DeepEval / Confident AI

Pytest-style Python framework for testing LLM apps, paired with a hosted platform for shared test runs and tracing.

By Confident AI · deepeval.com

Package download activity

Each package is shown on its own; packages that can be installed together are never added up. Week 2026-W40 (2026-09-28 to 2026-10-04).

PyPIdeepeval · headline (ranked)

686,214 downloads in the week, +9.7% vs prior week · rank 10 on PyPI

2026-W29 to 2026-W40, 12 weeks; min 554,926, max 1,659,352

Reproduce this number (ClickHouse SQL) · registry metadata (mapping checked 2026-10-07)

Packages not measured

The vendor's docs name these packages, but their registry metadata does not link the vendor's domain or GitHub organisation, so under our mapping rule they are not counted. No download number is shown for them.

PyPI confident-trace: registry metadata has no project/repository/homepage link (registry metadata, checked 2026-10-07)
npm confident-trace: registry metadata has no project/repository/homepage link (registry metadata, checked 2026-10-07)

GitHub stars

confident-ai/deepeval: 18,682 stars (rank 7). Stars are a point-in-time count of a repository's bookmarks, not people using the tool.

Series starts 2026-W40 (18,682).

Reproduce (GitHub API) · repository link source

Facts

Facts for DeepEval / Confident AI
Categories	Evaluation, Tracing & observability, Prompt management
Status	Generally available
Licence	Apache-2.0 (open core)	source, checked 2026-10-07
Self-host	Enterprise only	source, checked 2026-10-07
OpenTelemetry	Native (OTLP)	source, checked 2026-10-07
Pricing model	flat
Entry price	$200/mo; Confident AI platform: Free $0 forever (2 seats, 1 project, 1 GB-month traces); Starter $200/month (5 GB-months traces, then $1 per GB-month); Team $2,000/month; Enterprise custom. DeepEval library itself is free/open source.	source, checked 2026-10-07
Free tier	Yes
Measurability	Measured (mapped SDK packages)

Facts last verified 2026-10-07 on first-party pages. Prices as published, taxes excluded; non-USD prices are not converted.

Compare

Spotted an outdated fact? The methodology page explains how facts are checked; corrections are applied at the next weekly build.