LlamaParse Extract API is one of 36 APIs that LlamaParse publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Extract. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, an API reference, and a getting-started guide.
This API exposes
7 operations
across 5 paths,
and defines 54 schemas.
It is described by OpenAPI 3.2.0, at version 0.1.0.
Requests are made against a single base URL, https://api.cloud.llamaindex.ai.
The identity and technical contract details declared by the specification.
LlamaParseWebhookConfiguration
object
Webhook configuration for receiving parsing job notifications. Webhooks are called when specified events occur during job processing. Configure multiple webhoo…
4 properties
SplitCategory
object
Category definition for document splitting.
2 properties
1 required
ExtractV2Parameters
object
Typed parameters for an extract v2 product configuration.
12 properties
2 required
UntypedParameters
object
Catch-all for configurations without a dedicated typed schema. Accepts arbitrary JSON fields alongside producttype.
1 property
1 required
SplitV1Parameters
object
Typed parameters for a split v1 product configuration.
3 properties
2 required
LlamaParseTables
object
Table formatting options for markdown output.
4 properties
LlamaParseOutputOptions
object
Output formatting and content extraction options. Controls how parsed content is formatted and what additional data is extracted.
7 properties
AutoModeIgnoreOptions
object
Ignore options for auto mode parsing configuration.
2 properties
LlamaParseHtmlOptions
object
HTML/web page parsing options.
3 properties
ExtractV2Job
object
An extraction job.
12 properties
6 required
LlamaParseProcessingOptions
object
Processing options shared across all parsing tiers. These options control how documents are analyzed and processed regardless of the selected tier. Some option…
7 properties
LlamaParseCropBox
object
Crop box boundaries for processing only a portion of each page. All values are ratios from 0 to 1, where (0,0) is the top-left corner and (1,1) is the bottom-r…
4 properties
ClassifyV2Rule
object
A rule for classifying documents.
2 properties
2 required
ClassifyV2ParsingConfiguration
object
Parsing configuration for classify jobs.
3 properties
ExtractJobUsage
object
Extraction usage metrics.
1 property
LlamaParseCostOptimizerParameters
object
Cost optimizer configuration for reducing parsing costs on simpler pages. When enabled, the parser analyzes each page and routes simpler pages to faster, cheap…
1 property
LlamaParseInputOptions
object
Input format-specific parsing options. These options only apply when parsing documents of the corresponding format. LlamaParse automatically detects the input…
4 properties
LlamaParseSpatialTextOptions
object
Spatial text output options for preserving document layout. Spatial text maintains the visual positioning of text elements, useful for documents where layout c…
3 properties
ExtractV2SchemaValidateRequest
object
Request schema for validating an extraction schema.
1 property
1 required
ExtractV2JobQueryResponse
object
Paginated list of extraction jobs.
3 properties
1 required
ExtractJobMetadata
object
Extraction metadata.
3 properties
WebhookConfiguration
object
Configuration for a single outbound webhook endpoint.
4 properties
AutoModeParsingConf
object
Parsing configuration applied when auto mode triggers match. These settings override the base configuration for pages where trigger conditions are satisfied. O…
14 properties
ClassifyV2Parameters
object
Typed parameters for a classify v2 product configuration.
4 properties
2 required
LlamaParseAgenticOptions
object
Options for AI-powered parsing tiers (costeffective, agentic, agenticplus). These options customize how the AI processes and interprets document content. Only…
1 property
LlamaParseTablesAsSpreadsheetOptions
object
Options for exporting extracted tables as XLSX spreadsheet files.
2 properties
SplitStrategy
object
Configuration for how to split the document.
1 property
LlamaParseFastOptions
object
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 mos…
ExtractConfiguration
object
Extract configuration combining parse and extract settings.
11 properties
1 required
ParserLanguages
string
Enum for representing the languages supported by the parser.
LlamaParseJobFailureConditions
object
Conditions that determine when a parsing job should fail vs complete with partial results. By default, jobs complete successfully even if some pages fail to pa…
5 properties
HTTPValidationError
object
1 property
LlamaParsePdfOptions
object
LlamaParseProcessingControl
object
Job processing controls for timeouts and failure handling.
2 properties
LlamaParseSpreadsheetOptions
object
Spreadsheet (Excel, CSV, ODS) parsing options.
3 properties
LlamaParseOcrParameters
object
OCR (Optical Character Recognition) configuration parameters.
1 property
ExtractV2JobCreate
object
Request to create an extraction job. Provide configurationid or inline configuration.
4 properties
1 required
ParseV2Parameters
object
Configuration for LlamaParse v2 document parsing. Includes tier selection, processing options, output formatting, page targeting, and webhook delivery. Refer t…
14 properties
3 required
AutoModeCropBox
object
Crop box options for auto mode parsing configuration.
4 properties
LlamaParseMarkdownOptions
object
Markdown output formatting options.
3 properties
ConfigurationCreateRequest
object
Request body for creating a product configuration.
2 properties
2 required
LlamaParsePresentationOptions
object
Presentation (PowerPoint, Keynote, ODP) parsing options.
2 properties
ExtractV2SchemaValidateResponse
object
Response schema for schema validation.
1 property
1 required
LlamaParseIgnoreOptions
object
Options for ignoring specific types of text during extraction.
3 properties
ExtractV2JobMetadata
object
Job-level metadata.
1 property
SpreadsheetV1Parameters
object
Typed parameters for a spreadsheet v1 product configuration.
9 properties
1 required
ExtractedFieldMetadata
object
Metadata for extracted fields including document, page, and row level info.
3 properties
AutoModeConfigurationEntry
object
A single auto mode rule with trigger conditions and parsing configuration. Auto mode allows conditional parsing where different configurations are applied base…
36 properties
1 required
ExtractV2SchemaGenerateRequest
object
Request schema for generating an extraction schema.
4 properties
LlamaParsePageRanges
object
Page selection options for processing specific pages or limiting page count.
2 properties
LlamaParseTimeouts
object
Job timeout configuration. Total timeout = baseinseconds + (extratimeperpageinseconds × pagecount). Use these settings for large documents or complex parsing t…
2 properties
ValidationError
object
5 properties
3 required
AutoModeSpatialTextOptions
object
Spatial text options for auto mode parsing configuration.
3 properties
AutoModePresentationOptions
object
Presentation-specific options for auto mode parsing configuration.
2 properties
The full machine-readable OpenAPI contract behind this narrative.
Other APIs LlamaParse publishes across the network.
