Deepchecks LLM Evaluation
Platform for testing, validating and monitoring LLM and agent applications, with automated evaluators, version comparison and continuous production monitoring.
Find alternatives to Deepchecks LLM Evaluation
No public prices. Basic and Scale tiers require a demo/contact request, Enterprise is custom; deepchecks.com/pricing/ names seats, DPUs/month and data retention per tier but no dollar figure for any.
What it does
- Evaluation and observability
Sources
- Pricing
-
Four options read live: Basic (free trial, 3 seats, 1 AI application, 5K DPUs/month, 3-month retention), Scale (demo required, 5 seats, 3 applications, 20K DPUs/month), Enterprise (custom), plus Deepchecks on SageMaker AI and Deepchecks Dedicated for on-prem/bare-metal. No dollar figure named on any tier.
- Description
-
Official documentation · 9 Sep 2026
Fetched 2026-09-09: feature list names Agents, Evaluators, Version Comparison, Auto-Scoring.
- Sold within
-
Bought and metered on its own pricing page -- no parent offering it ships inside.
- URL
-
Official documentation · 9 Sep 2026
Product page, linked from the homepage's own "Try LLM Evaluation" call to action.
- Deployment
-
Cloud-hosted tiers (Basic/Scale/Enterprise) are SaaS; "Deepchecks on Sagemaker AI" names AWS-managed with on-premises data locality; "Deepchecks Dedicated" names single-tenant, on-prem and bare-metal options explicitly.
Also from Deepchecks
-
Deepchecks ML Testing Developer tool
Open-source Python package that runs pre-built suites of checks over machine-learning data and models -- data integrity, train/test distribution mismatch and model performance -- in a research notebook or in CI/CD.
Open Deepchecks in the directory
Something wrong here? Send a correction — quote this product id: deepchecks-llm-evaluation.