Skip to content
Framework Docs

Parse File

client.Parsing.New(ctx, params) (*ParsingNewResponse, error)
POST/api/v2/parse

Parse a file by file ID or URL.

Provide either file_id (a previously uploaded file) or source_url (a publicly accessible URL). Configure parsing with options like tier, target_pages, and lang.

Tiers

  • fast — rule-based, cheapest, no AI
  • cost_effective — balanced speed and quality
  • agentic — full AI-powered parsing
  • agentic_plus — premium AI with specialized features

The job runs asynchronously. Poll GET /parse/{job_id} with expand=text or expand=markdown to retrieve results.

ParametersExpand Collapse
params ParsingNewParams
Tier param.Field[ParsingNewParamsTier]

Body param: Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy)

const ParsingNewParamsTierFast ParsingNewParamsTier = "fast"
const ParsingNewParamsTierCostEffective ParsingNewParamsTier = "cost_effective"
const ParsingNewParamsTierAgentic ParsingNewParamsTier = "agentic"
const ParsingNewParamsTierAgenticPlus ParsingNewParamsTier = "agentic_plus"
Version param.Field[ParsingNewParamsVersion]

Body param: Tier version. Use 'latest' for the current stable version, or specify a specific version (e.g., '1.0', '2.0') for reproducible results

type ParsingNewParamsVersion string

Tier version. Use 'latest' for the current stable version, or specify a specific version (e.g., '1.0', '2.0') for reproducible results

One of the following:
const ParsingNewParamsVersion2025_12_11 ParsingNewParamsVersion = "2025-12-11"
const ParsingNewParamsVersion2025_12_18 ParsingNewParamsVersion = "2025-12-18"
const ParsingNewParamsVersion2025_12_31 ParsingNewParamsVersion = "2025-12-31"
const ParsingNewParamsVersion2026_01_08 ParsingNewParamsVersion = "2026-01-08"
const ParsingNewParamsVersion2026_01_09 ParsingNewParamsVersion = "2026-01-09"
const ParsingNewParamsVersion2026_01_16 ParsingNewParamsVersion = "2026-01-16"
const ParsingNewParamsVersion2026_01_21 ParsingNewParamsVersion = "2026-01-21"
const ParsingNewParamsVersion2026_01_22 ParsingNewParamsVersion = "2026-01-22"
const ParsingNewParamsVersion2026_01_24 ParsingNewParamsVersion = "2026-01-24"
const ParsingNewParamsVersion2026_01_29 ParsingNewParamsVersion = "2026-01-29"
const ParsingNewParamsVersion2026_01_30 ParsingNewParamsVersion = "2026-01-30"
const ParsingNewParamsVersion2026_02_03 ParsingNewParamsVersion = "2026-02-03"
const ParsingNewParamsVersion2026_02_18 ParsingNewParamsVersion = "2026-02-18"
const ParsingNewParamsVersion2026_02_20 ParsingNewParamsVersion = "2026-02-20"
const ParsingNewParamsVersion2026_02_24 ParsingNewParamsVersion = "2026-02-24"
const ParsingNewParamsVersion2026_02_26 ParsingNewParamsVersion = "2026-02-26"
const ParsingNewParamsVersion2026_03_02 ParsingNewParamsVersion = "2026-03-02"
const ParsingNewParamsVersion2026_03_03 ParsingNewParamsVersion = "2026-03-03"
const ParsingNewParamsVersion2026_03_04 ParsingNewParamsVersion = "2026-03-04"
const ParsingNewParamsVersion2026_03_05 ParsingNewParamsVersion = "2026-03-05"
const ParsingNewParamsVersion2026_03_09 ParsingNewParamsVersion = "2026-03-09"
const ParsingNewParamsVersion2026_03_10 ParsingNewParamsVersion = "2026-03-10"
const ParsingNewParamsVersion2026_03_11 ParsingNewParamsVersion = "2026-03-11"
const ParsingNewParamsVersion2026_03_12 ParsingNewParamsVersion = "2026-03-12"
const ParsingNewParamsVersion2026_03_17 ParsingNewParamsVersion = "2026-03-17"
const ParsingNewParamsVersion2026_03_19 ParsingNewParamsVersion = "2026-03-19"
const ParsingNewParamsVersion2026_03_20 ParsingNewParamsVersion = "2026-03-20"
const ParsingNewParamsVersion2026_03_22 ParsingNewParamsVersion = "2026-03-22"
const ParsingNewParamsVersion2026_03_23 ParsingNewParamsVersion = "2026-03-23"
const ParsingNewParamsVersion2026_03_24 ParsingNewParamsVersion = "2026-03-24"
const ParsingNewParamsVersion2026_03_25 ParsingNewParamsVersion = "2026-03-25"
const ParsingNewParamsVersion2026_03_26 ParsingNewParamsVersion = "2026-03-26"
const ParsingNewParamsVersion2026_03_27 ParsingNewParamsVersion = "2026-03-27"
const ParsingNewParamsVersion2026_03_30 ParsingNewParamsVersion = "2026-03-30"
const ParsingNewParamsVersion2026_03_31 ParsingNewParamsVersion = "2026-03-31"
const ParsingNewParamsVersion2026_04_02 ParsingNewParamsVersion = "2026-04-02"
const ParsingNewParamsVersion2026_04_06 ParsingNewParamsVersion = "2026-04-06"
const ParsingNewParamsVersion2026_04_09 ParsingNewParamsVersion = "2026-04-09"
const ParsingNewParamsVersion2026_04_14 ParsingNewParamsVersion = "2026-04-14"
const ParsingNewParamsVersion2026_04_19 ParsingNewParamsVersion = "2026-04-19"
const ParsingNewParamsVersion2026_04_22 ParsingNewParamsVersion = "2026-04-22"
const ParsingNewParamsVersion2026_04_27 ParsingNewParamsVersion = "2026-04-27"
const ParsingNewParamsVersionLatest ParsingNewParamsVersion = "latest"
string
OrganizationID param.Field[string]optional

