> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infery.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Document tools

> Document tools available as workflow steps and through /v1/capabilities.

**3 tools.** Each one is deterministic: the same input gives the same output, and
nothing is inferred. Call one directly with
[`POST /v1/capabilities/{id}/run`](/api-reference/capabilities/run), or use it as a step in a
[workflow](/workflows/step-types).

Prices are on the [live catalogue](https://infery.ai/models) — they change, and a stale price here would be
worse than none.

| Tool                                                 | Does                                                             | In → out            |
| ---------------------------------------------------- | ---------------------------------------------------------------- | ------------------- |
| [`document.convert_format`](#documentconvert_format) | Convert between markdown, html, docx, pdf, epub, latex.          | document → document |
| [`document.extract_text`](#documentextract_text)     | Parse PDF/DOCX/HTML/etc. to markdown or JSON, with optional OCR. | document → text     |
| [`document.render_slides`](#documentrender_slides)   | Convert markdown to a slide deck (pdf, pptx, html).              | document → document |

## `document.convert_format`

**document → document** · Billed per request

Convert documents between formats: markdown ↔ HTML ↔ DOCX ↔ PDF ↔ EPUB ↔ LaTeX.

### When to use

* **Generate PDFs** from markdown for reports, invoices, or documentation.
* **Export DOCX** for users who need to edit in Word.
* **Convert to HTML** for embedding content in web pages.
* **Produce EPUB** for e-reader distribution.

### Inputs & outputs

|                        |                                 |
| ---------------------- | ------------------------------- |
| **Input modality**     | Markdown (inline string or URL) |
| **Output modality**    | Document file (GCS URL)         |
| **Max inline size**    | 1 MB                            |
| **Max URL input size** | 50 MB                           |

### Parameters

| Param | Required | Description                                            |
| ----- | -------- | ------------------------------------------------------ |
| `to`  | yes      | Target format — `pdf`, `html`, `docx`, `epub`, `latex` |
| `toc` | no       | Include a table of contents. Default: `false`          |

### Examples

#### Markdown → PDF with table of contents

```json theme={null}
{
  "type": "document.convert_format",
  "input": { "markdown_inline": "# Report\n\n## Section 1\n\nContent here." },
  "params": { "to": "pdf", "toc": true }
}
```

#### Markdown URL → DOCX

```json theme={null}
{
  "type": "document.convert_format",
  "input": { "markdown_url": "https://example.com/content/article.md" },
  "params": { "to": "docx" }
}
```

### Pricing

Billed per conversion. PDF conversions are slightly higher due to rendering cost. See pricing dashboard for current rates.

### Related capabilities

* `document.extract_text` — extract markdown from PDF/DOCX before converting
* `document.render_slides` — render markdown as a slide deck instead of a document

### Examples

**Markdown → PDF with TOC**

```json theme={null}
{
  "type": "document.convert_format",
  "params": {
    "to": "pdf",
    "toc": true
  }
}
```

## `document.extract_text`

**document → text** · Billed per request

Parse PDF, DOCX, HTML, and other document formats into structured markdown or JSON, with optional OCR for scanned pages.

### When to use

* **Extract content** from PDFs (reports, contracts, invoices) for downstream text processing.
* **OCR scanned documents** — force OCR on image-only PDFs where no selectable text layer exists.
* **Normalize to markdown** for ingestion into RAG pipelines or LLM context windows.

### Inputs & outputs

|                       |                                                                          |
| --------------------- | ------------------------------------------------------------------------ |
| **Input modality**    | Document file — a public `http(s)` URL, or a file stored on the platform |
| **Output modality**   | Text (markdown or JSON)                                                  |
| **Supported formats** | PDF, DOCX, XLSX, PPTX, HTML, PNG, JPEG, TIFF                             |
| **Max input size**    | 100 MB                                                                   |

The document is named ONE of two ways — set exactly one:

| Input          | What it is                                                                                                  |
| -------------- | ----------------------------------------------------------------------------------------------------------- |
| `document_url` | A public `http(s)` URL, or a `${steps.<id>.outputRef}` binding (which resolves to a `gs://` object we hold) |
| `file_id`      | The id of a stored file — what `POST /v1/files` returned, or `${steps.<id>.output.file_id}`                 |

> **Both spellings of a file we hold are workspace-scoped.** A `gs://` object or
> a file id belonging to another workspace is a `404`, never a read. What
> actually reaches the extraction worker is a short-lived signed `https` URL for
> that one object, minted per call and never persisted.

