LLM observability for AI agents
Trace model calls, tool steps, and retrievals with OpenTelemetry. Inspect token usage, cost, latency, and errors from your instrumentation. Connect your AI application with our SDKs or an existing OTLP exporter.
Free plan: 30,000 ingestion units a month, one per span, log record, or metric data point. No credit card required. Read the tracing setup guide.
When something breaks, you'll know why
Inspect a slow request or compare spend across models with traces and metrics.
Volume, cost, p95, errors
The four numbers you actually check, split by model, provider, and environment.
Inspect failed calls and timeouts
Find the error type and status alongside the request trace, when your instrumentation reports them.
Success rate
98%chat.completion · gpt-5.5 · 1,204 tok · $0.004
retrieval · pinecone · 8 docs · 120ms
tool · get_invoice · running
User message
LLM call · 820ms
Response streamed
Inputs and outputs, on your terms
Capture is on by default. Disable recognized input and output fields per environment before storage. Redaction patterns do not catch all sensitive data.
Find the trace behind a failure
Search by name or filter by status, environment, framework, or session to inspect an individual trace.
Send traces from anywhere
Drop in our SDK, or point any OpenTelemetry exporter at our endpoint. Any framework, any language, no lock-in.
Any framework. Any language. One endpoint.
However you added AI to your app, you can send its OTLP traces here. We normalize supported fields into a consistent view of spans, tokens, and cost.
- Connected
Vercel AI SDK
TypeScript · generateText, streamText
- Connected
LangChain
Python · agents, RAG, tools
- Connect
OpenTelemetry
Any language · OTLP/HTTP
Tokens (30d)
4.2M
Cost (30d)
$1.2K
p95 latency
1.8s
By model
By provider
By environment
Frequently Asked Questions
What is telemetry.dev?
telemetry.dev is an LLM observability platform for AI applications and agents, built on OpenTelemetry. A trace groups the instrumented model calls, tool steps, and retrievals in a request or agent run. Reported token usage, cost, latency, and errors help you debug failures and monitor spend.
How do I start sending traces?
Make a project API key, then configure a telemetry.dev integration or an OTLP/HTTP exporter. Run an instrumented request and open its trace in your project. The developer guide links to setup instructions for each SDK, provider, and framework.
Which frameworks and languages are supported?
TypeScript and Python have first-party SDKs, with integrations for providers and frameworks such as OpenAI, Anthropic, and Vercel AI SDK. Other languages can send standard OTLP over HTTP. Trace detail depends on what your instrumentation emits, so each integration guide describes its coverage.
How is cost calculated?
telemetry.dev calculates cost at ingest from reported token usage and its model-pricing catalog. Cache-read and cache-write tokens use separate rates when available. Reasoning tokens are not charged separately. An explicit span cost takes precedence. Without matching model pricing or token usage, computed cost is unavailable.
Is the free plan actually free?
Yes. The Free plan costs $0 and requires no credit card. It includes 30,000 ingestion units per month, 14-day retention, one project, and two seats. Each normalized span, OTLP log record, or metric data point uses one ingestion unit.
Can I keep prompts and completions out of storage?
Yes, for recognized prompt, response, and tool-payload fields. Capture is on by default, and you can disable it per environment before storage. This does not stop transmission to ingest or remove arbitrary content from logs, errors, or custom attributes. Built-in and project-specific redaction patterns apply, but pattern matching cannot catch all sensitive data. To prevent transmission, remove sensitive content in your instrumentation before export.
Trace your next AI request
Choose an integration, add your project API key, and run an instrumented request.
Free plan includes 30,000 ingestion units a month, one per span, log record, or metric data point. No credit card required.