LlamaParse (formerly LlamaCloud)
LlamaIndex's managed document parsing and extraction platform, renamed in 2026
Overview
LlamaParse (formerly LlamaCloud) is LlamaIndex's managed document-AI platform: agentic parsing of PDFs and 130+ formats into clean text and Markdown, schema extraction, classification, splitting and managed retrieval, deployable as SaaS in the US or EU, in your cloud or self-hosted. Free 10,000 credits a month; Starter $50, Pro $500.
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 1 Oct 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.
- 100 users
- Community support
- 20 requests per minute
- Pay-as-you-go up to $500/mo
- Email support
- 50 indexes
- Pay-as-you-go up to $5,000/mo
- Priority Slack support
- 20 concurrent parse jobs
- 5 projects
- 5x higher rate limits
- Enterprise SSO
- SaaS or hybrid deployment
- Dedicated account manager
Use cases
What you can produce with LlamaParse (formerly LlamaCloud)
- Agentic document parsing for 130+ formats
- Schema-based extraction (Extract)
- Document classification and splitting
- Managed retrieval index (v2)
- MCP server and open-source LiteParse
- SaaS, BYOC and self-hosted deployment
LlamaParse is one of the strongest options for parsing difficult documents into AI-ready data, with flexible quality modes, extraction tools and serious deployment and compliance options. The rename from LlamaCloud and the deprecation of its first Index add some churn, and costs scale quickly in the agentic modes. Its usage figures are its own. Excellent for teams building retrieval or extraction over messy files; test the parsing mode you need on your own documents before committing volume.
What we found
LlamaParse, called LlamaCloud until late September 2026, is LlamaIndex's managed platform for turning complex documents into data that AI applications can use. Its core is document parsing: it reads PDFs, slides, spreadsheets, scans and more than 130 file formats in over 80 languages, including tables, charts and handwriting, and returns clean text, Markdown or structured output, with modes ranging from fast to agentic. Around that it offers Extract, which pulls fields into a schema and gained a faster Turbo tier and version 2.5 in autumn 2026, Classify and Split for sorting and dividing documents, a new version of its managed Index for retrieval, an MCP server and an open-source LiteParse library; its older Index, Sheets and Verify products are deprecated. The company says more than 300,000 people use LlamaParse and that it has processed over a billion documents, its own figures.
LlamaParse is run by LlamaIndex, Inc. of San Francisco, the company behind the open-source LlamaIndex framework, started by Jerry Liu and Simon Suo. It raised a $19 million Series A led by Norwest Venture Partners in March 2025, for $27.5 million in total, and Databricks and KPMG later took strategic stakes. It names Carlyle, KPMG, Cemex and Jeppesen among customers. It runs as managed SaaS in North America and the EU, single-tenant, in a customer's own AWS, Azure or Google Cloud account, or self-hosted, with SOC 2 Type II, GDPR and HIPAA compliance.
Pricing uses credits, with 1,000 credits costing $1.25. Parsing costs 1 to 45 credits a page depending on the mode, or $0.00125 to $0.056. The free plan includes 10,000 credits a month and community support; Starter costs $50 a month for 40,000 credits and pay-as-you-go up to $500; Pro costs $500 for 400,000 credits, priority Slack support and pay-as-you-go up to $5,000; and Enterprise is custom.
LlamaParse suits teams building retrieval and document-AI applications on messy real-world files.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
About this listing
This entry was compiled from publicly available data including LlamaParse (formerly LlamaCloud)'s official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with LlamaParse (formerly LlamaCloud) unless explicitly stated.
Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.
For the latest details, please refer to LlamaParse (formerly LlamaCloud) directly →
Spotted something out of date? Suggest an update →
Related reading
Alternatives to LlamaParse (formerly LlamaCloud)
More in Code & Dev Tools