**The document type.** For a stored file it comes from the file's own recorded
type (sniffed from its bytes at upload), so nothing has to be declared. For an
external URL it is read from the extension, and a URL that ends in none — no
`.pdf`, `.docx`, `.pptx`, `.xlsx`, `.html`, `.png`, `.jpg`, `.tif` — is refused
with `400 unsupported_mime`. Upload it and pass `file_id` instead.

### Parameters

| Param           | Required | Description                                                                                              |
| --------------- | -------- | -------------------------------------------------------------------------------------------------------- |
| `ocr`           | no       | OCR mode — `auto` (try text layer first), `force` (always OCR), `off` (text layer only). Default: `auto` |
| `output_format` | no       | Output format — `markdown` or `json`. Default: `markdown`                                                |

### Examples

#### PDF with auto-OCR → markdown

```json theme={null}
{
  "type": "document.extract_text",
  "input": { "document_url": "https://example.com/docs/report.pdf" },
  "params": { "ocr": "auto", "output_format": "markdown" }
}
```

#### Force OCR on scanned invoice → JSON

```json theme={null}
{
  "type": "document.extract_text",
  "input": { "document_url": "https://example.com/docs/scanned_invoice.pdf" },
  "params": { "ocr": "force", "output_format": "json" }
}
```

#### A file you uploaded

`POST /v1/files` returns a `file_id`; pass it directly. No extension is needed —
the stored type is used.

```json theme={null}
{
  "type": "document.extract_text",
  "input": { "file_id": "file_abc123" },
  "params": { "ocr": "auto", "output_format": "markdown" }
}
```

#### A document a previous step produced

```json theme={null}
{
  "type": "document.extract_text",
  "input": { "document_url": "${steps.render.outputRef}" },
  "params": { "ocr": "auto", "output_format": "markdown" }
}
```

### Pricing

Billed per page processed. OCR pages are billed at a higher rate than text-layer extraction. See pricing dashboard for current rates.

### Related capabilities

* `document.convert_format` — convert the extracted markdown to HTML, DOCX, or PDF
* `document.render_slides` — render markdown as a slide deck

### Examples

**PDF with auto-OCR → markdown**

```json theme={null}
{
  "type": "document.extract_text",
  "params": {
    "ocr": "auto",
    "output_format": "markdown"
  }
}
```

## `document.render_slides`

**document → document** · Billed per request

Convert a Marp-flavoured markdown file into a slide deck: PDF, PPTX, or interactive HTML.

### When to use

* **Generate presentation PDFs** from markdown for sharing or printing.
* **Export PPTX** for further editing in PowerPoint or Keynote.
* **Build HTML decks** for self-hosted or embedded presentations.

### Inputs & outputs

|                     |                                                       |
| ------------------- | ----------------------------------------------------- |
| **Input modality**  | Markdown with Marp frontmatter (inline string or URL) |
| **Output modality** | Slide deck file (GCS URL)                             |
| **Max slides**      | 200 per deck                                          |
| **Max inline size** | 500 KB                                                |

### Parameters

| Param           | Required | Description                                                            |
| --------------- | -------- | ---------------------------------------------------------------------- |
| `output_format` | yes      | Output format — `pdf`, `html`, `pptx`                                  |
| `theme`         | no       | Marp built-in theme — `default`, `gaia`, `uncover`. Default: `default` |
| `slide_size`    | no       | Aspect ratio — `16:9` or `4:3`. Default: `16:9`                        |

### Examples

#### 16:9 PDF deck with default theme

```json theme={null}
{
  "type": "document.render_slides",
  "input": { "markdown_inline": "---\nmarp: true\n---\n# Slide 1\n\n---\n\n# Slide 2" },
  "params": { "output_format": "pdf", "theme": "default", "slide_size": "16:9" }
}
```

#### PPTX with Gaia theme from URL

```json theme={null}
{
  "type": "document.render_slides",
  "input": { "markdown_url": "https://example.com/decks/pitch.md" },
  "params": { "output_format": "pptx", "theme": "gaia", "slide_size": "4:3" }
}
```

### Pricing

Billed per slide rendered. See pricing dashboard for current rates.

### Related capabilities

* `document.convert_format` — convert plain markdown to PDF/DOCX (non-slide layout)
* `document.extract_text` — extract content from existing PDF presentations

### Examples

**PDF deck 16:9**

```json theme={null}
{
  "type": "document.render_slides",
  "params": {
    "output_format": "pdf",
    "theme": "default",
    "slide_size": "16:9"
  }
}
```