Query param

formatuuid
ProjectID param.Field[string]optional

Query param

formatuuid
AgenticOptions param.Field[ParsingNewParamsAgenticOptions]optional

Body param: Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus).

These options customize how the AI processes and interprets document content. Only applicable when using non-fast tiers.

CustomPrompt stringoptional

Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: 'Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.'

ClientName param.Field[string]optional

Body param: Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2'

CropBox param.Field[ParsingNewParamsCropBox]optional

Body param: Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges

Bottom float64optional

Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded

maximum1
minimum0
Left float64optional

Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded

maximum1
minimum0
Right float64optional

Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded

maximum1
minimum0
Top float64optional

Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded

maximum1
minimum0
DisableCache param.Field[bool]optional

Body param: Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results

FastOptions param.Field[any]optional

Body param: Options for fast tier parsing (rule-based, no AI).

Fast tier uses deterministic algorithms for text extraction without AI enhancement. It's the fastest and most cost-effective option, best suited for simple documents with standard layouts. Currently has no configurable options but reserved for future expansion.

FileID param.Field[string]optional

Body param: ID of an existing file in the project to parse. Mutually exclusive with source_url

HTTPProxy param.Field[string]optional

Body param: HTTP/HTTPS proxy for fetching source_url. Ignored if using file_id

InputOptions param.Field[ParsingNewParamsInputOptions]optional

Body param: Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type

HTML ParsingNewParamsInputOptionsHTMLoptional

HTML/web page parsing options (applies to .html, .htm files)

MakeAllElementsVisible booloptional

Force all HTML elements to be visible by overriding CSS display/visibility properties. Useful for parsing pages with hidden content or collapsed sections

RemoveFixedElements booloptional

Remove fixed-position elements (headers, footers, floating buttons) that appear on every page render

