LLM observability for AI agents
Follow model calls, tool steps, and retrievals in one trace. Find failures, inspect latency, and track token usage and cost. Connect with our SDKs or your existing OpenTelemetry exporter.
Free plan: 30,000 ingestion units a month, one per span, log record, or metric data point. No credit card required. Read the quickstart.
Find the slow step. Inspect the failed call.
Pinpoint a tool timeout, inspect a model response, and see where your budget goes.
Keep cost and reliability in view
Compare spend, latency, and errors 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.
Invoice lookup timed out
invoice_assistant · production
Error · 5.94s- retrieval120ms
8 documents retrieved
- chat.completion820ms
1,204 tokens · tool call requested
- get_invoice5.00s
TimeoutError
Invoice API did not respond within 5 seconds.
Control what gets stored
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.
Failed requests
invoice_assistant
TimeoutError5.94sanswer_question
RateLimitError240ms
Connect your application
Choose a setup guide for your provider or framework, or use your existing OTLP/HTTP exporter.
From your first trace to your next fix
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.
Answer with retrieved context
answer_question · TypeScript SDK
Completed in 1.24s
- search_docs180ms
6 matching documents
- chat.completion1.06s
2,184 input · 286 output tokens
Model and retrieval spans, connected in one request.
Usage · last 30 days
Tokens (30d)
4.2M
Cost (30d)
$1.2K
p95 latency
1.8s
Last 30 days
Spend by provider
$1,248.00 estimated cost
Costs depend on reported token usage and available model pricing.
Start building
Send your first trace, or go straight to the guide for the stack you already use.
- Open
Quickstart
Send your first trace with TypeScript or Python in five minutes.
- Open
Find your integration
Choose the guide for your provider, framework, coding agent, or SDK.
- Open
TypeScript SDK
Record functions, model calls, tools, and agents from Node and edge runtimes.
- Open
Python SDK
Record sync and async Python code with decorators and context managers.
- Open
OpenTelemetry
Keep your existing instrumentation and export standard OTLP/HTTP.
- Open
OTLP ingest API
Send traces, logs, and metrics from any OpenTelemetry exporter or collector.
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 integration directory 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.