Braintrust: pricing and features
by Braintrust Data
Prices and features checked 2026-10-17 on the vendor's own pages. Anything we could not confirm says “not verified”.
What is Braintrust? Hosted platform for evaluation, tracing and prompt iteration, with LLM-as-judge and code scorers, human review, datasets and a CI runner. Pricing combines a platform fee, processed data and scores.
Best for: Product and engineering teams that run many experiments and want evals, human review and prompt playgrounds in one hosted tool.
Pricing
- Free tier
- Starter $0: 1 GB processed data, 10k scores, 14-day retention, unlimited users; then $4/GB and $2.50 per 1k scores [source, checked 2026-10-17]
- Entry paid price
- Pro $249/month: 5 GB and 50k scores included, then $3/GB and $1.50 per 1k scores; 30-day retention [source, checked 2026-10-17]
- What you pay for (meter)
- Processed data (GB) plus scores, plus model credits at token rates [source]
- Licence
- Hosted service; its autoevals scorer library is MIT [source]
- Self-hosting
- Self-hosted data plane; on-prem or hosted deployment on Enterprise [source]
- Data retention
- 14 days (Starter), 30 days (Pro), up to 180 days at $0.50/GB/month [source]
Features
| OpenTelemetry | Accepts OpenTelemetry traces and logs [source] |
|---|---|
| CI gating | GitHub Actions or the bt eval CLI [source] |
| LLM-as-judge | LLM-as-a-judge and code scorers [source] |
| Human annotation | Human review scores on traces and experiments [source] |
| Prompt management | Prompt version history, restore and compare [source] |
| Dataset versioning | Pin dataset versions with snapshots [source] |
| SOC 2 / HIPAA | SOC 2 Type II listed; BAA for HIPAA on Enterprise [source] |
Compare
- All 12 LLM evaluation platforms compared
- Braintrust vs Langfuse
- Braintrust vs LangSmith
- Langfuse alternatives
- LangSmith alternatives
- Braintrust alternatives
- Arize AX and Phoenix alternatives
- Pricing calculator · LLM observability tools
Other tools: Langfuse · LangSmith · Arize AX and Phoenix · Promptfoo · DeepEval and Confident AI · Galileo (Splunk Agent Observability) · Maxim AI · Helicone · Comet Opik · W&B Weave · Ragas
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.