RemoveNavigationElements booloptional

Remove navigation elements (nav bars, sidebars, menus) to focus on main content

Pdf anyoptional

PDF-specific parsing options (applies to .pdf files)

Presentation ParsingNewParamsInputOptionsPresentationoptional

Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)

OutOfBoundsContent booloptional

Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries

SkipEmbeddedData booloptional

Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data

Spreadsheet ParsingNewParamsInputOptionsSpreadsheetoptional

Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)

DetectSubTablesInSheets booloptional

Detect and extract multiple tables within a single sheet. Useful when spreadsheets contain several data regions separated by blank rows/columns

ForceFormulaComputationInSheets booloptional

Compute formula results instead of extracting formula text. Use when you need calculated values rather than formula definitions

IncludeHiddenSheets booloptional

Parse hidden sheets in addition to visible ones. By default, hidden sheets are skipped

OutputOptions param.Field[ParsingNewParamsOutputOptions]optional

Body param: Output formatting options for markdown, text, and extracted images

ExtractPrintedPageNumber booloptional

Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers

ImagesToSave []stringoptional

Image categories to extract and save. Options: 'screenshot' (full page renders useful for visual QA), 'embedded' (images found within the document), 'layout' (cropped regions from layout detection like figures and diagrams). Empty list saves no images

One of the following:
const ParsingNewParamsOutputOptionsImagesToSaveScreenshot ParsingNewParamsOutputOptionsImagesToSave = "screenshot"
const ParsingNewParamsOutputOptionsImagesToSaveEmbedded ParsingNewParamsOutputOptionsImagesToSave = "embedded"
const ParsingNewParamsOutputOptionsImagesToSaveLayout ParsingNewParamsOutputOptionsImagesToSave = "layout"
Markdown ParsingNewParamsOutputOptionsMarkdownoptional

Markdown formatting options including table styles and link annotations

Add link annotations to markdown output in the format text. When false, only the link text is included

InlineImages booloptional

Embed images directly in markdown as base64 data URIs instead of extracting them as separate files. Useful for self-contained markdown output

Tables ParsingNewParamsOutputOptionsMarkdownTablesoptional

Table formatting options including markdown vs HTML format and merging behavior

CompactMarkdownTables booloptional

Remove extra whitespace padding in markdown table cells for more compact output

MarkdownTableMultilineSeparator stringoptional

Separator string for multiline cell content in markdown tables. Example: '<br>' to preserve line breaks, ' ' to join with spaces

MergeContinuedTables booloptional

Automatically merge tables that span multiple pages into a single table. The merged table appears on the first page with merged_from_pages metadata

OutputTablesAsMarkdown booloptional

Output tables as markdown pipe tables instead of HTML <table> tags. Markdown tables are simpler but cannot represent complex structures like merged cells

SpatialText ParsingNewParamsOutputOptionsSpatialTextoptional

Spatial text output options for preserving document layout structure

DoNotUnrollColumns booloptional

Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers

PreserveLayoutAlignmentAcrossPages booloptional

Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes

PreserveVerySmallText booloptional

Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out

TablesAsSpreadsheet ParsingNewParamsOutputOptionsTablesAsSpreadsheetoptional

Options for exporting tables as XLSX spreadsheets

Enable booloptional

Whether this option is enabled

GuessSheetName booloptional

Automatically generate descriptive sheet names from table context (headers, surrounding text) instead of using generic names like 'Table_1'

PageRanges param.Field[ParsingNewParamsPageRanges]optional

Body param: Page selection: limit total pages or specify exact pages to process

MaxPages int64optional

Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence

minimum1
TargetPages stringoptional

Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: '1,3,5' (pages 1, 3, 5), '1-5' (pages 1 through 5 inclusive), '1,3,5-8,10' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error

ProcessingControl param.Field[ParsingNewParamsProcessingControl]optional

Body param: Job execution controls including timeouts and failure thresholds

JobFailureConditions ParsingNewParamsProcessingControlJobFailureConditionsoptional

Quality thresholds that determine when a job should fail vs complete with partial results

