Pricing that tracks real volume

Currai is an LLM observability and evaluation platform. It traces every prompt, token, and tool call your app makes so you can debug, measure, and ship with confidence — full traces, token usage, and cost in one view. It also supports LLM evals, prompt A/B testing, and OpenTelemetry/Langfuse-compatible ingestion.

Yes. Beyond LLM observability, Currai is an AI evaluation platform: run LLM-as-a-judge and heuristic evals with your own evaluation metrics, A/B test and regression-test prompts, and score agent evaluation and multi-turn conversation testing on real production traces. Build golden datasets from those traces and wire evals into CI/CD to catch hallucinations and quality regressions before they ship.

Currai is an AI observability and LLM monitoring platform for production. You get LLM tracing across every prompt, token, and tool call, plus AI quality monitoring, hallucination detection, prompt drift detection, and latency and cost tracking — rolled up per trace, model, session, and user so you can watch quality and spend on live traffic.

About five minutes. Install the SDK with pip install currai or npm i currai, paste your public / secret key pair, and wrap a single LLM call. There's no agent to deploy and no collector to run — the first request you make shows up in the dashboard right away.

Currai ships first-class Python and TypeScript SDKs, and it's byte-compatible with the Langfuse SDKs and OpenTelemetry. If you're already instrumented, you migrate by changing a single host line — your existing trace code, spans, and exporters keep working.

Currai is an option for teams comparing Langfuse alternatives, Braintrust alternatives, or DeepEval alternatives for hosted LLM observability, production traces, evals, prompt A/B tests, token cost tracking, and OpenTelemetry-compatible ingestion. Test your exact workflow before switching.

No. Traces are batched and flushed in the background, so instrumentation never blocks a request. In short-lived processes you call flush() (or flush_async()) before exit to make sure everything is sent.

Usage is billed on the data Currai actually processes — measured in processed bytes — not on a flat per-trace fee. Large traces and tiny traces are priced for what they are, so your cost tracks real volume instead of row counts.

Retention follows your plan, so you keep traces for as long as your plan's window allows. You can export or delete your data on demand at any time.

None. Currai hosts ingestion, columnar storage, and dashboards for you — there's no ClickHouse to babysit. It scales with your traffic so you watch data, not infrastructure.