https://platform.reducto.ai/split_asyncBody
asyncconfig__v3__AsyncConfigThe configuration options for asynchronous processing (default synchronous).
3 properties
metadataunknownJSON metadata included in webhook request body. Defaults to None.
prioritybooleanWorkers poll the priority queue ahead of the standard queue, so priority jobs start sooner when there is queued work; sync jobs are prioritized above async jobs by default.
- Default
false
webhookSvixWebhookConfig | DirectWebhookConfigThe webhook configuration for the asynchronous processing.
2 variants
modestring- Default
"svix"
channelsstring[]A list of Svix channels the message will be delivered down, omit to send to all channels.
modestring- Default
"direct"
urlstringRequired
inputstring | string[] | UploadResponseRequiredFor parse/split/extract pipelines, the URL of the document to be processed. You can provide one of the following: 1. A publicly available URL 2. A presigned S3 URL 3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document 4. A jobid:// prefixed URL obtained from a previous /parse invocation 5. A list of URLs (for multi-document pipelines, V3 API only)
For edit pipelines, this should be a string containing the edit instructionsUploadResponse properties
file_idstringRequiredpresigned_urlstring
parsingParseOptionsThe configuration options for parsing the document. If you are passing in a jobid:// URL for the file, then this configuration will be ignored.
5 properties
enhanceEnhance4 properties
agentic(TableAgentic | FigureAgentic | TextAgentic)[]For legacy Parse, agentic processing uses vision language models to improve text, table, or figure extraction. With r-1, use agentic processing for custom prompts or advanced chart extraction. Agentic processing adds latency.
3 variants
scopestringRequiredpromptstringCustom prompt for table agentic.
modestringMode for table agentic: 'default' selectively applies enrichment only to tables likely to benefit, and 'max' runs enrichment on all tables.
- Default
"default"- Allowed
defaultautomax
scopestringRequiredpromptstringCustom prompt for figure agentic.
advanced_chart_agentbooleanIf True, run advanced chart extraction on figures classified as charts: an agentic extractor that returns full structured series data (chart_data) plus a reconstruction image re-drawn from that data (extra.chart_reconstruction). Higher latency. Defaults to False.
- Default
false
scopestringRequiredpromptstringCustom instructions for agentic text. Note: This only applies to form regions (key-value).
advanced_chart_agentbooleanIf True, run advanced chart extraction on figures classified as charts, without requiring a figure-scoped agentic entry. Returns full structured series data (chart_data) plus a reconstruction image re-drawn from that data. Higher latency. Defaults to False.
- Default
false
summarize_figuresbooleanFor legacy Parse, if True, summarize figures using a separate vision language model. r-1 generates figure descriptions natively and ignores this setting. Defaults to True.
- Default
true
intelligent_orderingbooleanFor legacy Parse, if True, use an advanced vision language model to improve reading order accuracy, with a small increase in latency. r-1 handles reading order natively and ignores this setting. Defaults to False.
- Default
false
retrievalRetrieval3 properties
chunkingChunking3 properties
chunk_modestringChoose how to partition chunks. Variable mode chunks by character length and visual context. Section mode chunks by section headers. Page mode chunks according to pages. Page sections mode chunks first by page, then by sections within each page. Disabled returns one single chunk.
- Default
"disabled"- Allowed
variablesectionpagedisabledblockpage_sections
chunk_sizenumberThe approximate size of chunks (in characters) that the document will be split into. Defaults to null, in which case the chunk size is variable between 250 - 1500 characters.
chunk_overlapnumberNumber of characters of overlap to include from adjacent chunks. Defaults to 0.
- Default
0
filter_blocksstring[]A list of block types to filter out from 'content' and 'embed' fields. By default, no blocks are filtered.
embedding_optimizedbooleanIf True, use embedding optimized mode. Defaults to False.
- Default
false
formattingFormatting4 properties
add_page_markersbooleanIf True, add page markers to the output. Defaults to False. Useful for extracting data with page specific information.
- Default
false
table_output_formatstringThe table output format. Defaults to dynamic, which returns md for simpler tables and html for more complex tables. r-1 does not support jsonbbox.
- Default
"dynamic"- Allowed
htmljsonmdjsonbboxdynamiccsv
merge_tablesbooleanA flag to indicate if consecutive tables with the same number of columns should be merged. Defaults to False.
- Default
false
includestring[]For legacy Parse, the formatting details to include in the output. r-1 always includes highlights, signatures, hyperlinks, and watermark removal, and ignores those values.
spreadsheetSpreadsheet5 properties
split_large_tablesSplitLargeTables2 properties
enabledbooleanIf True, split large tables into smaller tables. Defaults to True.
- Default
true
sizenumber | SplitLargeTableSizesThe size of the tables to split into. Defaults to 50. Use 'row' and 'column' to independently specify the number of rows and columns to include when splitting. If you only want to split by rows or columns, set the other value to None.
- Default
50
SplitLargeTableSizes properties
rownumberThe number of rows to include in each chunk when splitting large tables. Does not chunk rows if set to None.
columnnumberThe number of columns to include in each chunk when splitting large tables. Does not chunk columns if set to None.
includestring[]Whether to include cell color, formula, and dropdown information in the output.
clusteringstringIn a spreadsheet with different tables inside, we enable splitting up the tables by default. Accurate mode applies more powerful models for superior accuracy, at 5× the default per-cell rate. Disabling will register as one large table.
