> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Nanonets OCR

> Nanonets OCR extracts structured data from documents using trained, model-based OCR workflows.

![Nanonets OCR logo](https://mintcdn.com/composio-preview/9YPuzjEU4UlMnwGq/images/toolkits/nanonets_ocr.svg?fit=max\&auto=format\&n=9YPuzjEU4UlMnwGq\&q=85\&s=df9dc5b751355587e0c81399045112b1)

* **Category:** documents & ocr
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 6
* **Triggers:** 0
* **Slug:** `NANONETS_OCR`
* **Version:** 20261101\_00

## Tools

> [accordion] Extract From Public URL
>
> **Slug:** `NANONETS_OCR_EXTRACT_FROM_URL`
>
> Synchronously extract model-defined fields and tables from one publicly reachable document URL. Returns normalized page results, with page and file IDs when supplied by Nanonets, even if no matching fields are found.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Publicly reachable document or image URL. Nanonets must be able to download it without authentication.
>
> **model\_id** `string` *required*
>
> Hosted OCR model ID to use; confirm readiness with NANONETS\_OCR\_GET\_MODEL.
>
> **request\_metadata** `string`
>
> Optional caller correlation metadata persisted with the prediction and returned by history and result tools.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get OCR Model
>
> **Slug:** `NANONETS_OCR_GET_MODEL`
>
> Get readiness, accuracy, extraction fields, and table configuration for one Nanonets OCR model.
>
> #### Input Parameters
>
> **model\_id** `string` *required*
>
> OCR model ID returned by NANONETS\_OCR\_LIST\_MODELS.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get OCR Prediction File
>
> **Slug:** `NANONETS_OCR_GET_PREDICTION_FILE`
>
> Get normalized extraction results for every page of one previously processed Nanonets OCR file. A successful page can have no extracted fields.
>
> #### Input Parameters
>
> **model\_id** `string` *required*
>
> OCR model ID used for the prediction.
>
> **request\_file\_id** `string` *required*
>
> File-level prediction ID returned by extraction or NANONETS\_OCR\_LIST\_PREDICTIONS.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get OCR Prediction Page
>
> **Slug:** `NANONETS_OCR_GET_PREDICTION_PAGE`
>
> Get normalized extracted fields and tables for an OCR prediction page. If the response contains no page matching the requested ID, the tool returns the first page in the response.
>
> #### Input Parameters
>
> **page\_id** `string` *required*
>
> Page-level ID returned by extraction, file retrieval, or NANONETS\_OCR\_LIST\_PREDICTIONS.
>
> **model\_id** `string` *required*
>
> OCR model ID used for the prediction.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List OCR Models
>
> **Slug:** `NANONETS_OCR_LIST_MODELS`
>
> List the OCR models available to the connected Nanonets account, including each model's ID, readiness state, and extraction categories.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List OCR Predictions
>
> **Slug:** `NANONETS_OCR_LIST_PREDICTIONS`
>
> List compact OCR prediction-page summaries for a model within an inclusive UTC date range. Nanonets returns the entire matching range without pagination, so prefer narrow ranges when a model has substantial history.
>
> #### Input Parameters
>
> **end\_date** `string` *required*
>
> Inclusive UTC end date in YYYY-MM-DD format; must not precede start\_date.
>
> **model\_id** `string` *required*
>
> OCR model ID whose prediction history to inspect.
>
> **start\_date** `string` *required*
>
> Inclusive UTC start date in YYYY-MM-DD format.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
