OpenTelemetry LLM tracing
Send OpenTelemetry LLM traces to PromptLayer. Native OTLP/HTTP endpoint with GenAI semantic conventions — works with any OTel-instrumented AI framework.
Trace every OpenTelemetry run
Full span traces
See the complete execution tree of every OpenTelemetry run — nested spans, tool calls, and LLM requests on one timeline.
Cost & latency analytics
Track token usage, cost, and latency for every OpenTelemetry call, broken down by model, prompt, or metadata.
Rich metadata & search
Tag, score, and search every request. Filter production traffic by content, model, status, or custom key-value pairs.
OpenTelemetry-native
OpenTelemetry streams traces straight to PromptLayer's OTLP endpoint — no proxy in your request path, no SDK rewrite.
Debug in the playground
Open any OpenTelemetry trace in the Playground to reproduce, tweak, and fix the exact prompt that failed.
Turn traces into evals
Promote real OpenTelemetry runs into versioned datasets and run evaluation pipelines to catch regressions.
Understand what your OpenTelemetry app is doing
OpenTelemetry is the open standard for tracing. PromptLayer speaks it natively, so any instrumented app can stream traces with no proprietary SDK.
See the full picture
Every OpenTelemetry run becomes a searchable, replayable trace — inputs, outputs, models, and timing.
Find the bottleneck
Pinpoint the slow span or expensive model call dragging down your OpenTelemetry pipeline.
Catch failures fast
Surface errors, failed tool calls, and low-quality outputs before your users do.
Ship with confidence
Connect traces to evaluation pipelines so every change to your OpenTelemetry app is tested.
Frequently asked questions
If you still have questions feel free to contact us at sales@promptlayer.com