AllowedPageFailureRatio float64optional

Maximum ratio of pages allowed to fail before the job fails (0-1). Example: 0.1 means job fails if more than 10% of pages fail. Default is 0.05 (5%)

maximum1
exclusiveMinimum0
FailOnBuggyFont booloptional

Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters

FailOnImageExtractionError booloptional

Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job

FailOnImageOcrError booloptional

Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image

FailOnMarkdownReconstructionError booloptional

Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction

Timeouts ParsingNewParamsProcessingControlTimeoutsoptional

Timeout settings for job execution. Increase for large or complex documents

BaseInSeconds int64optional

Base timeout for the job in seconds (max 1800 = 30 minutes). This is the minimum time allowed regardless of document size

maximum1800
exclusiveMinimum0
ExtraTimePerPageInSeconds int64optional

Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout = base + (this value × page count)

maximum300
exclusiveMinimum0
ProcessingOptions param.Field[ParsingNewParamsProcessingOptions]optional

Body param: Document processing options including OCR, table extraction, and chart parsing

AggressiveTableExtraction booloptional

Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables

AutoModeConfiguration []ParsingNewParamsProcessingOptionsAutoModeConfigurationoptional

Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered

ParsingConf ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConf

Parsing configuration to apply when trigger conditions are met

AdaptiveLongTable booloptional

Whether to use adaptive long table handling

AggressiveTableExtraction booloptional

Whether to use aggressive table extraction

CropBox ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfCropBoxoptional

Crop box options for auto mode parsing configuration.

Bottom float64optional

Bottom boundary of crop box as ratio (0-1)

maximum1
minimum0
Left float64optional

Left boundary of crop box as ratio (0-1)

maximum1
minimum0
Right float64optional

Right boundary of crop box as ratio (0-1)

maximum1
minimum0
Top float64optional

Top boundary of crop box as ratio (0-1)

maximum1
minimum0
CustomPrompt stringoptional

Custom AI instructions for matched pages. Overrides the base custom_prompt

ExtractLayout booloptional

Whether to extract layout information

HighResOcr booloptional

Whether to use high resolution OCR

Ignore ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfIgnoreoptional

Ignore options for auto mode parsing configuration.

IgnoreDiagonalText booloptional

Whether to ignore diagonal text in the document

IgnoreHiddenText booloptional

Whether to ignore hidden text in the document

Language stringoptional

Primary language of the document

OutlinedTableExtraction booloptional

Whether to use outlined table extraction

Presentation ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfPresentationoptional

Presentation-specific options for auto mode parsing configuration.

OutOfBoundsContent booloptional

Extract out of bounds content in presentation slides

SkipEmbeddedData booloptional

Skip extraction of embedded data for charts in presentation slides

SpatialText ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpatialTextoptional

Spatial text options for auto mode parsing configuration.

DoNotUnrollColumns booloptional

Keep column structure intact without unrolling

PreserveLayoutAlignmentAcrossPages booloptional

Preserve text alignment across page boundaries

PreserveVerySmallText booloptional

Include very small text in spatial output

SpecializedChartParsing stringoptional

Enable specialized chart parsing with the specified mode

One of the following:
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpecializedChartParsingAgenticPlus ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpecializedChartParsing = "agentic_plus"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpecializedChartParsingAgentic ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpecializedChartParsing = "agentic"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpecializedChartParsingEfficient ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfSpecializedChartParsing = "efficient"
Tier stringoptional

Override the parsing tier for matched pages. Must be paired with version

One of the following:
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTierFast ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTier = "fast"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTierCostEffective ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTier = "cost_effective"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTierAgentic ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTier = "agentic"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTierAgenticPlus ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfTier = "agentic_plus"
Version stringoptional

