Sign in

v34

latestOpenAPI 3.1.0raw.githubusercontent.com2026-06-09194386949.7 KB
V2
Parse

Parse File

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.

post/api/v2/parse

Query parameters

project_idstring uuid nullable
organization_idstring uuid nullable

Cookies

sessionstring nullable

Request body

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)

client_namestring nullable

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

fast_optionsLlamaParseFastOptions

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.

disable_cacheboolean nullable

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

file_idstring nullable

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

source_urlstring nullable

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

http_proxystring nullable

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

Example request

{
  "processing_options": {
    "auto_mode_configuration": [
      {
        "parsing_conf": {
          "tier": "agentic",
          "version": "latest"
        },
        "table_in_page": true
      }
    ]
  },
  "webhook_configurations": [
    {
      "webhook_events": [
        "parse.success",
        "parse.error"
      ],
      "webhook_output_format": "json"
    }
  ],
  "output_options": {
    "additional_outputs": [
      "stripped_md",
      "concatenated_stripped_txt",
      "word_bbox"
    ],
    "granular_bboxes": [
      "word",
      "line",
      "cell"
    ]
  }
}

Response

Successful Response

idstring required

Unique parse job identifier

created_atstring date-time nullable

Creation datetime

updated_atstring date-time nullable

Update datetime

project_idstring required

Project this job belongs to

status'PENDING' | 'RUNNING' | 'COMPLETED' | 'FAILED' | 'CANCELLED' required

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

error_messagestring nullable

Error details when status is FAILED

namestring nullable

Optional display name for this parse job

tierstring nullable

Parsing tier used for this job

Example response

{
  "id": "pjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "project_id": "prj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
  "name": "Q4 Financial Report",
  "tier": "fast"
}