RAGFlow Pricing & Plans 2026

Name: RAGFlow
Brand: RAGFlow
Availability: InStock

Complete pricing guide for RAGFlow. Compare all plans, analyze costs, and find the perfect tier for your needs.

Not sure if free is enough? See our Free vs Paid comparison →
Still deciding? Read our full verdict on whether RAGFlow is worth it →

🆓Free Tier Available

💎4 Paid Plans

⚡No Setup Fees

Choose Your Plan

Open Source Self-Hosted

Free software license; infrastructure and model costs not included

Start Free →

Free

$0/month

Start Free Trial →

Starter

$29/month shown with a higher $59/month reference price on the site

Start Free Trial →

Pro

$129/month shown with a higher $259/month reference price on the site

Start Free Trial →

Enterprise

Contact sales

Contact Sales →

Pricing sourced from RAGFlow · Last verified March 2026

Feature Comparison

Detailed feature comparison coming soon. Visit RAGFlow's website for complete plan details.

View Full Features →

Is RAGFlow Worth It?

✅ Why Choose RAGFlow

• Strong document-ingestion focus: supports complex unstructured formats as well as Word, slides, spreadsheets, text, images, scanned copies, structured data, and web pages.
• Explainable chunking workflow with template-based chunking options and visualization of text chunks so humans can inspect or intervene before retrieval quality problems become answer quality problems.
• Grounded answer design includes quick reference views and traceable citations, which is useful for legal, finance, compliance, and internal knowledge workflows where source evidence matters.
• Hybrid retrieval stack combines vector search, BM25/full-text search, custom scoring, multiple recall, and fused reranking rather than relying only on embeddings.
• Open-source Apache-2.0 project with substantial GitHub traction, public documentation, Docker-based deployment, APIs, and active release history.
• Agent capabilities are built into the product direction, including visual workflows, tools, MCP integration, web search, chat channels, agent memory, and code executor support.

⚠️ Consider This

• Self-hosting is infrastructure-heavy for casual users: the README lists minimum requirements of 4 CPU cores, 16 GB RAM, 50 GB disk, Docker, Docker Compose, and Python 3.13.
• Prebuilt Docker images are documented as x86 only; ARM64 users must build compatible images themselves, and switching Infinity on Linux ARM64 is not officially supported.
• The Docker image is now a slim edition that relies on external LLM and embedding services, so teams still need to configure and pay for model providers or run compatible model infrastructure.
• The full stack has several moving parts, including document engine configuration, Docker environment files, backend service settings, and storage/search dependencies, which raises operational complexity.
• Cloud lower tiers have tight dataset-storage limits, especially the Free tier at 0.1 GB and Starter at 5 GB, which may be too small for realistic enterprise document collections.

What Users Say About RAGFlow

👍 What Users Love

✓Strong document-ingestion focus: supports complex unstructured formats as well as Word, slides, spreadsheets, text, images, scanned copies, structured data, and web pages.
✓Explainable chunking workflow with template-based chunking options and visualization of text chunks so humans can inspect or intervene before retrieval quality problems become answer quality problems.
✓Grounded answer design includes quick reference views and traceable citations, which is useful for legal, finance, compliance, and internal knowledge workflows where source evidence matters.
✓Hybrid retrieval stack combines vector search, BM25/full-text search, custom scoring, multiple recall, and fused reranking rather than relying only on embeddings.
✓Open-source Apache-2.0 project with substantial GitHub traction, public documentation, Docker-based deployment, APIs, and active release history.
✓Agent capabilities are built into the product direction, including visual workflows, tools, MCP integration, web search, chat channels, agent memory, and code executor support.

👎 Common Concerns

⚠Self-hosting is infrastructure-heavy for casual users: the README lists minimum requirements of 4 CPU cores, 16 GB RAM, 50 GB disk, Docker, Docker Compose, and Python 3.13.
⚠Prebuilt Docker images are documented as x86 only; ARM64 users must build compatible images themselves, and switching Infinity on Linux ARM64 is not officially supported.
⚠The Docker image is now a slim edition that relies on external LLM and embedding services, so teams still need to configure and pay for model providers or run compatible model infrastructure.
⚠The full stack has several moving parts, including document engine configuration, Docker environment files, backend service settings, and storage/search dependencies, which raises operational complexity.
⚠Cloud lower tiers have tight dataset-storage limits, especially the Free tier at 0.1 GB and Starter at 5 GB, which may be too small for realistic enterprise document collections.

Pricing FAQ

Is RAGFlow open source?

Yes. The GitHub repository lists RAGFlow under the Apache-2.0 license. The product also offers a hosted cloud service with Free, Starter, Pro, and Enterprise tiers.

What kinds of data can RAGFlow process?

RAGFlow states support for Word documents, slides, spreadsheets, text files, images, scanned copies, structured data, web pages, and other heterogeneous sources. Its website also describes a built-in ingestion pipeline for cleansing and processing multi-format data.

Does RAGFlow only use vector search?

No. The website describes high-precision hybrid search that combines vector search, BM25, custom scoring, and advanced reranking. The README also mentions multiple recall paired with fused reranking.

Can RAGFlow be self-hosted?

Yes. The README provides Docker Compose and source-development instructions. Documented self-hosting prerequisites include at least 4 CPU cores, 16 GB RAM, 50 GB disk, Docker 24.0.0 or later, Docker Compose v2.26.1 or later, and Python 3.13.

Does RAGFlow support AI agents?

Yes. RAGFlow describes unified AI agent orchestration with RAG, tools, MCPs, visual workflows, web search, chat, models, retrieval, and datasets. Recent listed updates include agentic workflow and MCP, agent memory, and a Python/JavaScript code executor component.

Ready to Get Started?

AI builders and operators use RAGFlow to streamline their workflow.

Try RAGFlow Now →

More about RAGFlow

Review Alternatives Free vs Paid Pros & Cons Worth It?Tutorial

Compare RAGFlow Pricing with Alternatives

GraphRAG Pricing

Microsoft's graph-based retrieval augmented generation for complex document understanding and multi-hop reasoning.

Compare Pricing →

LlamaIndex Pricing

A framework and managed platform for building agents over documents and enterprise data.

Compare Pricing →

Dify Pricing

Dify supports visual ai workflows, knowledge retrieval, agent tools for business ai applications and production llm workflows.

Compare Pricing →

Unstructured Pricing

Unstructured data platform for GenAI that connects to any source, processes 64+ file types, and outputs clean AI-ready inputs.

Compare Pricing →

RAGFlow Pricing & Plans 2026

Complete pricing guide for RAGFlow. Compare all plans, analyze costs, and find the perfect tier for your needs.

🆓Free Tier Available

💎4 Paid Plans

⚡No Setup Fees

Choose Your Plan

Open Source Self-Hosted

Free software license; infrastructure and model costs not included

Start Free →

Free

$0/month

Start Free Trial →

Starter

$29/month shown with a higher $59/month reference price on the site

Start Free Trial →

Pro

$129/month shown with a higher $259/month reference price on the site

Start Free Trial →

Enterprise

Contact sales

Contact Sales →

Pricing sourced from RAGFlow · Last verified March 2026

Is RAGFlow Worth It?

✅ Why Choose RAGFlow

• Strong document-ingestion focus: supports complex unstructured formats as well as Word, slides, spreadsheets, text, images, scanned copies, structured data, and web pages.
• Explainable chunking workflow with template-based chunking options and visualization of text chunks so humans can inspect or intervene before retrieval quality problems become answer quality problems.
• Grounded answer design includes quick reference views and traceable citations, which is useful for legal, finance, compliance, and internal knowledge workflows where source evidence matters.
• Hybrid retrieval stack combines vector search, BM25/full-text search, custom scoring, multiple recall, and fused reranking rather than relying only on embeddings.
• Open-source Apache-2.0 project with substantial GitHub traction, public documentation, Docker-based deployment, APIs, and active release history.
• Agent capabilities are built into the product direction, including visual workflows, tools, MCP integration, web search, chat channels, agent memory, and code executor support.

⚠️ Consider This

• Self-hosting is infrastructure-heavy for casual users: the README lists minimum requirements of 4 CPU cores, 16 GB RAM, 50 GB disk, Docker, Docker Compose, and Python 3.13.
• Prebuilt Docker images are documented as x86 only; ARM64 users must build compatible images themselves, and switching Infinity on Linux ARM64 is not officially supported.
• The Docker image is now a slim edition that relies on external LLM and embedding services, so teams still need to configure and pay for model providers or run compatible model infrastructure.
• The full stack has several moving parts, including document engine configuration, Docker environment files, backend service settings, and storage/search dependencies, which raises operational complexity.
• Cloud lower tiers have tight dataset-storage limits, especially the Free tier at 0.1 GB and Starter at 5 GB, which may be too small for realistic enterprise document collections.

What Users Say About RAGFlow

👍 What Users Love

✓Strong document-ingestion focus: supports complex unstructured formats as well as Word, slides, spreadsheets, text, images, scanned copies, structured data, and web pages.
✓Explainable chunking workflow with template-based chunking options and visualization of text chunks so humans can inspect or intervene before retrieval quality problems become answer quality problems.
✓Grounded answer design includes quick reference views and traceable citations, which is useful for legal, finance, compliance, and internal knowledge workflows where source evidence matters.
✓Hybrid retrieval stack combines vector search, BM25/full-text search, custom scoring, multiple recall, and fused reranking rather than relying only on embeddings.
✓Open-source Apache-2.0 project with substantial GitHub traction, public documentation, Docker-based deployment, APIs, and active release history.
✓Agent capabilities are built into the product direction, including visual workflows, tools, MCP integration, web search, chat channels, agent memory, and code executor support.

👎 Common Concerns

⚠Self-hosting is infrastructure-heavy for casual users: the README lists minimum requirements of 4 CPU cores, 16 GB RAM, 50 GB disk, Docker, Docker Compose, and Python 3.13.
⚠Prebuilt Docker images are documented as x86 only; ARM64 users must build compatible images themselves, and switching Infinity on Linux ARM64 is not officially supported.
⚠The Docker image is now a slim edition that relies on external LLM and embedding services, so teams still need to configure and pay for model providers or run compatible model infrastructure.
⚠The full stack has several moving parts, including document engine configuration, Docker environment files, backend service settings, and storage/search dependencies, which raises operational complexity.
⚠Cloud lower tiers have tight dataset-storage limits, especially the Free tier at 0.1 GB and Starter at 5 GB, which may be too small for realistic enterprise document collections.

Pricing FAQ

Is RAGFlow open source?

Yes. The GitHub repository lists RAGFlow under the Apache-2.0 license. The product also offers a hosted cloud service with Free, Starter, Pro, and Enterprise tiers.

What kinds of data can RAGFlow process?

Does RAGFlow only use vector search?

No. The website describes high-precision hybrid search that combines vector search, BM25, custom scoring, and advanced reranking. The README also mentions multiple recall paired with fused reranking.