LlamaIndex
Also known as: LlamaParse, LlamaCloud
Document agents and parsing platform (LlamaParse, LlamaAgents) plus the open source LlamaIndex framework for building agents and RAG over your data.
LlamaIndex builds tools for turning documents into context that AI agents can use. Its commercial LlamaParse Platform, run on LlamaCloud, covers agentic OCR and parsing across more than 130 file formats, structured extraction with citations and confidence scores, classification and splitting, with an SDK and API behind each. LlamaAgents deploys document workflow agents on top of it, from one-click starter templates such as SEC Insights and Invoice Matching or from code built with the llamactl CLI. LlamaIndex also publishes LiteParse, a fast local open source parser.
The open source LlamaIndex framework for Python and TypeScript supplies the building blocks. They include data connectors and an ingestion pipeline, indexes over vector stores, retrievers and query engines, agents that call tools defined as Python functions or ready made tool specs, memory with short term and long term blocks, and event driven Workflows that mix document operations, agent steps and human input. An evaluation module scores faithfulness and retrieval quality, and an OpenTelemetry integration exports traces of every step.
LlamaCloud is priced on credits across Free, Starter, Pro and Enterprise plans, in US and European regions. Enterprise adds SSO and MFA, private VPC, hybrid and self hosted deployment. LlamaIndex is certified for SOC 2 Type II, GDPR and HIPAA, with a trust center at security.llamaindex.ai.
Vendor details
Canonical URL
https://www.llamaindex.ai/
Category
Agent infrastructure
Company status
independent
Use cases & customers
Target customers
Deployment options
In practice
You need a chatbot that answers from 200,000 of your own PDFs and filings, not the open web. LlamaIndex ingests, indexes, and retrieves over that private data, returning answers with citations to the source passages.
Your invoices and contracts are scanned PDFs and messy spreadsheets that standard OCR mangles. LlamaParse reads complex layouts and tables, and Extract pulls the specific fields you need into structured data.
You want a document agent without wiring the whole pipeline yourself. LlamaAgents deploys a starter template such as SEC Insights, which classifies financial filings and extracts insights, in one click from LlamaCloud, and the llamactl CLI lets you fork and extend it in code.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
Agents execute tools defined as Python functions or FunctionTool and QueryEngineTool classes, plus pre-defined Tool Specs for common APIs, and MCP and data connectors are supported, so tools can be written by the customer or taken from a catalog. SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/deploying/agentsread 2026-09-21 |
|
| Workflow Orchestration | Full |
|
Workflows stitch Parse, Extract, Split, Classify and custom Python operations into event-driven multi-step processes, with multi-agent patterns in the framework and a durable runtime that releases idle workflows and resumes them, so one process can mix deterministic operations with agent steps. SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/overview and /python/llamaagents/workflows/dbosread 2026-09-21 |
|
| Knowledge Grounding & RAG | Full |
|
The framework's ingestion pipeline loads content through data connectors into documents and nodes, builds persistent indexes over vector stores, and queries them through retrievers and query engines, and extraction adds citations and confidence scores. SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/indexing and llamaindex.ai/pricingread 2026-09-21 |
|
| Human Oversight & Guardrails | Full |
|
Workflows pause on a built-in InputRequiredEvent that tells the caller what is needed, such as approving a draft, and resume only when a HumanResponseEvent comes back. Deployed workflows accept that response over an events endpoint, and a human-in-the-loop starter template is available. SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/workflows/human_in_the_loop and /workflows/deploymentread 2026-09-21 |
|
| Security, Identity & Governance | Full |
|
LlamaIndex is certified for SOC 2 Type II, GDPR and HIPAA, with custom BAAs and a trust center hosted on Vanta at security.llamaindex.ai, and Enterprise adds SSO and MFA for the customer's own identity provider. SourceLlamaIndex, llamaindex.ai/pricing and security.llamaindex.airead 2026-09-21 |
|
| Observability & Auditability | Partial |
|
LlamaIndex's own instrumentation and OpenTelemetry integration capture LLM calls, agent steps, retrieval components and workflow steps as spans exported to a backend the customer runs, and deployed workflows show an events log, so each step can be inspected. Traces live in the customer's chosen backend, and LlamaIndex offers no audit log separate from runtime traces and no retention by plan. SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/observability and /python/llamaagents/workflows/observabilityread 2026-09-21 |
