Fetch conversation metrics
Filter /v1/metrics/bulkAll by a conversation's traceId to retrieve its duration, token usage, TTS character count, and fixed-rate cost estimates.
Use an organization-scoped API key for this v1 endpoint. Project-scoped API keys cannot access it. The pricing values are legacy fixed-rate estimates. For recorded costs for a trace, use /metrics/v2/billing/traces?traceIds=<trace-id>.
Endpoint
Code
Use case: fetch consumption for a single conversation
Goal
Get the traceId from the Exchange record. Use a time window that includes the conversation summary, which is normally emitted during call finalization.
Request
Code
Query parameters
| Parameter | Value | Description |
|---|---|---|
from | 2026-03-10T08:00:00.000Z | Start of the time window (ISO 8601) |
to | 2026-03-20T08:00:00.000Z | End of the time window (ISO 8601) |
traceId | b8c31b19-ed4b-46bb-ba48-88d20c49b64d | traceId from the Exchange record, not its id |
metrics | See below | Comma-separated list of metrics to retrieve |
Metrics requested
| Metric | Description |
|---|---|
duration | Total conversation duration (seconds) |
indivisibleDuration | Billed duration blocks (minutes) |
usage.tts.characters | Characters sent to text-to-speech |
usage.conversational.inputTextTokens | Input tokens consumed by the conversational AI |
usage.conversational.outputTextTokens | Output tokens produced by the conversational AI |
usage.conversational.cachedTextTokens | Cached tokens reused by the conversational AI |
Example response
These aggregates are illustrative, with prices rounded to six decimal places.
Code
Reading the response
Each object in the array corresponds to one metric. With one matching conversation summary containing the requested metric, count is 1 and sum, avg, min, and max are identical. If no matching summary contains that metric, the endpoint returns zeros.
| Field | Type | Description |
|---|---|---|
timestamp | string | Start of the aggregation window (matches from) |
metric | string | Name of the metric |
data.sum | number | Total value for this conversation |
data.count | number | Number of matching summary events containing this metric |
pricing | number | Estimated cost in EUR for this metric |
Notes
- The
from/towindow must contain the time the conversation summary was emitted, normally during call finalization; otherwise the response returnscount: 0. - The
traceIdis a UUID assigned to each conversation by the Reecall platform. - The
bulkAllendpoint has no limit on the number of metrics requested and returns all as a flat array. - Your organization scope is applied automatically. Optionally pass
projectIdto narrow the query to a Project within that Organization. - The
pricingfield is a fixed-rate estimate in EUR for each requested metric. Summing these values gives an estimate for those metrics, not the recorded total conversation cost.