OCR
Written by
Updated at August 4, 2026
Image-to-text recognition with Yandex Vision OCR
The base64, url, objectStorage, and disk fields are mutually exclusive: you can use only one of them.
| Field name | Type | Required | Default value | Templating supported | Description |
|---|---|---|---|---|---|
recognizeText |
OCR.RecognizeText | Yes | No | No | Text recognition settings. |
base64 |
string |
No | No | Yes | Base64-encoded image. |
url |
string |
No | No | Yes | Image via a public URL. |
objectStorage |
OCR.ObjectStorage | No | No | No | Image from an Object Storage bucket. |
disk |
OCR.Disk | No | No | No | Image on Yandex Disk. |
OCR.RecognizeText
|
Field name |
Type |
This is a required field |
Default value |
Templating supported |
Description |
|
|
|
Yes |
No |
No |
Image file format. Available formats: |
|
|
|
Yes |
No |
No |
Text recognition languages. Available languages
|
|
|
|
Yes |
No |
No |
Text recognition model. Available models
|
OCR.ObjectStorage
| Field name | Type | Required | Default value | Templating supported | Description |
|---|---|---|---|---|---|
bucket |
string |
Yes | No | No | Name of the Object Storage bucket the image file is in. |
object |
string |
Yes | No | Yes | Object name, e.g., prefix/subprefix/data.png. |
OCR.Disk
| Field name | Type | Required | Default value | Templating supported | Description |
|---|---|---|---|---|---|
oauthToken |
string |
Yes | No | No | OAuth token |
path |
string |
Yes | No | Yes | Image file path. |
sharedDiskId |
string |
No | No | Yes | Shared disk label |