|
| Memory & State Persistence | Full |
|
The Memory class holds short-term memory as a token-limited queue of messages scoped by session, and long-term memory blocks that receive messages flushed from short-term memory and extract information over time, merged back into context on retrieval with a stated priority when limits are hit. SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/deploying/agents/memoryread 2026-09-21 |
|
| Deployment & Data Residency | Full |
|
The platform is offered in US and European regions, and Enterprise adds SaaS or hybrid deployment, private VPCs across cloud providers so data never leaves the customer's tenant, and self-hosting and bring-your-own-cloud deployment. The open source framework runs wherever the customer runs it. SourceLlamaIndex, llamaindex.ai/pricing and developers.llamaindex.ai/llamaparse/self_hostingread 2026-09-21 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
LlamaAgents offers starter templates deployable in one click from LlamaCloud, each a complete, working document workflow application, including SEC Insights for classifying financial filings and extracting insights and Invoice Matching. SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/cloud/click-to-deploy and llamaindex.ai/pricingread 2026-09-21 |
|
| Triggers & Channel Coverage | Partial |
|
Deployed workflows start on HTTP calls and accept events while running, so any outside system can be wired to them. The customer wires up each source, and LlamaIndex names no built in channel and has no schedule or event subscription that starts an agent on its own. The platform's webhooks are callbacks on finished jobs. SourceLlamaIndex, developers.llamaindex.ai/python/llamaagents/workflows/deployment and llamaindex.ai/pricingread 2026-09-21 |
|
| Model Flexibility & Routing | Full |
|
The developer chooses the LLM and embedding model from the framework's model integrations, and agents send tool schemas to whichever provider is configured. SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/models and /module_guides/deploying/agentsread 2026-09-21 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
The LlamaParse Platform ships an SDK and API key access to Parse, Extract, Classify, Split and Index, deployed workflows expose HTTP endpoints, and the framework itself is a Python and TypeScript SDK. SourceLlamaIndex, developers.llamaindex.ai/llamaparse and /python/llamaagents/workflows/deploymentread 2026-09-21 |
|
| Testing, Debugging & Optimization | Full |
|
The evaluation module scores the customer's own pipeline. A faithfulness evaluator checks whether answers are supported by the retrieved context, a retriever evaluator scores retrieval against named metrics, and a batch runner evaluates sets of queries as scored test cases. SourceLlamaIndex, developers.llamaindex.ai/python/framework/module_guides/evaluatingread 2026-09-21 |
|
| Browser & Computer Use | Not documented |
|
LlamaIndex parses documents. The framework, LlamaAgents and the LlamaParse Platform offer no browser, desktop or computer control. SourceLlamaIndex, developers.llamaindex.airead 2026-09-21 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
OCRia-1, a 4 billion parameter vision language model that LlamaIndex trained for document parsing, now powers LlamaParse at the same price. It rebuilds complex tables with nested headers and merged cells, turns charts into tables of their data points, and keeps formatting such as superscripts, checkboxes and math notation. On ParseBench it scores 87.4 overall, 12.1 points ahead of the next parsing model under 35 billion parameters.
Bears on: Agent capability
View sourceOpenDocRouter, a new standalone API from LlamaIndex, turns PDFs and images into markdown using a choice of frontier and open source models, each benchmarked on ParseBench for quality and cost per page. An optional layout mode returns bounding boxes with one shared set of layout classes for every model, and billing is token based, with $5 of starter credit and no charge for failed pages.
Bears on: Pricing / packaging
View sourceLlamaIndex released Extract v2.5, new document extraction agents that reason over document structure and cross reference context across pages. The stronger harness, previously limited to the top tier, now runs on the cheaper tiers too, and citations with bounding boxes reach the Agentic tier, with no change in per page price.
Bears on: Agent capability
View sourcePricing
Starter is $50 a month with 40K credits, and Pro is $500 a month with 400K credits. A Free plan includes 10K credits a month, and Enterprise is custom.
Monthly LlamaCloud plans with included credits, which parsing, extraction, classification, splitting and indexing draw down. Usage beyond the included credits is pay as you go at $1.25 per 1,000 credits, up to a cap on each plan.
