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

# Airparser

Airparser extracts structured data from emails, documents, and other files using AI-powered parsing.

- **Category:** documents & ocr
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 10
- **Triggers:** 0
- **Slug:** `AIRPARSER`
- **Version:** 20261014_00

## Tools

### Clone Extraction Schema

**Slug:** `AIRPARSER_CLONE_EXTRACTION_SCHEMA`

Replace a destination inbox's extraction schema with a copy of a source inbox's schema.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `source_inbox_id` | string | Yes | Inbox whose extraction schema should be copied. |
| `destination_inbox_id` | string | Yes | Inbox whose current extraction schema should be replaced by the copy. |

#### 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 |

### Create Inbox

**Slug:** `AIRPARSER_CREATE_INBOX`

Create an Airparser inbox/parser for a document family using a text or vision extraction engine.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | Yes | Human-readable name for the new inbox. |
| `llm_engine` | string ("text" | "vision") | No | Parsing engine. Use vision for general documents; use text for small, dense, or tabular text. |

#### 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 |

### Delete Inbox

**Slug:** `AIRPARSER_DELETE_INBOX`

Permanently delete an Airparser inbox and every document it contains. This destructive, cascading operation cannot be undone and requires explicit confirmation.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `inbox_id` | string | Yes | Inbox ID to permanently delete. Deletion also permanently removes every document contained in the inbox and cannot be undone. |
| `confirm_permanent_deletion` | boolean | Yes | Must be true to confirm permanent deletion of the inbox and all contained documents. This cascading deletion cannot be undone. |

#### 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 Account Usage

**Slug:** `AIRPARSER_GET_ACCOUNT_USAGE`

Return the connected Airparser account's role, verification state, plan, and parsing-credit usage without exposing personal, secret, or internal account fields.

#### 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 Document

**Slug:** `AIRPARSER_GET_DOCUMENT`

Get parsed output and status for a document, optionally including extended source and navigation details.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `source` | string ("current" | "parsed") | No | For extended detail only, choose current post-processed output or force the original parsed output. |
| `document_id` | string | Yes | Document ID returned by parsing or listing documents. |
| `detail_level` | string ("compact" | "extended") | No | Use compact for normal parsed JSON; extended also returns source text, pages, format, inbox ID, and adjacent document IDs. |

#### 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 Inbox

**Slug:** `AIRPARSER_GET_INBOX`

Get one Airparser inbox, including its current extraction schema and useful parsing configuration.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `inbox_id` | string | Yes | Inbox ID returned by create or list inboxes. |

#### 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 Documents

**Slug:** `AIRPARSER_LIST_DOCUMENTS`

List and search documents in one inbox, one page at a time.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | Optional document search text, commonly matched against document names. |
| `to_date` | string | No | Optional upper date filter; provider inclusivity and timezone semantics are undocumented. |
| `inbox_id` | string | Yes | Inbox whose documents should be listed. |
| `per_page` | integer | No | Maximum documents in this page (1-500). |
| `from_date` | string | No | Optional inclusive lower date filter; provider timezone semantics are undocumented. |
| `next_cursor` | string | No | Continuation cursor returned by a previous call; omit for the first page. |

#### 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 Inboxes

**Slug:** `AIRPARSER_LIST_INBOXES`

List the Airparser inboxes available to the connected account.

#### 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 |

### Parse Document Synchronously

**Slug:** `AIRPARSER_PARSE_DOCUMENT_SYNC`

Upload one document to an inbox and wait for its extracted JSON. This non-idempotent operation consumes plan credits, including one credit per PDF page. Do not retry automatically after an ambiguous failure because a retry can consume credits and create another document.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | EML, PDF, HTML, TXT, MD, DOCX, XLSX, CSV, JPG, PNG, or BMP file up to 20 MB. ZIP is not supported in synchronous mode. |
| `inbox_id` | string | Yes | Inbox whose extraction schema should parse the document. |
| `metadata` | object | No | Optional JSON metadata copied into parsed output as __meta__. |

#### 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 |

### Upsert Extraction Schema

**Slug:** `AIRPARSER_UPSERT_EXTRACTION_SCHEMA`

Create or completely replace the extraction schema used by an Airparser inbox. The fields array is the complete replacement, not a partial update.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `fields` | array | Yes | Complete replacement schema. Include every scalar, list, object, and enum field that the inbox should extract. |
| `inbox_id` | string | Yes | Inbox whose complete extraction schema should be replaced. |

#### 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 |