Telemetry.dev
Overview
OpenTelemetry-based observability for AI agents, tracing model calls, tools, retrievals, tokens, cost, latency, and errors.
Telemetry.dev is an LLM observability platform for AI applications and agents. It helps teams trace model calls, tool steps, and retrievals with OpenTelemetry, then inspect token usage, estimated cost, latency, errors, inputs, and outputs from instrumented requests. Teams can send data through first-party TypeScript and Python SDKs or an existing OTLP/HTTP exporter.
AI Agent Store research
What the evidence says about Telemetry.dev
Telemetry.dev is a hosted LLM observability platform built around OpenTelemetry. It focuses on tracing AI agent runs, including model calls, tool steps, and retrievals, while normalizing reported token usage, cost, latency, and errors into inspectable traces and metrics.
Verified September 17, 2026
Verified capabilities
- Agent-run tracing
Groups instrumented model calls, tool steps, and retrievals into traces for a request or agent run.[1]
- OpenTelemetry ingest
Accepts traces through first-party TypeScript and Python SDKs or through a standard OTLP/HTTP exporter.[1]
- LLM cost and token monitoring
Tracks reported input, output, cached, and reasoning tokens over time and calculates cost per call when token usage and matching model pricing are available.[1]
- Latency and error inspection
Shows latency, errors, status, and request traces so teams can inspect failed calls, timeouts, and slow requests.[1]
- Grouped metrics
Breaks down cost and latency by attributes such as model, provider, environment, or user when emitted by instrumentation.[1]
- Input and output capture controls
Captures recognized inputs and outputs by default and allows disabling recognized prompt, response, and tool-payload fields per environment before storage.[1]
Where it fits best
- Engineering teams operating LLM applications or AI agents that need traces connecting model calls, tool steps, and retrievals in a request or agent run.[1]
- Teams that want to monitor reported token usage, computed cost, latency, and errors across models, providers, environments, or users.[1]
- Developers who want to send traces through TypeScript or Python SDKs, framework integrations such as Vercel AI SDK and LangChain, or a standard OTLP/HTTP exporter.[1]
Buying and deployment notes
Telemetry.dev offers a Free plan at $0 with no credit card required. The free plan includes 30,000 ingestion units per month, 14-day retention, one project, and two seats.[1]
Platforms: Web app, TypeScript SDK, Python SDK, OTLP/HTTP ingest, Vercel AI SDK integration, LangChain Python integration[1]
Deployment: Cloud-hosted telemetry.dev service, SDK instrumentation, Standard OTLP/HTTP exporter[1]
Important considerations
- The free plan is limited to 30,000 ingestion units per month, 14-day retention, one project, and two seats.[1]
- Computed cost is unavailable when matching model pricing or reported token usage is not available; an explicit span cost takes precedence when provided.[1]
- Prompt and completion capture is on by default. Recognized prompt, response, and tool-payload fields can be disabled per environment before storage, but this does not stop transmission to ingest or remove arbitrary content from logs, errors, or custom attributes.[1]
- Trace detail depends on what the application instrumentation emits, so coverage varies by SDK, provider, framework, and emitted attributes.[1]
Sources and research method (1)
We record only claims tied to public sources checked by our team or listing workflow. Counts above are derived directly from this profile, not a subjective rating.
- LLM Observability & AI Agent Tracing | telemetry.devOfficial site · checked 2026-09-17
Autonomy level
18%
Comparisons
Custom Comparisons
Some of the use cases of Telemetry.dev:
- Tracing AI agent runs across model calls, tools, and retrievals
- Debugging failed or slow LLM requests
- Monitoring token usage, cost, latency, and errors by model, provider, environment, or user
- Sending AI application traces through OpenTelemetry or first-party SDKs
Loading Community Opinions...
Pricing model:
Code access:
Popularity level: 43%
Tags:
Telemetry.dev Video:
Turn this profile into a trust signal
Show prospects that Telemetry.dev has a public place where they can check product details, pricing, ratings, and reviews.
Build confidence
Give buyers a third-party profile to explore.
Reduce hesitation
Put validation beside your strongest CTA.
Earn discovery
Every badge links prospects to your listing.
Choose your style
Preview it, then copy the complete embed code.
Shows buyers where to validate your product, pricing, and reputation.
Plain HTML. No signup, script, or maintenance required.
Describe the job. Get an AI worker you can actually message.
We create the setup, keep it running after your laptop closes, and save its memory. Test in the browser, then add Telegram, WhatsApp, or Slack.
Plans start at $29/month. Cancel anytime.
Hosted agent
OpenClaw or Hermes