LiteLLM vs DeepEval / Confident AI
Facts come from each vendor's own pages; download numbers are the headline package of each tool in 2026-W40.
| Fact | LiteLLM | DeepEval / Confident AI |
|---|---|---|
| PyPI downloads, week (rank) | 22,710,323 (#1)litellm | 686,214 (#10)deepeval |
| npm downloads, week (rank) | no npm SDK | SDK not mapped |
| GitHub stars (rank) | 60,298 (#1)BerriAI/litellm | 18,682 (#7)confident-ai/deepeval |
| PyPI series (12 weeks) | ||
| npm series (12 weeks) | no npm SDK | no npm SDK |
| Categories | Gateways with observability | Evaluation, Tracing & observability, Prompt management |
| Status | Generally available | Generally available |
| Licence | MIT (open core) | Apache-2.0 (open core) |
| Self-host | Yes | Enterprise only |
| OpenTelemetry | Exporter / bridge | Native (OTLP) |
| Pricing model | contact | flat |
| Entry price | Contact sales; Open Source $0 self-hosted; Enterprise is annual, sized to usage, price not published ('Talk to sales') | $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. |
| Free tier | Yes | Yes |
| Measurability | Measured (mapped SDK packages) | Measured (mapped SDK packages) |
| Sources | pricing · licence · self-host · OTel (checked 2026-10-07) | pricing · licence · self-host · OTel (checked 2026-10-07) |
More downloads means more package installs (including CI and dependencies), not a better product. See the methodology.