Home / Code · Agents / telemetry.dev
telemetry.dev
For monitoring LLMs and agents: tracks cost and latency with OpenTelemetry-based tracing
What is telemetry.dev
telemetry.dev monitors LLM applications and agents, tracking cost and latency with tracing built on OpenTelemetry (OTel). The free plan includes 30,000 units with 14-day retention; Pro costs $25/month and Team $50/month.
How to use
- Sign up for free at telemetry.dev (no credit card required) and create a project.
- Create a project API key.
- Connect your app with the TypeScript SDK (@telemetry-dev/openai, @telemetry-dev/ai-sdk), the Python SDK (telemetry-dev), or your existing OTLP/HTTP OpenTelemetry exporter;
- or copy the setup prompt for your coding agent.
- Run an instrumented request and open its trace in your project.
- Inspect model calls, tool steps, retrievals, latency, tokens and cost;
- filter traces and view MCP analytics.
- Set up email alerts for cost, budgets, agent loops and errors, and manage prompts and evals.
Use cases
- Tracing LLM agent runs across model calls, tool steps and retrievals Finding slow steps and failed tool or model calls Tracking token usage, spend and latency by model, provider and environment Monitoring MCP server methods, tools and failures Getting alerts on cost spikes, budget overruns, agent loops and errors Managing prompt versions and tracing eval runs
FAQ
What counts as an ingestion unit?
One normalized span, OTLP log record, or metric data point counts as one ingestion unit. A trace containing five spans uses five units. Logs derived from span events and metric updates applied to existing spans do not add units.
What happens if I reach the Free limit?
Free includes 30,000 ingestion units per month, with 20% headroom. We reject an ingestion request if accepting it would bring your workspace's monthly total above 36,000 units. To resume ingestion, upgrade or wait for your allowance to reset at 00:00 UTC on the first day of the next calendar month.
What happens if I exceed my paid allowance?
Pro includes 500,000 units per month; Team includes 2 million. Ingestion continues above these amounts, with no automatic overage charges. If your usage consistently exceeds your allowance, we'll contact you to discuss a suitable plan. Usage resets at 00:00 UTC on the first day of each calendar month, independently of your billing date.
How do seats and projects work?
A seat is a member of your workspace, and every member sees every project in it. Owners and admins manage API keys and settings. When you need more seats or projects, move up a plan.
Is the Free plan actually free?
Yes, with no credit card. You get 30,000 ingestion units a month — one per span, log record, or metric data point — plus 14-day retention, one project, and two seats. Upgrade only when your volume outgrows it.
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. 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.
Can I change plans or cancel anytime?
Yes. Upgrade, downgrade, or cancel whenever you need to, billed per workspace. No contracts, no cancellation penalties.
Price from official sources
Freemium
- Prices are per workspace, per month.
- Free:$0 — 30k ingestion units/month, 14-day retention, 1 project, 2 seats.
- Pro:$25/month — 500k ingestion units/month (no automatic overage charges), 30-day retention, 5 projects, 5 seats.
- Team:$50/month — 2M ingestion units/month, 90-day retention, unlimited projects and seats, priority support.
Check the official site for current pricing · Price not yet checked by our editors
Source: telemetry.dev · Info as of Nov 2, 2026
Company
Reviews
No reviews yet.
Alternatives
-
sweet-search
Free
For agents searching codebases: local semantic search that saves 5–33% per agent run
- Added
- Nov 2, 2026
Same category: Code
-
nonce Not stated For securely granting AI access to your email: issues time-limited, least-privilege access per question
- Added
- Nov 2, 2026
Same category: Code
-
Skep Free For collaborating with coding agents across devices: share live sessions with a join code
- Added
- Nov 2, 2026
Same category: Code
-
Rufous
Free
For coding with small local models: an agent framework built for 2B–12B models
- Added
- Nov 2, 2026
Same category: Code
Social