- Default
"accurate"- Allowed
accuratefastdisabled
excludestring[]Whether to exclude hidden sheets, rows, or columns in the output.
max_cell_countnumberMaximum total non-empty cells allowed across all sheets. If exceeded, the request is rejected with a 422 error. Set to null to disable the limit. Defaults to null.
settingsSettings17 properties
modelstringThe parse model to use. 'r-1' is the full-featured flagship model, with the highest accuracy and lower latency. 'r-1-mini' gives high accuracy at low cost. Both models include agentic capabilities for complex documents. 'r-1-mini' does not accept spreadsheets. 'legacy' is the previous parsing pipeline. Starting December 7, 2026, Parse defaults to 'r-1'. To keep legacy Parse, set this field to 'legacy'.
ocr_systemstringThe OCR system for legacy Parse. Standard is the best multilingual OCR system. Legacy supports Germanic languages and remains available for backwards compatibility. r-1 uses native full-page processing and ignores this setting. Defaults to standard.
- Default
"standard"- Allowed
standardlegacy
extraction_modestringThe text extraction method for legacy Parse. OCR uses optical character recognition only. Hybrid combines OCR with embedded PDF text. r-1 uses native full-page processing and ignores this setting. Defaults to hybrid.
- Default
"hybrid"- Allowed
ocrhybrid
force_url_resultbooleanForce the result to be returned in URL form.
- Default
false
force_file_extensionstringForce the URL to be downloaded as a specific file extension (e.g.
.png).return_ocr_databooleanIf True, return OCR data in the result. Defaults to False.
- Default
false
return_imagesstring[]Whether to return images for the specified block types. 'page' returns full page images. By default, no images are returned.
embed_pdf_metadatabooleanIf True, embed OCR metadata into the returned PDF. Defaults to False.
- Default
false
extract_document_propertiesbooleanIf True, return properties embedded in the original document. Defaults to False.
- Default
false
embed_pdf_metadata_dpinumberRender DPI used when rasterizing the source PDF before embedding the OCR text layer (only applies when
embed_pdf_metadatais True). Lower values produce dramatically smaller output PDFs; higher values preserve more detail when zoomed past 200%. Defaults to 200 (good for on-screen viewing); raise toward the source scan DPI for crisper output. Min 50, max 250.- Default
200
persist_resultsbooleanIf True, persist the results indefinitely. Defaults to False.
- Default
false
tenant_throttlingTenantThrottlingPer-tenant throttling for multi-tenant applications. Tag each request with your tenant's id to bound how much of your account's concurrency a single tenant can consume. Account-level throttles still apply.
TenantThrottling properties
tenant_idstringRequiredYour identifier for the tenant (customer, workspace, organization) this request belongs to. Used only for noisy-neighbor throttling inside your account.
max_sharenumberMaximum fraction of your account's concurrency ceiling this tenant may use, between 0 (exclusive) and 1. Defaults to 0.5.
- Default
0.5
timeoutnumberThe timeout for the job in seconds.
page_rangePageRange | PageRange[] | number[] | string[]The page range to process (1-indexed). By default, the entire document is processed. For spreadsheets, you can also provide a list of sheet names.
2 variants
startnumberThe page number to start processing from (1-indexed).
endnumberThe page number to stop processing at (1-indexed).
startnumberThe page number to start processing from (1-indexed).
endnumberThe page number to stop processing at (1-indexed).
document_passwordstringPassword to decrypt password-protected documents.
hybrid_vpcHybridVpcSettingsHybrid VPC request-scoped settings.
1 property
environmentstringNamed Hybrid VPC environment to use for this request. Only applies when your organization has Hybrid VPC environments configured.
return_citationsbooleanIf True, locate every word of each text block on the page and return the per-word boxes in the block's
extra['word_citations']. Each entry carries the word'stext, itschar_start/char_endspan in that block'scontent(half-open, tags included), and abboxcovering that word on the page, in the same shape as the block's ownbbox(includingpage).bboxis null when the word cannot be located on the page. Table blocks also getextra['cell_citations']: one entry per non-empty cell with itstext,row_idxandcol_idx(0-based lists of every row and column the cell spans, so a cell merged across rows 1 and 2 hasrow_idx[1, 2]), and abboxframing the cell's words, null when none of them can be located. Requires r-1 or r-1 mini. Not supported with formatting.merge_tables. Defaults to False.- Default
false
split_descriptionSplitCategory[]RequiredThe configuration options for processing the document.
3 properties
namestringRequireddescriptionstringRequiredpartition_keystring
split_rulesstringThe prompt that describes rules for splitting the document.
- Default
"Split the document into the applicable sections. Sections may only overlap at their first and last page if at all."
settingsSplitSettingsThe settings for split processing.
5 properties
table_cutoffstringIf tables should be truncated to the first few rows or if all content should be preserved. truncate improves latency, preserve is recommended for cases where partition_key is being used and the partition_key may be included within the table. Defaults to truncate
- Default
"truncate"- Allowed
truncatepreserve
allow_page_overlapbooleanIf True, a page can belong to multiple categories/partitions. If False, each page must belong to exactly one category. Defaults to True.
- Default
true
auto_partitionbooleanIf True (default), deep split may split a category into partitions even when that category has no configured partition_key. If False, categories without a partition_key are never partitioned, so partitioning happens only where you explicitly configured a partition_key.
- Default
true
deep_splitbooleanIf True, uses the deep split agent for higher-quality document splitting. Off by default.
- Default
false
force_url_resultbooleanForce the endpoint result to be returned in URL form.
- Default
false
Response
job_idstringRequired
detailValidationError[]5 properties
loc(string | number)[]RequiredmsgstringRequiredtypestringRequiredinputunknownctxobject