Tier version when overriding tier. Required when tier is specified

One of the following:
string
One of the following:
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2025_12_11 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2025-12-11"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2025_12_18 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2025-12-18"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2025_12_31 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2025-12-31"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_08 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-08"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_09 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-09"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_16 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-16"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_21 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-21"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_22 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-22"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_24 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-24"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_29 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-29"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_01_30 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-01-30"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_02_03 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-02-03"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_02_18 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-02-18"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_02_20 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-02-20"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_02_24 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-02-24"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_02_26 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-02-26"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_02 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-02"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_03 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-03"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_04 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-04"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_05 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-05"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_09 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-09"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_10 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-10"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_11 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-11"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_12 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-12"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_17 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-17"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_19 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-19"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_20 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-20"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_22 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-22"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_23 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-23"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_24 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-24"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_25 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-25"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_26 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-26"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_27 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-27"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_30 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-30"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_03_31 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-03-31"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_02 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-02"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_06 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-06"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_09 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-09"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_14 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-14"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_19 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-19"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_22 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-22"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion2026_04_27 ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "2026-04-27"
const ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersionLatest ParsingNewParamsProcessingOptionsAutoModeConfigurationParsingConfVersion = "latest"
string
FilenameMatchGlob stringoptional

Single glob pattern to match against filename

FilenameMatchGlobList []stringoptional

List of glob patterns to match against filename

FilenameRegexp stringoptional

Regex pattern to match against filename

FilenameRegexpMode stringoptional

Regex mode flags (e.g., 'i' for case-insensitive)

FullPageImageInPage booloptional

Trigger if page contains a full-page image (scanned page detection)

FullPageImageInPageThreshold ParsingNewParamsProcessingOptionsAutoModeConfigurationFullPageImageInPageThresholdUnionoptional

Threshold for full page image detection (0.0-1.0, default 0.8)

One of the following:
float64
string
ImageInPage booloptional

Trigger if page contains non-screenshot images

LayoutElementInPage stringoptional

Trigger if page contains this layout element type

LayoutElementInPageConfidenceThreshold ParsingNewParamsProcessingOptionsAutoModeConfigurationLayoutElementInPageConfidenceThresholdUnionoptional

Confidence threshold for layout element detection

One of the following:
float64
string
PageContainsAtLeastNCharts ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNChartsUnionoptional

Trigger if page has more than N charts

One of the following:
int64
string
PageContainsAtLeastNImages ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNImagesUnionoptional

Trigger if page has more than N images

One of the following:
int64
string
PageContainsAtLeastNLayoutElements ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNLayoutElementsUnionoptional

Trigger if page has more than N layout elements

One of the following:
int64
string
PageContainsAtLeastNLines ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNLinesUnionoptional

Trigger if page has more than N lines

One of the following:
int64
string

Trigger if page has more than N links

One of the following:
PageContainsAtLeastNNumbers ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNNumbersUnionoptional

Trigger if page has more than N numeric words

One of the following:
int64
string
PageContainsAtLeastNPercentNumbers ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNPercentNumbersUnionoptional

Trigger if page has more than N% numeric words

One of the following:
int64
string
PageContainsAtLeastNTables ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNTablesUnionoptional

Trigger if page has more than N tables

One of the following:
int64
string
PageContainsAtLeastNWords ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtLeastNWordsUnionoptional

Trigger if page has more than N words

One of the following:
int64
string
PageContainsAtMostNCharts ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNChartsUnionoptional

Trigger if page has fewer than N charts

One of the following:
int64
string
PageContainsAtMostNImages ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNImagesUnionoptional

Trigger if page has fewer than N images

One of the following:
int64
string
PageContainsAtMostNLayoutElements ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNLayoutElementsUnionoptional

Trigger if page has fewer than N layout elements

One of the following:
int64
string
PageContainsAtMostNLines ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNLinesUnionoptional

Trigger if page has fewer than N lines

One of the following:
int64
string

Trigger if page has fewer than N links

One of the following:
PageContainsAtMostNNumbers ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNNumbersUnionoptional

Trigger if page has fewer than N numeric words

One of the following:
int64
string
PageContainsAtMostNPercentNumbers ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNPercentNumbersUnionoptional

