Aller au contenu
AI.info

AI Tools

LlamaIndex

LlamaIndex : prix, capacités, mises à jour et alternatives, lus sur les pages de l’éditeur.

Le site de LlamaIndex

En anglais

Key facts

Price
Paid plans: see pricing Read on llamaindex.ai
Free plan
No Read on llamaindex.ai
Platforms
Web · API Read on developers.llamaindex.ai
API
Yes
Open source
Yes · Apache-2.0 Read on github.com
Certifications
SOC 2 Type II Read on security.llamaindex.ai
Latest version
0.14.25
Last update
13 Nov 2026 Read on github.com
Prices checked
9 Nov 2026 Read on llamaindex.ai

LlamaIndex provides developer tools for connecting data to language models and building retrieval and agent applications. Its commercial LlamaParse platform parses documents and supports structured extraction, classification, splitting, and indexing for search and AI workflows.

The Python framework is open source under the MIT license. LlamaParse is a separate commercial service with a free monthly credit allowance and paid plans; its parsing and extraction use credits. The pricing below is for LlamaParse, not the open-source framework.

Category
Developer Tools
Read from the maker’s pages
2026-11-18

Company

LlamaIndex Inc.

Features

  • Build data-connected LLM applications with the Python framework
  • Create retrieval and agent applications
  • Parse documents with complex layouts, tables, charts, images, and handwriting
  • Extract structured data using schemas, with citations and confidence scores
  • Split documents into sections and classify their contents
  • Index documents for retrieval using chunking and embeddings
  • Open-source framework and Workflows are separate from commercial LlamaParse
  • LlamaIndex framework repository is MIT licensed

Use cases

  • Build a retrieval-augmented application over private documents
  • Parse invoices and extract fields into a defined schema
  • Index technical documents so users can search for answers
  • Automate document-based financial or compliance reviews
  • Create an agent workflow that processes business documents

Pricing

Paid plans: see pricing

Prices checked
2026-11-09

Pay-as-you-go

$0/mo

  • $0 /month
  • $1.5 per 1k credits
  • Includes 10K free credits
  • 100 users
  • Basic support
  • 5 concurrent parse jobs
  • 5 concurrent extract jobs
  • 1 project

Pro

$500/mo

  • $500 /month
  • $1.25 per 1k credits
  • 400K included credits
  • 20 concurrent parse jobs
  • 20 concurrent extract jobs
  • 100 users
  • 5 projects
  • Priority Slack support

Enterprise

price on request

  • Volume discount on credits
  • 5x higher rate limits
  • Enterprise SSO
  • SaaS or Hybrid cloud deployment
  • Dedicated account manager
  • Dedicated support

Capabilities

  • Self-hosted — “For enterprises, we also offer deployment in private VPCs across all cloud providers, ensuring data never leaves your tenant.” source
  • API — “Webhooks & API callbacks” source
  • Builds agents and workflows — “Build and deploy end-to-end document agents” source
  • Search over your data — “Built to deliver precision and relevance in every retrieval call for best-in-class RAG.” source

Latest updates

  • Version 0.14.26

    Relocked integration uv.lock files and raised requires-python for security fixes across integrations.

  • Version 0.14.25
  • Version 0.14.24

    Fixed issues with CodeSplitter, chat history, HTMLNodeParser, MMR search, ingestion upserts, tool parameters, filters, and AgentWorkflow output.

  • Version 0.14.21

    Fixed core issues in node deletion, structured output failures, persistence encoding, and message block buffer resolution.

  • Version 0.14.20

Where it works

Web · API

Security

  • SOC 2 Type II — “SOC 2 Type II Report (2025)” source
  • SOC 2 — “SOC 2 Type II Report (2025)” source

Alternatives to LlamaIndex

  • Reducto

    Reducto parses, extracts, classifies, splits, and edits documents, returning structured data for AI and business workflows.

  • Mindee Document AI API

    Mindee’s API extracts structured data from documents and can classify, split, and crop files.

  • Haystack

    Haystack is an open-source Python framework for building AI agents and applications with modular pipelines for retrieval, tools, memory, and generation.

  • AnythingLLM

    Chat with documents, run AI agents, and use local or cloud models through a desktop, mobile, self-hosted, or hosted workspace.

  • Vectara Platform

    Vectara helps organizations build AI agents that search business data, generate grounded answers, and connect to tools.

  • Cohere

    Cohere provides enterprise AI models and tools for text generation, search, document parsing, speech transcription, and workplace agents.

Questions about LlamaIndex

Is LlamaIndex free?

No. The maker’s pricing page lists no free plan for LlamaIndex. Prices checked on 9 Nov 2026.

How much does LlamaIndex cost?

The plans on the maker’s pricing page: Pay-as-you-go ($0/mo), Pro ($500/mo) and Enterprise (price on request). Prices checked on 9 Nov 2026.

Does LlamaIndex have an API?

Yes. The maker’s pages state that LlamaIndex has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does LlamaIndex run on?

LlamaIndex runs on Web and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is LlamaIndex open source?

Yes. The code of LlamaIndex is published at github.com/run-llama/liteparse under the Apache-2.0 licence. Read on the maker’s pages on 18 Nov 2026.

Is LlamaIndex still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that LlamaIndex has ended.

What changed recently in LlamaIndex?

The latest entry in its maker’s changelog: 13 Nov 2026, “Version 0.14.26”. Before it: 21 Sept 2026, “Version 0.14.25”. Changelog checked on 15 Nov 2026.

Sources

Official website