Vercel AI SDK tracing
Trace Vercel AI SDK calls — generateText, streamText, tool calls, and reasoning — in PromptLayer. OpenTelemetry native, no proxy.
Trace every Vercel AI SDK run
Full span traces
See the complete execution tree of every Vercel AI SDK run — nested spans, tool calls, and LLM requests on one timeline.
Cost & latency analytics
Track token usage, cost, and latency for every Vercel AI SDK 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
Vercel AI SDK streams traces straight to PromptLayer's OTLP endpoint — no proxy in your request path, no SDK rewrite.
Debug in the playground
Open any Vercel AI SDK trace in the Playground to reproduce, tweak, and fix the exact prompt that failed.
Turn traces into evals
Promote real Vercel AI SDK runs into versioned datasets and run evaluation pipelines to catch regressions.
Understand what your Vercel AI SDK app is doing
The Vercel AI SDK powers streaming, tool-calling AI apps. PromptLayer captures each generateText and streamText call as a replayable trace.
See the full picture
Every Vercel AI SDK 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 Vercel AI SDK 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 Vercel AI SDK app is tested.
Frequently asked questions
If you still have questions feel free to contact us at sales@promptlayer.com