can also be invoked with specific models (ex: providers: 'amazon/model1, amazon/model2, google/model3')

providers*

fallback_providers

array of strings

length ≤ 5

Defaults to

Providers in this list will be used as fallback if the call to provider in providers parameter fails. To use this feature, you must input only one provider in the providers parameter. but you can put up to 5 fallbacks.

They will be tried in the same order they are input, and it will stop to the first provider who doesn't fail.

Doesn't work with async subfeatures.

fallback_providers

response_as_dict

boolean

Defaults to true

Optional : When set to true (default), the response is an object of responses with providers names as keys :
{"google" : { "status": "success", ... }, }
When set to false the response structure is a list of response objects :
[{"status": "success", "provider": "google" ... }, ].

attributes_as_list

boolean

Defaults to false

Optional : When set to false (default) the structure of the extracted items is list of objects having different attributes :
{'items': [{"attribute_1": "x1","attribute_2": "y2"}, ... ]}
When it is set to true, the response contains an object with each attribute as a list :
{ "attribute_1": ["x1","x2", ...], "attribute_2": [y1, y2, ...]}

show_base_64

boolean

Defaults to true

show_original_response

boolean

Defaults to false

Optional : Shows the original response of the provider.
When set to true, a new attribute original_response will appear in the response object.

file

File to analyse in binary format to be used with content-type: multipart/form-data
Does not work with application/json !

file_url

uri | null

File URL to analyse to be used with with content-type: application/json.

file_password

string | null

If your PDF file has a password, you can pass it here!

language

string | null

Language code of the language the document is written in (ex: fr (French), en (English), es (Spanish))

Responses

200

400

403

404

500