--- title: "List Configurations" method: GET path: "/api/v1/beta/configurations" tags: ["Beta", "Configurations", "Configurations"] --- # List Configurations `GET /api/v1/beta/configurations` List product configurations for the current project. ## Query parameters - `product_type` string[], nullable — Filter by one or more product types. Repeat the parameter for multiple values. - `name` string, nullable — Filter by configuration name. - `page_size` integer, nullable — Number of items per page. - `page_token` string, nullable — Pagination token. - `latest_only` boolean — Return only the latest version per configuration name. - `project_id` string, uuid, nullable - `organization_id` string, uuid, nullable ## Cookies - `session` string, nullable ## Response `200` Successful Response - ConfigurationQueryResponse — Paginated list of product configurations. - `items` ConfigurationResponse[], required — The list of items. - `id` string, required — Unique configuration ID. - `created_at` string, date-time, nullable — Creation timestamp. - `updated_at` string, date-time, nullable — Last update timestamp. - `name` string, required — Configuration name. - `product_type` 'split_v1' | 'extract_v2' | 'classify_v2' | 'parse_v2' | 'spreadsheet_v1' | 'unknown', required — Product type. - `version` string, required — Version identifier (datetime string). - `parameters` union, required — Product-specific configuration parameters. - SplitV1Parameters — Typed parameters for a *split v1* product configuration. - `categories` SplitCategory[], required — Categories to split documents into. - `name` string, required — Name of the category. - `description` string, nullable — Optional description of what content belongs in this category. - `splitting_strategy` SplitStrategy — Configuration for how to split the document. - `allow_uncategorized` 'include' | 'forbid' | 'omit' — Controls handling of pages that don't match any category. 'include': pages can be grouped as 'uncategorized' and included in results. 'forbid': all pages must be assigned to a defined category. 'omit': pages can be classified as 'uncategorized' but are excluded from results. - `product_type` 'split_v1', required — Product type. - ExtractV2Parameters — Typed parameters for an *extract v2* product configuration. - `target_pages` string, nullable — Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `max_pages` integer, nullable — Maximum number of pages to process. Omit for no limit. - `tier` 'cost_effective' | 'agentic' — Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page) - `version` string — Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. - `data_schema` object, required — JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. - `extraction_target` 'per_doc' | 'per_page' | 'per_table_row' — Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row - `system_prompt` string, nullable — Custom system prompt to guide extraction behavior - `cite_sources` boolean — Include citations in results - `confidence_scores` boolean — Include confidence scores in results - `parse_tier` string, nullable — Parse tier to use before extraction. Defaults to the extract tier if not specified. - `parse_config_id` string, nullable — Saved parse configuration ID to control how the document is parsed before extraction - `product_type` 'extract_v2', required — Product type. - ClassifyV2Parameters — Typed parameters for a *classify v2* product configuration. - `rules` ClassifyV2Rule[], required — Classify rules to evaluate against the document (at least one required) - `type` string, required — Document type to assign when rule matches - `description` string, required — Natural language criteria for matching this rule - `mode` 'FAST' — Classify execution mode - `parsing_configuration` ClassifyV2ParsingConfiguration — Parsing configuration for classify jobs. - `lang` string — ISO 639-1 language code for the document - `target_pages` string, nullable — Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. - `max_pages` integer, nullable — Maximum number of pages to process. Omit for no limit. - `product_type` 'classify_v2', required — Product type. - ParseV2Parameters — Configuration for LlamaParse v2 document parsing. Includes tier selection, processing options, output formatting, page targeting, and webhook delivery. Refer to the LlamaParse documentation for details on each field. - `tier` 'fast' | 'cost_effective' | 'agentic' | 'agentic_plus', required — Parsing tier: 'fast' (rule-based, cheapest), 'cost_effective' (balanced), 'agentic' (AI-powered with custom prompts), or 'agentic_plus' (premium AI with highest accuracy) - `version` union, required — Version for the selected tier. Use `latest`, or pin one of that tier's dated versions. Current `latest` by tier: - `fast`: `2025-12-11` - `cost_effective`: `2026-06-05` - `agentic`: `2026-06-04` - `agentic_plus`: `2026-06-04` Full list: `GET /api/v2/parse/versions`. - 'latest' | '2026-06-05' | '2026-06-04' | '2025-12-11' - string - `client_name` string, nullable — Identifier for the client/application making the request. Used for analytics and debugging. Example: 'my-app-v2' - `processing_options` LlamaParseProcessingOptions — Processing options shared across all parsing tiers. These options control how documents are analyzed and processed regardless of the selected tier. Some options automatically enable additional behaviors (e.g., specialized_chart_parsing enables extract_layout and precise_bounding_box). - `ignore` LlamaParseIgnoreOptions — Options for ignoring specific types of text during extraction. - `ignore_diagonal_text` boolean, nullable — Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring watermarks or decorative angled text - `ignore_text_in_image` boolean, nullable — Skip OCR text extraction from embedded images. Use when images contain irrelevant text (watermarks, logos) that shouldn't be in the output - `ignore_hidden_text` boolean, nullable — Skip text marked as hidden in the document structure. Some PDFs contain invisible text layers used for accessibility or search indexing - `ocr_parameters` LlamaParseOcrParameters — OCR (Optical Character Recognition) configuration parameters. - `languages` ParserLanguages[], nullable — 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 - `aggressive_table_extraction` boolean, nullable — Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables - `disable_heuristics` boolean, nullable — Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results - `specialized_chart_parsing` 'agentic_plus' | 'agentic' | 'efficient', nullable — 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 - `cost_optimizer` LlamaParseCostOptimizerParameters — 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` boolean, nullable — 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 - `auto_mode_configuration` AutoModeConfigurationEntry[], nullable — 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 - `parsing_conf` AutoModeParsingConf, required — Parsing configuration applied when auto mode triggers match. These settings override the base configuration for pages where trigger conditions are satisfied. Only specify fields you want to override - unset fields inherit from the base configuration. - … - `trigger_mode` string, nullable — How to combine multiple trigger conditions: 'and' (all conditions must match, this is the default) or 'or' (any single condition can trigger) - `page_md_error` boolean, nullable — Trigger on pages with markdown extraction errors - `text_in_page` string, nullable — Trigger if page text/markdown contains this string - `table_in_page` boolean, nullable — Trigger if page contains a table - `image_in_page` boolean, nullable — Trigger if page contains non-screenshot images - `full_page_image_in_page` boolean, nullable — Trigger if page contains a full-page image (scanned page detection) - `full_page_image_in_page_threshold` union — Threshold for full page image detection (0.0-1.0, default 0.8) - … - `filename_regexp` string, nullable — Regex pattern to match against filename - `filename_regexp_mode` string, nullable — Regex mode flags (e.g., 'i' for case-insensitive) - `filename_match_glob` string, nullable — Single glob pattern to match against filename - `filename_match_glob_list` string[], nullable — List of glob patterns to match against filename - `page_longer_than_n_chars` union — Trigger if page has more than N characters - … - `page_shorter_than_n_chars` union — Trigger if page has fewer than N characters - … - `page_contains_at_least_n_words` union — Trigger if page has more than N words - … - `page_contains_at_most_n_words` union — Trigger if page has fewer than N words - … - `page_contains_at_least_n_lines` union — Trigger if page has more than N lines - … - `page_contains_at_most_n_lines` union — Trigger if page has fewer than N lines - … - `page_contains_at_least_n_images` union — Trigger if page has more than N images - … - `page_contains_at_most_n_images` union — Trigger if page has fewer than N images - … - `page_contains_at_least_n_tables` union — Trigger if page has more than N tables - … - `page_contains_at_most_n_tables` union — Trigger if page has fewer than N tables - … - `page_contains_at_least_n_links` union — Trigger if page has more than N links - … - `page_contains_at_most_n_links` union — Trigger if page has fewer than N links - … - `page_contains_at_least_n_charts` union — Trigger if page has more than N charts - … - `page_contains_at_most_n_charts` union — Trigger if page has fewer than N charts - … - `page_contains_at_least_n_layout_elements` union — Trigger if page has more than N layout elements - … - `page_contains_at_most_n_layout_elements` union — Trigger if page has fewer than N layout elements - … - `page_contains_at_least_n_percent_numbers` union — Trigger if page has more than N% numeric words - … - `page_contains_at_most_n_percent_numbers` union — Trigger if page has fewer than N% numeric words - … - `page_contains_at_least_n_numbers` union — Trigger if page has more than N numeric words - … - `page_contains_at_most_n_numbers` union — Trigger if page has fewer than N numeric words - … - `regexp_in_page` string, nullable — Regex pattern to match in page content - `regexp_in_page_mode` string, nullable — Regex mode flags for regexp_in_page - `layout_element_in_page` string, nullable — Trigger if page contains this layout element type - `layout_element_in_page_confidence_threshold` union — Confidence threshold for layout element detection - … - `fast_options` LlamaParseFastOptions — 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. - `agentic_options` LlamaParseAgenticOptions — 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. - `custom_prompt` string, nullable — 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.' - `webhook_configurations` LlamaParseWebhookConfiguration[] — Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services - `webhook_url` string, nullable — HTTPS URL to receive webhook POST requests. Must be publicly accessible - `webhook_headers` object, nullable — Custom HTTP headers to include in webhook requests. Use for authentication tokens or custom routing. Example: {'Authorization': 'Bearer xyz'} - `webhook_events` string[], nullable — Events that trigger this webhook. Options: 'parse.success' (job completed), 'parse.error' (job failed), 'parse.partial_success' (some pages failed), 'parse.pending', 'parse.running', 'parse.cancelled'. If not specified, webhook fires for all events - `webhook_output_format` 'string' | 'json', nullable — Format of the webhook payload body. 'string' (default) sends the payload as a JSON-encoded string; 'json' sends it as a JSON object. - `input_options` LlamaParseInputOptions — Input format-specific parsing options. These options only apply when parsing documents of the corresponding format. LlamaParse automatically detects the input format based on file extension and content. - `html` LlamaParseHtmlOptions — HTML/web page parsing options. - `make_all_elements_visible` boolean, nullable — Force all HTML elements to be visible by overriding CSS display/visibility properties. Useful for parsing pages with hidden content or collapsed sections - `remove_fixed_elements` boolean, nullable — Remove fixed-position elements (headers, footers, floating buttons) that appear on every page render - `remove_navigation_elements` boolean, nullable — Remove navigation elements (nav bars, sidebars, menus) to focus on main content - `pdf` LlamaParsePdfOptions - `spreadsheet` LlamaParseSpreadsheetOptions — Spreadsheet (Excel, CSV, ODS) parsing options. - `detect_sub_tables_in_sheets` boolean, nullable — Detect and extract multiple tables within a single sheet. Useful when spreadsheets contain several data regions separated by blank rows/columns - `force_formula_computation_in_sheets` boolean, nullable — Compute formula results instead of extracting formula text. Use when you need calculated values rather than formula definitions - `include_hidden_sheets` boolean, nullable — Parse hidden sheets in addition to visible ones. By default, hidden sheets are skipped - `presentation` LlamaParsePresentationOptions — Presentation (PowerPoint, Keynote, ODP) parsing options. - `out_of_bounds_content` boolean, nullable — Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries - `skip_embedded_data` boolean, nullable — Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data - `crop_box` LlamaParseCropBox — 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-right corner. For example, to process only the top half of each page, set bottom=0.5 (keeping top=0, left=0, right=1). - `bottom` number, nullable — Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded - `left` number, nullable — Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded - `right` number, nullable — Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded - `top` number, nullable — Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded - `page_ranges` LlamaParsePageRanges — Page selection options for processing specific pages or limiting page count. - `max_pages` integer, nullable — 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 - `target_pages` string, nullable — 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 - `disable_cache` boolean, nullable — Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results - `output_options` LlamaParseOutputOptions — Output formatting and content extraction options. Controls how parsed content is formatted and what additional data is extracted. - `markdown` LlamaParseMarkdownOptions — Markdown output formatting options. - `annotate_links` boolean, nullable — Add link annotations to markdown output in the format [text](url). When false, only the link text is included - `tables` LlamaParseTables — Table formatting options for markdown output. - … - `inline_images` boolean, nullable — Embed images directly in markdown as base64 data URIs instead of