Trigger if page has fewer than N% numeric words

One of the following:
int64
string
PageContainsAtMostNTables ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNTablesUnionoptional

Trigger if page has fewer than N tables

One of the following:
int64
string
PageContainsAtMostNWords ParsingNewParamsProcessingOptionsAutoModeConfigurationPageContainsAtMostNWordsUnionoptional

Trigger if page has fewer than N words

One of the following:
int64
string
PageLongerThanNChars ParsingNewParamsProcessingOptionsAutoModeConfigurationPageLongerThanNCharsUnionoptional

Trigger if page has more than N characters

One of the following:
int64
string
PageMdError booloptional

Trigger on pages with markdown extraction errors

PageShorterThanNChars ParsingNewParamsProcessingOptionsAutoModeConfigurationPageShorterThanNCharsUnionoptional

Trigger if page has fewer than N characters

One of the following:
int64
string
RegexpInPage stringoptional

Regex pattern to match in page content

RegexpInPageMode stringoptional

Regex mode flags for regexp_in_page

TableInPage booloptional

Trigger if page contains a table

TextInPage stringoptional

Trigger if page text/markdown contains this string

TriggerMode stringoptional

How to combine multiple trigger conditions: 'and' (all conditions must match, this is the default) or 'or' (any single condition can trigger)

CostOptimizer ParsingNewParamsProcessingOptionsCostOptimizeroptional

Cost optimizer configuration for reducing parsing costs on simpler pages.

When enabled, the parser analyzes each page and routes simpler pages to faster, cheaper processing while preserving quality for complex pages. Only works with 'agentic' or 'agentic_plus' tiers.

Enable booloptional

Enable cost-optimized parsing. Routes simpler pages to faster processing while complex pages use full AI analysis. May reduce speed on some documents. IMPORTANT: Only available with 'agentic' or 'agentic_plus' tiers

DisableHeuristics booloptional

Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results

Ignore ParsingNewParamsProcessingOptionsIgnoreoptional

Options for ignoring specific text types (diagonal, hidden, text in images)

IgnoreDiagonalText booloptional

Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring watermarks or decorative angled text

IgnoreHiddenText booloptional

Skip text marked as hidden in the document structure. Some PDFs contain invisible text layers used for accessibility or search indexing

IgnoreTextInImage booloptional

Skip OCR text extraction from embedded images. Use when images contain irrelevant text (watermarks, logos) that shouldn't be in the output

OcrParameters ParsingNewParamsProcessingOptionsOcrParametersoptional

OCR configuration including language detection settings

Languages []ParsingLanguagesoptional

Languages to use for OCR text recognition. Specify multiple languages if document contains mixed-language content. Order matters - put primary language first. Example: ['en', 'es'] for English with Spanish

