# Create scan URL: https://docs.hanzo.ai/docs/openapi/books/post-books-scan > Takes a receipt or invoice as RAW BYTES — a PDF, an image or plain text, uploaded under its own content type, not wrapped in JSON — extracts what the document says, resolves the vendor's expense category, and answers a DRAFT carrying a balanced voucher proposed for it. `POST /v1/books/scan` > [Books →](https://docs.hanzo.ai/docs/openapi/books) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | -------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/books/scan` | | **Method** | `POST` | | **Operation** | `post_books_scan` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Takes a receipt or invoice as RAW BYTES — a PDF, an image or plain text, uploaded under its own content type, not wrapped in JSON — extracts what the document says, resolves the vendor's expense category, and answers a DRAFT carrying a balanced voucher proposed for it. NOTHING IS POSTED. That split is the whole design: the model only ever produces a structured reading of the document, the voucher is assembled deterministically in Go from that reading, and the ledger is written only by the separate book call a human confirms. So a misread scan can propose a wrong draft; it cannot move money. Amounts are exact integer cents end to end — the extraction returns cents, never a decimal — so no rounding enters the ledger. The draft's id is the FILE HASH, and that is what makes booking idempotent: re-scanning the same bytes addresses the same draft rather than queuing a second one. A row is written to the org's document inbox as a side effect, moving it from unsorted to draft. Scoped to the caller's own org from the validated principal and refused without one; `sandbox=true` targets the sandbox ledger, and `filename` is recorded for the inbox. An empty or oversized upload is a 400, and a deployment with no scanner model answers 501. ## Request 1 field, body `application/octet-stream`. | Field | In | Type | Required | Description | | -------- | ---- | --------------- | -------- | ----------- | | `(body)` | body | string (binary) | yes | | ## Response | Status | Body | Meaning | | ------ | --------- | ------- | | `2XX` | ScanDraft | Success | `2XX` body — 32 fields. | Field | In | Type | Always | Description | | ----------------------------------- | ---- | ----------- | ------ | ----------- | | `balanced` | body | boolean | — | | | `category` | body | string | — | | | `confidence` | body | string | — | | | `extracted` | body | Extracted | — | | | `extracted.category` | body | string | — | | | `extracted.currency` | body | string | — | | | `extracted.issuedAt` | body | string | — | | | `extracted.lineItems` | body | LineItem\[] | — | | | `extracted.lineItems[].amountCents` | body | integer | — | | | `extracted.lineItems[].description` | body | string | — | | | `extracted.merchant` | body | string | — | | | `extracted.note` | body | string | — | | | `extracted.taxCents` | body | integer | — | | | `extracted.totalCents` | body | integer | — | | | `questions` | body | Question\[] | — | | | `questions[].account` | body | string | — | | | `questions[].amount` | body | string | — | | | `questions[].id` | body | string | — | | | `questions[].kind` | body | string | — | | | `questions[].postedAt` | body | string | — | | | `questions[].text` | body | string | — | | | `scanId` | body | string | — | | | `vendor` | body | string | — | | | `voucher` | body | Voucher | — | | | `voucher.description` | body | string | — | | | `voucher.legs` | body | Leg\[] | — | | | `voucher.legs[].account` | body | string | — | | | `voucher.legs[].credit` | body | integer | — | | | `voucher.legs[].debit` | body | integer | — | | | `voucher.postingAt` | body | string | — | | | `voucher.sourceId` | body | string | — | | | `voucher.sourceKind` | body | string | — | | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo books scan create ``` **SDK** **.ts** ```ts import { Configuration, BooksApi } from 'hanzoai'; const api = new BooksApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.postBooksScan(); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import BooksApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = BooksApi(client).post_books_scan() ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.BooksAPI.PostBooksScan(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, books_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = books_api::post_books_scan(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.BooksApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new BooksApi(client).postBooksScan(); ``` **HTTP** ```bash curl -X POST https://api.hanzo.ai/v1/books/scan \ -H "Authorization: Bearer $HANZO_API_KEY" ``` **MCP** MCP reaches **books** through the `books` tool, which names its 20 operations with its own verbs — this one among them, under a name only MCP declares. `describe` explains any of them: ```bash curl -X POST https://api.hanzo.ai/v1/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "describe", "arguments": { "op": "list_book_accounts" } } }' ``` --- [Books API](https://docs.hanzo.ai/docs/openapi/books) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)