---
canonical_url: "https://docs.composio.dev/toolkits/nanonets_ocr"
markdown_url: "https://docs.composio.dev/toolkits/nanonets_ocr.md"
product: "platform"
version: null
last_updated: null
---

# Nanonets OCR

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

- **Category:** documents & ocr
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 6
- **Triggers:** 0
- **Slug:** `NANONETS_OCR`
- **Version:** 20261014_00

## Tools

### Extract From Public URL

**Slug:** `NANONETS_OCR_EXTRACT_FROM_URL`

Synchronously extract model-defined fields and tables from one publicly reachable document URL. Returns durable page and file IDs even when the model finds no matching fields.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Publicly reachable document or image URL. Nanonets must be able to download it without authentication. |
| `model_id` | string | Yes | Hosted OCR model ID to use; confirm readiness with NANONETS_OCR_GET_MODEL. |
| `request_metadata` | string | No | Optional caller correlation metadata persisted with the prediction and returned by history and result tools. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get OCR Model

**Slug:** `NANONETS_OCR_GET_MODEL`

Get readiness, accuracy, extraction fields, and table configuration for one Nanonets OCR model.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model_id` | string | Yes | OCR model ID returned by NANONETS_OCR_LIST_MODELS. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model_id` | string | Yes | OCR model ID used for the prediction. |
| `request_file_id` | string | Yes | File-level prediction ID returned by extraction or NANONETS_OCR_LIST_PREDICTIONS. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get OCR Prediction Page

**Slug:** `NANONETS_OCR_GET_PREDICTION_PAGE`

Get normalized extracted fields and tables for one OCR prediction page.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `page_id` | string | Yes | Page-level ID returned by extraction, file retrieval, or NANONETS_OCR_LIST_PREDICTIONS. |
| `model_id` | string | Yes | OCR model ID used for the prediction. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `end_date` | string | Yes | Inclusive UTC end date in YYYY-MM-DD format; must not precede start_date. |
| `model_id` | string | Yes | OCR model ID whose prediction history to inspect. |
| `start_date` | string | Yes | Inclusive UTC start date in YYYY-MM-DD format. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |