René's URL Explorer Experiment

{"@context":"https://schema.org","@graph":[{"@type":"WebPage","@id":"https://telemetry.dev/#webpage","url":"https://telemetry.dev/","name":"LLM observability for AI agents","description":"Trace LLM calls and AI agents with OpenTelemetry. Inspect token usage, cost, latency, and errors with TypeScript, Python, or an existing OTLP integration.","isPartOf":{"@type":"WebSite","@id":"https://telemetry.dev/#website","name":"telemetry.dev","url":"https://telemetry.dev/"},"publisher":{"@type":"Organization","@id":"https://telemetry.dev/#organization","name":"telemetry.dev","url":"https://telemetry.dev/"}},{"@type":"Organization","@id":"https://telemetry.dev/#organization","name":"telemetry.dev","url":"https://telemetry.dev/","logo":"https://telemetry.dev/logo512.png","sameAs":["https://github.com/telemetry-dev","https://www.npmjs.com/package/@telemetry-dev/sdk","https://pypi.org/project/telemetry-dev/"],"contactPoint":{"@type":"ContactPoint","contactType":"customer support","email":"support@telemetry.dev","availableLanguage":["en"]},"address":{"@type":"PostalAddress","streetAddress":"2261 Market Street, #5211","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94114","addressCountry":"US"}},{"@type":"WebSite","@id":"https://telemetry.dev/#website","name":"telemetry.dev","url":"https://telemetry.dev/","publisher":{"@id":"https://telemetry.dev/#organization"}},{"@type":"SoftwareApplication","@id":"https://telemetry.dev/#software","name":"telemetry.dev","url":"https://telemetry.dev/","applicationCategory":"DeveloperApplication","operatingSystem":"Web","description":"Trace LLM calls and AI agents with OpenTelemetry. Inspect token usage, cost, latency, and errors with TypeScript, Python, or an existing OTLP integration.","offers":[{"@type":"Offer","name":"Free","price":"0","priceCurrency":"USD"}],"publisher":{"@id":"https://telemetry.dev/#organization"}},{"@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What is telemetry.dev?","acceptedAnswer":{"@type":"Answer","text":"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."}},{"@type":"Question","name":"How do I start sending traces?","acceptedAnswer":{"@type":"Answer","text":"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."}},{"@type":"Question","name":"Which frameworks and languages are supported?","acceptedAnswer":{"@type":"Answer","text":"TypeScript and Python have first-party SDKs, with integrations for providers and frameworks such as OpenAI, Anthropic, and Vercel AI SDK. The Claude SDK and the Claude API can also send their native OpenTelemetry spans to telemetry.dev. Other languages can send standard OTLP over HTTP. Trace detail depends on what your instrumentation emits, so each integration guide describes its coverage."}},{"@type":"Question","name":"How is cost calculated?","acceptedAnswer":{"@type":"Answer","text":"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."}},{"@type":"Question","name":"Is the free plan actually free?","acceptedAnswer":{"@type":"Answer","text":"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."}},{"@type":"Question","name":"Can I keep prompts and completions out of storage?","acceptedAnswer":{"@type":"Answer","text":"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. Capture settings cover telemetry only, not experiment outputs, dataset items, or saved prompt versions."}}]}]}