Developers
OpenTelemetry ingestion
Already tracing your agents? Point an OTLP exporter at eBRBe and every model call becomes an agent run, priced and ready to bill.
Endpoint
| Value | |
|---|---|
| URL | https://ebrbe.com/api/v1/otel/v1/traces |
| Protocol | OTLP/HTTP: application/json or application/x-protobuf, optionally Content-Encoding: gzip |
| Auth | Authorization: Bearer <API key> with the telemetry:write scope (agent_runs:write also works). Optional eBRBe-Workspace: <slug>. |
| Limits | 4 MB per request (16 MB decompressed), 10,000 spans and 1,000 gen-AI spans per request, and the key's API rate limit per request. |
| Response | 200 with an OTLP ExportTraceServiceResponse; spans that can't be logged are reported as partial success (rejected spans and the reason), so exporters don't retry them. |
Environment (any OpenTelemetry SDK or Collector)
OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=https://ebrbe.com/api/v1/otel/v1/traces
OTEL_EXPORTER_OTLP_TRACES_PROTOCOL=http/protobuf
OTEL_EXPORTER_OTLP_TRACES_HEADERS="Authorization=Bearer ebrbe_...,eBRBe-Workspace=acme"With a Collector, add an otlphttp exporter with traces_endpoint set to the URL above and the same headers, and a filter so only gen-AI spans are forwarded.
How spans become runs
Spans that carry token usage under the OpenTelemetry GenAI semantic conventions become one run each. Other spans are accepted and ignored.
| Run field | From |
|---|---|
| model | gen_ai.response.model, else gen_ai.request.model |
| provider | gen_ai.provider.name (or gen_ai.system) |
| input / output tokens | gen_ai.usage.input_tokens / output_tokens |
| cache read / write | gen_ai.usage.cache_read.input_tokens / cache_write.input_tokens (or cache_creation.input_tokens) |
| tool | ebrbe.tool, else gen_ai.agent.name, else resource service.name |
| started, duration | span start and end time |
| project / client / work item | ebrbe.project_id, ebrbe.client_id, ebrbe.work_item_id (span or resource attributes, UUIDs) |
| cost | eBRBe's price table for the model, or ebrbe.cost_usd if you set it |
| billable | ebrbe.billable (default true) |
| external_id | otel:<trace id>:<span id> |
- No double counting:
gen_ai.usage.input_tokensincludes cache reads and writes, so eBRBe subtracts them. When a span and one of its descendants in the same request both carry usage (an SDK client span around the server span, aroundanthropic.model_request), only the deepest counts. Send one source per request (SDK spans or API spans) if they arrive in different batches. - Idempotent: re-sending a batch adds nothing; the response headers
eBRBe-Runs-CreatedandeBRBe-Runs-Duplicatesay what happened. - Runs act as the key's owner: the same permissions, project checks, prices, markup and webhooks as runs logged over the REST API.
- Models without a price are rejected unless the span has
ebrbe.cost_usd.
Try it
Terminal
curl https://ebrbe.com/api/v1/otel/v1/traces \
-H "Authorization: Bearer $EBRBE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"resourceSpans":[{"resource":{"attributes":[{"key":"service.name","value":{"stringValue":"support-bot"}}]},
"scopeSpans":[{"spans":[{"traceId":"5b8efff798038103d269b633813fc60c","spanId":"eee19b7ec3c1b174",
"name":"chat claude-opus-5-5","startTimeUnixNano":"1793260800000000000","endTimeUnixNano":"1793260803000000000",
"attributes":[{"key":"gen_ai.request.model","value":{"stringValue":"claude-opus-5-5"}},
{"key":"gen_ai.usage.input_tokens","value":{"intValue":"1200"}},
{"key":"gen_ai.usage.output_tokens","value":{"intValue":"300"}}]}]}]}]}'The run appears in Agent costs with source otel. For Claude Code sessions, the CLI hook is simpler; for a provider's whole bill, use the usage sync.