Free tool · #3

OTel GenAI Trace Validator

Check an OpenTelemetry span against the gen_ai.* semantic conventions — what conforms, what is missing, what is deprecated.

OTel span or OTLP trace (JSON)

Validated in your browser — nothing is sent anywhere.

Result — chat gpt-4o

3/3 required · 2 deprecated · 6/7 recommended

conformant

gen_ai.usage.output_tokensCompletion tokens — required to compute output cost.
gen_ai.systemRenamed to the provider namespace. Use gen_ai.provider.name instead.openai
gen_ai.usage.completion_tokensThe old name predates the stable usage namespace. Use gen_ai.usage.output_tokens instead.340
gen_ai.operation.nameThe operation performed — sets what the span means (chat, embeddings, …).chat
gen_ai.provider.nameWhich provider served the call — needed to attribute cost and latency.openai
gen_ai.request.max_tokensThe requested output-token cap.1024
gen_ai.request.modelThe requested model. Without it, a trace cannot be priced.gpt-4o
gen_ai.request.temperatureSampling temperature.0.7
gen_ai.response.finish_reasonsWhy generation stopped — an array of strings.[stop]
gen_ai.response.idThe provider response id, for correlation.chatcmpl-abc123
gen_ai.response.modelThe model that actually served the request (can differ from the requested one).gpt-4o-2026-05-01
gen_ai.usage.input_tokensPrompt tokens — required to compute input cost.1200

Modernized attributes (deprecated names replaced)

{
  "gen_ai.operation.name": "chat",
  "gen_ai.provider.name": "openai",
  "gen_ai.request.model": "gpt-4o",
  "gen_ai.request.temperature": 0.7,
  "gen_ai.request.max_tokens": 1024,
  "gen_ai.response.model": "gpt-4o-2026-05-01",
  "gen_ai.response.id": "chatcmpl-abc123",
  "gen_ai.response.finish_reasons": [
    "stop"
  ],
  "gen_ai.usage.input_tokens": 1200,
  "gen_ai.usage.output_tokens": 340
}

Use this tool from code — or hand it to your agentagent prompt · REST · MCP

Hand this tool to your coding agent

Paste into Claude Code, Cursor, Codex, or any agent. It learns to call this tool over REST or MCP, reaches for it when you ask, and keeps our sourced/pending labels honest.

You can use telemeter.ai's free "OTel GenAI Trace Validator" — a keyless, read-only tool (no signup), available as an HTTP API and an MCP tool. What it does: Check an OpenTelemetry span against the gen_ai.* semantic conventions — what conforms, what is missing, what is deprecated.

Whenever I ask you something this tool answers, call it and use its result instead of estimating yourself.

REST:
  curl -sX POST https://telemeter.ai/api/tools/otel-validator -H 'content-type: application/json' -d '{"trace":{"name":"chat gpt-4o","kind":"SPAN_KIND_CLIENT","attributes":{"gen_ai.operation.name":"chat","gen_ai.provider.name":"openai","gen_ai.request.model":"gpt-4o","gen_ai.response.model":"gpt-4o-2026-05-01","gen_ai.usage.input_tokens":1200,"gen_ai.usage.output_tokens":340,"gen_ai.response.finish_reasons":["stop"]}}}'

MCP: the telemeter MCP server at https://telemeter.ai/mcp exposes this as the tool "otel-validator" — call it with tools/call.

The response is JSON: { status, data, summary, provenance }. "provenance" carries the source and the date the figure was verified. If status is "pending" or "stale", tell me the value isn't currently verified rather than presenting it as fact.

Or call it directly. This tool runs behind one handler with three front doors — this page, a REST endpoint, and an MCP tool. Same result, read-only, no key. The example below is a request that works.

REST

curl -sX POST https://telemeter.ai/api/tools/otel-validator \
  -H 'content-type: application/json' \
  -d '{"trace":{"name":"chat gpt-4o","kind":"SPAN_KIND_CLIENT","attributes":{"gen_ai.operation.name":"chat","gen_ai.provider.name":"openai","gen_ai.request.model":"gpt-4o","gen_ai.response.model":"gpt-4o-2026-05-01","gen_ai.usage.input_tokens":1200,"gen_ai.usage.output_tokens":340,"gen_ai.response.finish_reasons":["stop"]}}}'

MCP — tools/call at https://telemeter.ai/mcp

curl -sX POST https://telemeter.ai/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"otel-validator","arguments":{"trace":{"name":"chat gpt-4o","kind":"SPAN_KIND_CLIENT","attributes":{"gen_ai.operation.name":"chat","gen_ai.provider.name":"openai","gen_ai.request.model":"gpt-4o","gen_ai.response.model":"gpt-4o-2026-05-01","gen_ai.usage.input_tokens":1200,"gen_ai.usage.output_tokens":340,"gen_ai.response.finish_reasons":["stop"]}}}}}'

Input schema (JSON Schema)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "trace": {
      "anyOf": [
        {
          "type": "string",
          "minLength": 1
        },
        {
          "type": "object",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        {
          "type": "array",
          "items": {}
        }
      ]
    }
  },
  "required": [
    "trace"
  ],
  "additionalProperties": false
}

Want this across your whole stack?

Telemeter tracks real cost, latency, and quality on every production agent run.

Join the waitlist See how it works

Share or cite this tool

https://telemeter.ai/tools/otel-validator

No account, nothing sent anywhere — your trace is parsed and validated entirely in your browser. Data notice →