r-1 is Reducto’s parsing model. It reads each full page in one pass and returns text, tables, figures, layout, reading order, and formatting, with a bounding box for every block. You do not need to turn on OCR modes, formatting options, figure summaries, or agentic passes. r-1 does that work by default.
Use r-1
from reducto import Reducto
client = Reducto()
result = client.parse.run(
input="https://cdn.reducto.ai/samples/fidelity-example.pdf",
settings={"model": "r-1"},
)
for chunk in result.result.chunks:
print(chunk.content)import Reducto from 'reductoai';
const client = new Reducto();
const result = await client.parse.run({
input: 'https://cdn.reducto.ai/samples/fidelity-example.pdf',
settings: { model: 'r-1' },
});
for (const chunk of result.result.chunks) {
console.log(chunk.content);
}out, err := client.Parse(ctx, &reducto.SyncParseConfig{
Input: reducto.DocumentInputFromString("https://cdn.reducto.ai/samples/fidelity-example.pdf"),
Settings: &reducto.Settings{Model: reducto.SettingsModelR1},
})curl -X POST https://platform.reducto.ai/parse \
-H "Authorization: Bearer $REDUCTO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": "https://cdn.reducto.ai/samples/fidelity-example.pdf",
"settings": {"model": "r-1"}
}'Extract and Split parse the document first. Set the model in their parsing object:
result = client.extract.run(
input=upload.file_id,
instructions={"schema": schema},
parsing={"settings": {"model": "r-1"}},
)r-1 mini
r-1 mini gives premium parsing without the premium cost. At $1 per 1,000 pages, it breaks a new price barrier for high-accuracy document parsing.
result = client.parse.run(
input=upload.file_id,
settings={"model": "r-1-mini"}
)const result = await client.parse.run({
input: upload.file_id,
settings: { model: 'r-1-mini' }
});curl -X POST https://platform.reducto.ai/parse \
-H "Authorization: Bearer $REDUCTO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": "reducto://your-file-id",
"settings": {"model": "r-1-mini"}
}'Use r-1 when accuracy or latency matters most, for example in synchronous use. Use r-1 mini for large, cost-sensitive workloads.
What r-1 does for you
| Content | r-1 behavior |
|---|---|
| Text | Reads digital text, scans, handwriting, and mixed languages. |
| Tables | Reads merged cells and nested headers with the page context. |
| Layout and reading order | Resolves columns, headers, footers, and sidebars. |
| Figures | Detects figures and writes a short description of each. |
| Formatting | Keeps headings, lists, bold, underline, strikethrough, highlights, signatures, and watermarks as meaningful content. |
| Bounding boxes | Returns a page-relative box for each block. |
What you can still configure
These options change the shape of the output after parsing. They work the same with r-1:
- Chunking for RAG and embeddings.
- Table output format:
dynamic,html,md,json, orcsv. - Page ranges, returned images, and the other processing settings.
- Spreadsheet options.
- Change tracking, comments, and hyperlinks for DOCX files.
Settings from legacy Parse, such as ocr_system, extraction_mode, summarize_figures, and promptless agentic scopes, have no effect on r-1. See Legacy Parse settings.
Add-ons
r-1 by itself is the right choice for most workloads. Add-ons are optional. See Credit usage for prices.
| Add-on | What it gives you | Setting |
|---|---|---|
| Parse citations | Word-level bounding boxes for every word in the output, and cell boxes for tables. | settings.return_citations: true |
| Advanced chart extraction | Structured series data for each chart. | enhance.advanced_chart_agent: true |
| LLM enrichment | An extra model pass with your own prompt. Not recommended for most workloads. | enhance.agentic with a prompt |