Ship AI agents faster,
with confidence

Free: Best for individuals and smaller teams getting started with tracing, experiments, evals, and prompt iteration.

Pro: Best for teams running in production and includes additional LLM span volume, predictable on demand pricing, and retention add ons.

Each call to an LLM provider like OpenAI or Anthropic is captured as its own LLM span. One agent run can create multiple LLM spans inside the same workflow.

LLM Observability meters and bills only on the count of LLM spans. Tool spans, embedding and retrieval spans, and agent spans are not billed.

That means pricing scales better as your context window grows and your agent becomes more complex and autonomous.

Instrument your LLM application with an SDK for Python or Node, or submit spans through an API if your application is written in another language.

If you use orchestration frameworks like LangChain and popular LLM providers, auto instrumentation can capture traces for you.

View instrumentation docs

There is no separate product fee for offline or online evaluations. Every plan includes the full evaluation workflow.

If an eval run makes LLM calls, those calls count as LLM spans. You are not charged a separate eval fee on top of that.

On-demand Free and Pro plans have a 15-day trace, span and experiment data retention. When committing to M2M or Annual contracts, trace and span data are retained for 15 days. Experiment results are retained for 90 days.

Retention add-ons extend traces and spans to 30, 60, or 90 days and extend experiments to 6, 9, or 12 months.

Datasets have a separate 3-year retention and are versioned so you can rerun experiments against the same baseline and compare results over time.

Yes. LLM Observability scans, identifies, and redacts sensitive information in your LLM application by using Sensitive Data Scanner.

This helps prevent data leakage across personal information, financial data, health records, and other sensitive content that needs protection.

You do not need to buy SDS separately for LLM Observability. For every 10K LLM requests, you get an allocation of 1 GB of Sensitive Data Scanner.

Free includes up to 40K LLM spans per month. Pro starts at $240 per month and includes 100K LLM spans.

Additional on demand usage is billed after the first 100K LLM spans. Retention add ons are billed per 10K LLM spans. M2M and annual commitments are discounted.