Included quota
The framework is free and open source. Free, at $0, includes 10K credits a month, 5 indexes of 50 files, 1 project, 100 users and community support. Starter, at $50 a month, includes 40K credits, pay as you go up to $500 a month, and 50 indexes of 500 files. Pro, at $500 a month, includes 400K credits, pay as you go up to $5,000 a month, 100 indexes of 2,000 files, 5 projects and Slack Connect support. Enterprise has custom credits, 5x rate limits, SSO, SaaS or hybrid deployment and a dedicated account manager.
What is public
LlamaCloud offers Free ($0, 10K credits), Starter ($50 a month, 40K credits) and Pro ($500 a month, 400K credits), with limits per plan on concurrent jobs, indexes and projects, a credit rate of $1.25 per 1,000 credits, and US or Europe hosting. Enterprise is custom. The LlamaIndex framework is free and open source.
Billing mechanics
LlamaCloud runs on credits ($1.25 per 1,000 credits) consumed by parsing, extraction, classification, splitting and indexing. Starter and Pro are monthly plans with included credits and capped pay as you go usage. The open source framework carries no fee.
Cost watchouts
Credit use varies with the parse and extract tier chosen, so cost tracks document complexity as well as page count. Model, embedding and vector store costs for the open source framework are the customer's own.
Variable cost rationale
LlamaCloud meters credits, which parsing, extraction, classification, splitting and indexing draw down at a rate set by the parse or extract tier chosen. Spend grows with pages processed and document complexity, on top of the monthly plan fee. Pay as you go usage is capped at $500 a month on Starter and $5,000 on Pro, a cached result parses again at no credit cost, and Enterprise negotiates volume discounts. The open source framework meters nothing, and its model, embedding and vector store costs are the customer's own.
Additional watchouts
Credit burn depends on the parse tier. SSO and VPC deployment start at Enterprise. The Pro launch bonus of 800K credits is a limited time, one time offer and expires on downgrade.
Overage / add-ons
Usage beyond the included credits is pay as you go at $1.25 per 1,000 credits, capped at $500 a month on Starter and $5,000 on Pro. Enterprise negotiates volume discounts. Parsing a cached result again costs no credits.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan at $0 with 10K credits a month, and the open source framework is free
Lowest paid plan
Starter at $50 a month, with 40K credits
Commercial notes
LlamaIndex sells the LlamaParse Platform on LlamaCloud and publishes the LlamaIndex framework and LiteParse as open source. The platform is also listed on the AWS and Microsoft Azure marketplaces.
Key ambiguities
The credit cost per page depends on the parse or extract tier selected. Enterprise pricing is set through sales.
Cancellation / refund
The open source framework has no contract, and LlamaCloud Free costs nothing. Starter and Pro are self serve monthly plans with included credits and capped pay as you go usage, and Enterprise is contracted through sales.
Support SLA / resale
Community support on Free, email support on Starter, priority Slack Connect on Pro, and dedicated support with an account manager on Enterprise. All plans state 99.9% uptime.
Missing data
Enterprise pricing is not published.
Related vendors
- AgentOps — Agent observability and debugging platform: open source SDKs trace…
- AgentPhone — AgentPhone gives the AI agents a team builds their own US or…
- Agno — Python agent framework and AgentOS runtime (formerly Phidata) for…
- AIsa — Resource and payment gateway for AI agents, with one key to 110+…
- Albato — Albato is a no code integration platform that sells an embedded,…
- AlphaBitCore — AI control plane for regulated financial firms: one gateway enforces…
Alternatives to LlamaIndex
The closest documented capability profiles to LlamaIndex among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- LangChain11.5 / 14A lighter documented profile than LlamaIndexLlamaIndex vs LangChain →
- Agno13.0 / 14Fuller documented coverage on Observability & Auditability and Triggers & Channel Coverage
- Haystack12.0 / 14Fuller documented coverage on Observability & AuditabilityLlamaIndex vs Haystack →
- Tray.ai13.0 / 14Fuller documented coverage on Observability & Auditability and Triggers & Channel Coverage
- Kestra12.5 / 14Fuller documented coverage on Observability & Auditability and Triggers & Channel Coverage
- Mastra14.0 / 14Adds documented Browser & Computer Use
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded