How much does PandasAI cost?

The core library is free and open-source under the MIT license. Sinaptik offers a freemium model with Basic at $10, Pro at $30, and Enterprise plans available via sales contact for managed cloud or self-hosted editions.

Which LLMs can I use with PandasAI?

PandasAI uses a multi-model approach via LiteLLM. You can connect to OpenAI, Anthropic, local Ollama models, or any other provider supported by LiteLLM, allowing you to swap models as needed for your data analysis tasks.

Is PandasAI secure for running generated code?

Yes, it wraps the LLM in a code-execution sandbox. Generated code runs in an isolated Docker environment, preventing it from escaping into your host environment. This is a key differentiator over rolling your own LangChain agents.

What are the system requirements for PandasAI?

PandasAI is a Python library requiring versions 3.8 through 3.11. It is designed for Python environments and is not suitable if you are not working in Python or need a polished no-code BI dashboard out of the box.

What data sources does PandasAI support?

It supports querying CSVs, parquet files, SQL warehouses, and pandas DataFrames. Version 3 adds support for multi-dataframe joins and semantic layers, allowing you to ask questions in plain English and receive dataframes, charts, or summaries.

PandasAI

Conversational data analysis library that turns natural-language questions into pandas, SQL and chart code.

Freemium· Basic: $10 · Pro: $30 · Enterprise: Contact salesCodingMulti-model (via LiteLLM)7.1 / 10

Visit website →

In short

PandasAI is an open-source Python library that converts natural language into pandas, SQL, and chart code. It runs in a secure Docker sandbox and supports multiple LLMs via LiteLLM.

Best for

Pick PandasAI if you want a battle-tested OSS layer for 'chat with your dataframe' that you can self-host and point at any LLM.

Skip if

Skip it if you need a polished no-code BI dashboard out of the box or aren't working in Python.

PandasAI is an open-source Python library (MIT-licensed) that lets you query CSVs, parquet files, SQL warehouses and pandas DataFrames in plain English. It wraps an LLM around a code-execution sandbox so a prompt like 'plot revenue by region for Q3' becomes real pandas/matplotlib code, runs it in an isolated Docker environment, and returns the dataframe, chart or summary. v3 supports multi-dataframe joins, semantic layers, and a LiteLLM backend so you can swap between OpenAI, Anthropic, local Ollama models or anything else LiteLLM supports.

It's aimed at two crowds: data analysts who want to skip boilerplate ('describe this dataset', 'find outliers'), and product teams embedding a chat-with-your-data feature without building the agent loop from scratch. The core library is free; the company behind it (Sinaptik) sells a managed cloud dashboard and a self-hosted enterprise edition (separate license, sales-led) that adds a BI-style UI, user management, and governed connectors on top of the OSS engine.

The Docker sandbox is the meaningful differentiator over rolling your own LangChain pandas agent — generated code can't escape into your host environment. Caveats: it's Python 3.8-3.11 only, results are only as good as the underlying LLM, and the 'AI Dashboard' marketing site is much thinner than the GitHub repo, which is where the real documentation lives.

Editor's take

One of the few natural-language-to-pandas projects that survived the 2023 hype cycle and matured. The sandboxed execution model is the right call, and the LiteLLM pivot in v3 means you're not locked into OpenAI. Treat the .com as a sales front and live in the GitHub repo.

— The AI Tool Bible editorial team

Pros

✅ MIT-licensed core with 23k+ GitHub stars and active releases
✅ LiteLLM backend means you pick the model (OpenAI, Anthropic, local)
✅ Docker sandbox isolates generated code execution
✅ Handles CSV, parquet, SQL and multi-dataframe joins out of the box

Cons

⚠️ Marketing site is sparse; real docs live in the GitHub repo
⚠️ Python 3.8-3.11 only; no Node/other-language SDK
⚠️ Enterprise/cloud pricing is opaque (contact sales)
⚠️ Output quality is bounded by the LLM you wire in

Use cases

data-analysisnatural-language-sqlchart-generationbusiness-intelligencedataframe-querying

Frequently asked

How much does PandasAI cost?: The core library is free and open-source under the MIT license. Sinaptik offers a freemium model with Basic at $10, Pro at $30, and Enterprise plans available via sales contact for managed cloud or self-hosted editions.
Which LLMs can I use with PandasAI?: PandasAI uses a multi-model approach via LiteLLM. You can connect to OpenAI, Anthropic, local Ollama models, or any other provider supported by LiteLLM, allowing you to swap models as needed for your data analysis tasks.
Is PandasAI secure for running generated code?: Yes, it wraps the LLM in a code-execution sandbox. Generated code runs in an isolated Docker environment, preventing it from escaping into your host environment. This is a key differentiator over rolling your own LangChain agents.
What are the system requirements for PandasAI?: PandasAI is a Python library requiring versions 3.8 through 3.11. It is designed for Python environments and is not suitable if you are not working in Python or need a polished no-code BI dashboard out of the box.
What data sources does PandasAI support?: It supports querying CSVs, parquet files, SQL warehouses, and pandas DataFrames. Version 3 adds support for multi-dataframe joins and semantic layers, allowing you to ask questions in plain English and receive dataframes, charts, or summaries.