Open-source framework

Ragas: pricing and features

by Ragas maintainers (repo now at vibrantlabsai/ragas)

Prices and features checked 2026-10-17 on the vendor's own pages. Anything we could not confirm says “not verified”.

What is Ragas? Open-source Python library of LLM-judged metrics for RAG pipelines and agents (faithfulness, context precision and recall, and more). It has no hosted plan; results usually go to another platform.

Best for: Teams that need RAG and agent metrics as a Python library inside their own pipeline or another platform.

Pricing

Free tier
Free, open source [source, checked 2026-10-17]
Entry paid price
No paid plan published [source, checked 2026-10-17]
What you pay for (meter)
No hosted plan published; metrics call a judge model you configure [source]
Licence
Apache-2.0 [source]
Self-hosting
A library you install and run yourself [source]
Data retention
not verified

Prices are list prices in USD as shown on the vendor page on the checked date. Vendors change plans often; follow the source link before you buy.

Features

OpenTelemetrynot verified
CI gatingAdd to a CI pipeline with pytest [source]
LLM-as-judgeLLM-judged metrics are the core of the library [source]
Human annotationnot verified
Prompt managementnot verified
Dataset versioningnot verified
SOC 2 / HIPAAnot verified

“not verified” means we did not find it on a vendor page; it may still exist. Corrections with a source link are welcome via the submit form.

More on Ragas

Our directory entry covers what Ragas tests, its licence and how to run it: Ragas on Evals Review.

Vendors: want a labelled featured slot on tool pages like this one? Sponsorships are always marked “Sponsored” and never change table order, verdicts or facts. See placements and how to book.

Sources

Last checked 2026-10-17. Data: tools.json · tools.csv (CC BY 4.0). Canonical: https://evalsreview.com/tools/ragas