LlamaCloud

LlamaCloud is the managed document parsing, extraction, indexing, and retrieval platform from LlamaIndex. It exposes REST APIs at https://api.cloud.llamaindex.ai for LlamaParse (document parsing to Markdown/JSON), managed ingestion pipelines and indexes, document management, retrieval, and LlamaExtract (schema-driven structured extraction), all secured with a Bearer API key. This is the hosted cloud platform, distinct from the open-source LlamaIndex framework.

5 APIs 0 Features

AIDocument ParsingExtractionIndexingRetrievalRAG

APIs

LlamaParse API

Asynchronous document parsing that uploads files (PDF, DOCX, PPTX, images, and more) and returns clean Markdown or structured JSON. Submit a parse job, poll job status, and retr...

LlamaCloud Pipelines and Indexes API

Managed ingestion and indexing pipelines that chunk, embed, and store documents into a scalable vector index with no infrastructure to manage. Create and configure pipelines, at...

LlamaCloud Documents and Files API

Upload, list, and manage files and the documents inside a pipeline. Add documents to an index, list pipeline documents, fetch document chunks, and delete documents from the mana...

LlamaCloud Retrieval API

Retrieve the most relevant chunks from a managed index for a natural language query, with Fast, Accurate, and Advanced retrieval modes, optional reranking, and metadata filterin...

LlamaExtract API

Schema-driven structured data extraction from documents. Define an extraction agent with a JSON data schema, run extraction jobs against uploaded files, and retrieve typed JSON ...

Collections

LlamaCloud API

OPEN

Pricing Plans

Llamacloud Plans Pricing

5 plans

PLANS

Rate Limits

Llamacloud Rate Limits

5 limits

RATE LIMITS

FinOps

Llamacloud Finops

FINOPS

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: LlamaCloud API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{LLAMA_CLOUD_API_KEY}}'
items:
- info:
    name: Parsing
    type: folder
  items:
  - info:
      name: Upload a file to start a parse job
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/parsing/upload
      body:
        type: multipart-form
        data: []
    docs: Uploads a document and creates an asynchronous LlamaParse job.
  - info:
      name: Get parse job status
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/parsing/job/{job_id}
    docs: Returns the status of a parse job; poll until SUCCESS.
  - info:
      name: Get parse result as Markdown
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/parsing/job/{job_id}/result/markdown
    docs: Returns the parse result as Markdown.
  - info:
      name: Get parse result as JSON
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/parsing/job/{job_id}/result/json
    docs: Returns the parse result as structured JSON.
- info:
    name: Pipelines
    type: folder
  items:
  - info:
      name: Create or upsert a pipeline
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines
      body:
        type: json
        data: '{}'
    docs: Creates a managed ingestion and indexing pipeline.
  - info:
      name: List pipelines
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines
    docs: Lists pipelines.
  - info:
      name: Get a pipeline
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines/{pipeline_id}
    docs: Returns a single pipeline.
  - info:
      name: Get pipeline ingestion status
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines/{pipeline_id}/status
    docs: Returns ingestion status for a pipeline.
  - info:
      name: Add files to a pipeline
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines/{pipeline_id}/files
      body:
        type: json
        data: '[]'
    docs: Attaches uploaded files to a pipeline for ingestion.
- info:
    name: Documents
    type: folder
  items:
  - info:
      name: Upload a file
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/files
      body:
        type: multipart-form
        data: []
    docs: Uploads a file to LlamaCloud.
  - info:
      name: List files
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/files
    docs: Lists uploaded files.
  - info:
      name: Add documents to a pipeline
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines/{pipeline_id}/documents
      body:
        type: json
        data: '[]'
    docs: Adds raw documents directly to a pipeline's managed index.
  - info:
      name: List pipeline documents
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines/{pipeline_id}/documents
    docs: Lists documents in a pipeline.
- info:
    name: Retrieval
    type: folder
  items:
  - info:
      name: Retrieve relevant chunks from a pipeline index
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/pipelines/{pipeline_id}/retrieve
      body:
        type: json
        data: '{}'
    docs: Runs a retrieval query and returns the most relevant nodes.
- info:
    name: Extraction
    type: folder
  items:
  - info:
      name: Create an extraction agent
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/extraction/extraction-agents
      body:
        type: json
        data: '{}'
    docs: Defines a LlamaExtract agent bound to a JSON data schema.
  - info:
      name: List extraction agents
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/extraction/extraction-agents
    docs: Lists extraction agents.
  - info:
      name: Run an extraction job
      type: http
    http:
      method: POST
      url: https://api.cloud.llamaindex.ai/api/v1/extraction/jobs
      body:
        type: json
        data: '{}'
    docs: Runs an extraction agent against an uploaded file.
  - info:
      name: Get extraction job status
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/extraction/jobs/{job_id}
    docs: Returns the status of an extraction job.
  - info:
      name: Get extraction job result
      type: http
    http:
      method: GET
      url: https://api.cloud.llamaindex.ai/api/v1/extraction/jobs/{job_id}/result
    docs: Returns the structured extraction result.