One of the following:
const ParsingLanguagesAf ParsingLanguages = "af"
const ParsingLanguagesAz ParsingLanguages = "az"
const ParsingLanguagesBs ParsingLanguages = "bs"
const ParsingLanguagesCs ParsingLanguages = "cs"
const ParsingLanguagesCy ParsingLanguages = "cy"
const ParsingLanguagesDa ParsingLanguages = "da"
const ParsingLanguagesDe ParsingLanguages = "de"
const ParsingLanguagesEn ParsingLanguages = "en"
const ParsingLanguagesEs ParsingLanguages = "es"
const ParsingLanguagesEt ParsingLanguages = "et"
const ParsingLanguagesFr ParsingLanguages = "fr"
const ParsingLanguagesGa ParsingLanguages = "ga"
const ParsingLanguagesHr ParsingLanguages = "hr"
const ParsingLanguagesHu ParsingLanguages = "hu"
const ParsingLanguagesID ParsingLanguages = "id"
const ParsingLanguagesIs ParsingLanguages = "is"
const ParsingLanguagesIt ParsingLanguages = "it"
const ParsingLanguagesKu ParsingLanguages = "ku"
const ParsingLanguagesLa ParsingLanguages = "la"
const ParsingLanguagesLt ParsingLanguages = "lt"
const ParsingLanguagesLv ParsingLanguages = "lv"
const ParsingLanguagesMi ParsingLanguages = "mi"
const ParsingLanguagesMs ParsingLanguages = "ms"
const ParsingLanguagesMt ParsingLanguages = "mt"
const ParsingLanguagesNl ParsingLanguages = "nl"
const ParsingLanguagesNo ParsingLanguages = "no"
const ParsingLanguagesOc ParsingLanguages = "oc"
const ParsingLanguagesPi ParsingLanguages = "pi"
const ParsingLanguagesPl ParsingLanguages = "pl"
const ParsingLanguagesPt ParsingLanguages = "pt"
const ParsingLanguagesRo ParsingLanguages = "ro"
const ParsingLanguagesRsLatin ParsingLanguages = "rs_latin"
const ParsingLanguagesSk ParsingLanguages = "sk"
const ParsingLanguagesSl ParsingLanguages = "sl"
const ParsingLanguagesSq ParsingLanguages = "sq"
const ParsingLanguagesSv ParsingLanguages = "sv"
const ParsingLanguagesSw ParsingLanguages = "sw"
const ParsingLanguagesTl ParsingLanguages = "tl"
const ParsingLanguagesTr ParsingLanguages = "tr"
const ParsingLanguagesUz ParsingLanguages = "uz"
const ParsingLanguagesVi ParsingLanguages = "vi"
const ParsingLanguagesAr ParsingLanguages = "ar"
const ParsingLanguagesFa ParsingLanguages = "fa"
const ParsingLanguagesUg ParsingLanguages = "ug"
const ParsingLanguagesUr ParsingLanguages = "ur"
const ParsingLanguagesBn ParsingLanguages = "bn"
const ParsingLanguagesAs ParsingLanguages = "as"
const ParsingLanguagesMni ParsingLanguages = "mni"
const ParsingLanguagesRu ParsingLanguages = "ru"
const ParsingLanguagesRsCyrillic ParsingLanguages = "rs_cyrillic"
const ParsingLanguagesBe ParsingLanguages = "be"
const ParsingLanguagesBg ParsingLanguages = "bg"
const ParsingLanguagesUk ParsingLanguages = "uk"
const ParsingLanguagesMn ParsingLanguages = "mn"
const ParsingLanguagesAbq ParsingLanguages = "abq"
const ParsingLanguagesAdy ParsingLanguages = "ady"
const ParsingLanguagesKbd ParsingLanguages = "kbd"
const ParsingLanguagesAva ParsingLanguages = "ava"
const ParsingLanguagesDar ParsingLanguages = "dar"
const ParsingLanguagesInh ParsingLanguages = "inh"
const ParsingLanguagesChe ParsingLanguages = "che"
const ParsingLanguagesLbe ParsingLanguages = "lbe"
const ParsingLanguagesLez ParsingLanguages = "lez"
const ParsingLanguagesTab ParsingLanguages = "tab"
const ParsingLanguagesTjk ParsingLanguages = "tjk"
const ParsingLanguagesHi ParsingLanguages = "hi"
const ParsingLanguagesMr ParsingLanguages = "mr"
const ParsingLanguagesNe ParsingLanguages = "ne"
const ParsingLanguagesBh ParsingLanguages = "bh"
const ParsingLanguagesMai ParsingLanguages = "mai"
const ParsingLanguagesAng ParsingLanguages = "ang"
const ParsingLanguagesBho ParsingLanguages = "bho"
const ParsingLanguagesMah ParsingLanguages = "mah"
const ParsingLanguagesSck ParsingLanguages = "sck"
const ParsingLanguagesNew ParsingLanguages = "new"
const ParsingLanguagesGom ParsingLanguages = "gom"
const ParsingLanguagesSa ParsingLanguages = "sa"
const ParsingLanguagesBgc ParsingLanguages = "bgc"
const ParsingLanguagesTh ParsingLanguages = "th"
const ParsingLanguagesChSim ParsingLanguages = "ch_sim"
const ParsingLanguagesChTra ParsingLanguages = "ch_tra"
const ParsingLanguagesJa ParsingLanguages = "ja"
const ParsingLanguagesKo ParsingLanguages = "ko"
const ParsingLanguagesTa ParsingLanguages = "ta"
const ParsingLanguagesTe ParsingLanguages = "te"
const ParsingLanguagesKn ParsingLanguages = "kn"
SpecializedChartParsing stringoptional