extracting them as separate files. Useful for self-contained markdown output - `spatial_text` LlamaParseSpatialTextOptions — Spatial text output options for preserving document layout. Spatial text maintains the visual positioning of text elements, useful for documents where layout conveys meaning (forms, tables, multi-column layouts). - `preserve_layout_alignment_across_pages` boolean, nullable — Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes - `preserve_very_small_text` boolean, nullable — Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out - `do_not_unroll_columns` boolean, nullable — Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers - `tables_as_spreadsheet` LlamaParseTablesAsSpreadsheetOptions — Options for exporting extracted tables as XLSX spreadsheet files. - `enable` boolean, nullable — Whether this option is enabled - `guess_sheet_name` boolean — Automatically generate descriptive sheet names from table context (headers, surrounding text) instead of using generic names like 'Table_1' - `extract_printed_page_number` boolean, nullable — 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 - `images_to_save` string[] — 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 - `additional_outputs` string[] — Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: 'stripped_md' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. 'concatenated_stripped_txt' — all stripped pages concatenated into a single plain-text file with `\n\n---\n\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. 'word_bbox' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`. - `granular_bboxes` string[] — Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape. - `processing_control` LlamaParseProcessingControl — Job processing controls for timeouts and failure handling. - `timeouts` LlamaParseTimeouts — Job timeout configuration. Total timeout = base_in_seconds + (extra_time_per_page_in_seconds × page_count). Use these settings for large documents or complex parsing that needs more time. - `base_in_seconds` integer, nullable — Base timeout for the job in seconds (max 7200 = 2 hours). This is the minimum time allowed regardless of document size - `extra_time_per_page_in_seconds` integer, nullable — Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout = base + (this value × page count) - `job_failure_conditions` LlamaParseJobFailureConditions — 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 parse. Use these settings to enforce stricter quality requirements. - `allowed_page_failure_ratio` number, nullable — 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%) - `fail_on_image_extraction_error` boolean, nullable — Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job - `fail_on_image_ocr_error` boolean, nullable — Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image - `fail_on_markdown_reconstruction_error` boolean, nullable — Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction - `fail_on_buggy_font` boolean, nullable — Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters - `product_type` 'parse_v2', required — Product type. - SpreadsheetV1Parameters — Typed parameters for a *spreadsheet v1* product configuration. - `sheet_names` string[], nullable — The names of the sheets to extract regions from. If empty, all sheets will be processed. - `include_hidden_cells` boolean — Whether to include hidden cells when extracting regions from the spreadsheet. - `extraction_range` string, nullable — A1 notation of the range to extract a single region from. If None, the entire sheet is used. - `generate_additional_metadata` boolean — Whether to generate additional metadata (title, description) for each extracted region. - `use_experimental_processing` boolean — Enables experimental processing. Accuracy may be impacted. - `flatten_hierarchical_tables` boolean — Return a flattened dataframe when a detected table is recognized as hierarchical. - `table_merge_sensitivity` 'strong' | 'weak' — Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging). - `specialization` string, nullable — Optional specialization mode for domain-specific extraction. Supported values: 'financial-standard', 'financial-enhanced', 'financial-precise'. Default None uses the general-purpose pipeline. - `product_type` 'spreadsheet_v1', required — Product type. - UntypedParameters — Catch-all for configurations without a dedicated typed schema. Accepts arbitrary JSON fields alongside ``product_type``. - `product_type` 'unknown', required — Product type. - `next_page_token` string, nullable — A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `total_size` integer, nullable — The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. ## Other responses - `422` — Validation Error --- [API](https://skmtc.net/run-llama/apis/llama-platform.md) · [All operations](https://skmtc.net/run-llama/apis/llama-platform/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/run-llama/llama-platform/versions/b17341164de9/schema)