Braintrust

A hosted observability, evaluation and gateway platform for LLM applications, offering multi-step agent tracing, LLM-as-a-judge and custom scorers, regression testing in CI and production monitoring.

Website

https://www.braintrust.dev/

Who it's for

Evaluation-driven teams that want unified tracing and evals across development and production.

Pricing

Starter $0/mo (1 GB processed data, 10k scores, 14-day retention, unlimited users); Pro $249/mo (5 GB, 50k scores, 30-day retention); Enterprise custom. Overage billed per GB and per 1k scores.

Category

Agent operations

Last verified

2026-10-22 (current)

Confidence

high

Key facts

• Closed-source hosted platform; some client libraries and scorers are open source
• Combines tracing, evaluation, datasets, experiments and an AI gateway
• Evals run in CI or continuously on production traffic
• 25+ built-in scorers; a built-in agent generates custom scorers from descriptions
• No per-seat charges - unlimited users on all tiers

Sources

Every claim above is drawn from these; we do not publish unsourced specifications.

• https://www.braintrust.dev/pricing
• https://www.braintrust.dev/docs/plans-and-limits

Something changed or out of date? Tell us — corrections are how this stays worth reading.