Enable AI-powered chart analysis. Modes: 'efficient' (fast, lower cost), 'agentic' (balanced), 'agentic_plus' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set

One of the following:
const ParsingNewParamsProcessingOptionsSpecializedChartParsingAgenticPlus ParsingNewParamsProcessingOptionsSpecializedChartParsing = "agentic_plus"
const ParsingNewParamsProcessingOptionsSpecializedChartParsingAgentic ParsingNewParamsProcessingOptionsSpecializedChartParsing = "agentic"
const ParsingNewParamsProcessingOptionsSpecializedChartParsingEfficient ParsingNewParamsProcessingOptionsSpecializedChartParsing = "efficient"
SourceURL param.Field[string]optional

Body param: Public URL of the document to parse. Mutually exclusive with file_id

WebhookConfigurations param.Field[[]ParsingNewParamsWebhookConfiguration]optional

Body param: Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services

WebhookEvents []stringoptional

Events that trigger this webhook. Options: 'parse.success' (job completed), 'parse.failure' (job failed), 'parse.partial' (some pages failed). If not specified, webhook fires for all events

WebhookHeaders map[string, any]optional

Custom HTTP headers to include in webhook requests. Use for authentication tokens or custom routing. Example: {'Authorization': 'Bearer xyz'}

WebhookURL stringoptional

HTTPS URL to receive webhook POST requests. Must be publicly accessible

ReturnsExpand Collapse
type ParsingNewResponse struct{…}

A parse job.

ID string

Unique parse job identifier

ProjectID string

Project this job belongs to

Status ParsingNewResponseStatus

Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED

One of the following:
const ParsingNewResponseStatusPending ParsingNewResponseStatus = "PENDING"
const ParsingNewResponseStatusRunning ParsingNewResponseStatus = "RUNNING"
const ParsingNewResponseStatusCompleted ParsingNewResponseStatus = "COMPLETED"
const ParsingNewResponseStatusFailed ParsingNewResponseStatus = "FAILED"
const ParsingNewResponseStatusCancelled ParsingNewResponseStatus = "CANCELLED"
CreatedAt Timeoptional

Creation datetime

formatdate-time
ErrorMessage stringoptional

Error details when status is FAILED

Name stringoptional

Optional display name for this parse job

Tier stringoptional

Parsing tier used for this job

UpdatedAt Timeoptional

Update datetime

formatdate-time

Parse File

package main

import (
  "context"
  "fmt"

  "github.com/stainless-sdks/llamacloud-prod-go"
  "github.com/stainless-sdks/llamacloud-prod-go/option"
)

func main() {
  client := llamacloudprod.NewClient(
    option.WithAPIKey("My API Key"),
  )
  parsing, err := client.Parsing.New(context.TODO(), llamacloudprod.ParsingNewParams{
    Tier: llamacloudprod.ParsingNewParamsTierFast,
    Version: llamacloudprod.ParsingNewParamsVersion2025_12_11,
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", parsing.ID)
}
{
  "id": "pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "status": "PENDING",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "name": "Q4 Financial Report",
  "tier": "fast",
  "updated_at": "2019-12-27T18:11:19.117Z"
}
Returns Examples
{
  "id": "pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "status": "PENDING",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "name": "Q4 Financial Report",
  "tier": "fast",
  "updated_at": "2019-12-27T18:11:19.117Z"
}