/

Docs
History
Schema
Generate

Filter operations

analytics110

get/v1/analytics/tools/usage/timeseriesTool invocations bucketed over time
get/v1/analytics/tools/usage/by-typeTool invocations grouped by tool_type
get/v1/analytics/tools/usage/by-toolTop-N tools by invocation count
get/v1/analytics/tools/usage/by-agentTool invocations grouped by agent_id
get/v1/analytics/tools/usage/unique-conversationsDistinct conversations per tool
get/v1/analytics/tools/performance/timeseriesLatency percentiles bucketed over time
get/v1/analytics/tools/performance/by-toolTop-N slowest tools by p95
get/v1/analytics/tools/performance/distributionLatency histogram across fixed buckets
get/v1/analytics/tools/performance/by-providerLatency percentiles grouped by provider
get/v1/analytics/tools/performance/retry-analysisPer-retry-count breakdown with avg/p95 latency
get/v1/analytics/tools/reliability/success-rate-timeseriesSuccess rate (%) bucketed over time
get/v1/analytics/tools/reliability/error-breakdownFailed-invocation count grouped by error_category
get/v1/analytics/tools/reliability/error-breakdown-by-statusFailed-invocation count grouped by HTTP status_code
get/v1/analytics/tools/reliability/rankingPer-tool success rate ranked worst-first
get/v1/analytics/tools/reliability/error-timeseriesError count over time, split by error_category
get/v1/analytics/tools/reliability/error-trendCurrent vs previous window error-rate comparison
get/v1/analytics/tools/reliability/timeout-analysisPer-tool timeout rate and latency tail
get/v1/analytics/tools/dashboardCombined tool analytics dashboard envelope
get/v1/analytics/tools/monitoring/anomaly-detectionPer-tool z-score anomaly scan vs a rolling baseline (window <= 1 day)
get/v1/analytics/tools/monitoring/health-checkPer-tool health (healthy/degraded/critical) with threshold violations
get/v1/analytics/sessions/volume-timeseriesNew-session counts bucketed over time, split by channel
get/v1/analytics/sessions/status-breakdownCurrent distribution of sessions across statuses
get/v1/analytics/sessions/resolution-timeResolution-time percentiles by channel and priority
get/v1/analytics/sessions/first-response-timeTime-to-first-response percentiles
get/v1/analytics/sessions/by-channelPer-channel comparison of session volume and quality
get/v1/analytics/sessions/escalation-ratePer-bucket escalation rate timeseries
get/v1/analytics/sessions/message-distributionHistogram of message count per session
get/v1/analytics/sessions/turn-depthTurn-depth summary (avg / single-turn rate / quantiles)
get/v1/analytics/voice/volume-timeseriesTerminated-call counts bucketed over time (completed / failed / no_answer)
get/v1/analytics/voice/outcome-breakdownDistribution of terminated calls across call-statuses
get/v1/analytics/voice/answer-rate-timeseriesPer-bucket answer/connection rate over time (share of LIVE calls that connected)
get/v1/analytics/voice/warm-transfers/summaryOutbound warm-transfer success rate and successful setup latency
get/v1/analytics/voice/warm-transfers/failure-reasonsOutbound warm-transfer failures grouped by normalized reason
get/v1/analytics/voice/warm-transfers/setup-latency-timeseriesSuccessful outbound warm-transfer setup latency over time
get/v1/analytics/voice/warm-transfers/dashboardOne-shot envelope of all outbound warm-transfer analytics
get/v1/analytics/knowledge/documents/adoptionPer-KB adoption rate and document counts
get/v1/analytics/knowledge/documents/ingestion-timeseriesDocument-ingestion counts bucketed over time
get/v1/analytics/knowledge/documents/processing-latencyDocument processing-time percentiles bucketed over time
get/v1/analytics/knowledge/documents/cleanup-summaryFailure-recovery analytics: failed / archived / cleaned_up / recovered
get/v1/analytics/knowledge/documents/retrieval-timeseriesSearch-call volume and latency percentiles bucketed over time
get/v1/analytics/knowledge/documents/retrieval-by-agentPer-agent retrieval breakdown: volume, hit-rate, and avg latency
get/v1/analytics/knowledge/documents/top-retrievedTop-N most-retrieved documents in a window
get/v1/analytics/knowledge/documents/staleDocuments currently active but unretrieved (or stale beyond N days)
get/v1/analytics/knowledge/inventoryCurrent-state KB inventory shape
get/v1/analytics/knowledge/connectors/freshnessPer-source latest sync state and time-since-last-event
get/v1/analytics/knowledge/dashboardOne-shot envelope of every knowledge analytics pipe
get/v1/analytics/memory/ingestion-timeseriesMemory episode counts bucketed over time
get/v1/analytics/memory/coverageMemory coverage: users-with-memory / active-end-users (clamped 100%)
get/v1/analytics/memory/recalls/timeseriesMemory recall volume bucketed over time with hit/miss + latency percentiles
get/v1/analytics/memory/users/distributionPer-user engagement quantiles (episodes/messages/recalls)
get/v1/analytics/memory/dashboardOne-shot envelope of every memory analytics pipe
get/v1/analytics/mocks/summarySingle-row dashboard summary: requests, match/error rates, latency
get/v1/analytics/mocks/requests-timeseriesMock request volume bucketed over time
get/v1/analytics/mocks/latency-timeseriesMock latency percentiles bucketed over time
get/v1/analytics/mocks/match-rate-timeseriesMock scenario match rate bucketed over time
get/v1/analytics/mocks/top-scenariosTop-N mock scenarios by request count
get/v1/analytics/mocks/dashboardOne-shot envelope of every mock analytics pipe
get/v1/analytics/integrations/summarySingle-row summary: invocations, failures, success rate, latency (vs prior window)
get/v1/analytics/integrations/usage-timeseriesIntegration tool-call volume bucketed over time
get/v1/analytics/integrations/success-rate-timeseriesEffective success rate (%) bucketed over time
get/v1/analytics/integrations/latency-timeseriesIntegration tool-call latency percentiles bucketed over time
get/v1/analytics/integrations/by-integrationVolume + reliability + p95 latency grouped by integration_key
get/v1/analytics/integrations/by-modeVolume + reliability + p95 latency grouped by mode (vendor_api/feather_mcp_client)
get/v1/analytics/integrations/error-breakdownFailures grouped by error_category (vendor_error / exception:<type>)
get/v1/analytics/integrations/dashboardOne-shot envelope of every integration analytics pipe
get/v1/analytics/integrations/connections/summarySingle-row connection-health summary: events, failures, success rate, latency
get/v1/analytics/integrations/connections/by-integrationConnection health grouped by integration_key (events, success rate, p95 latency)
get/v1/analytics/integrations/connections/events-timeseriesConnection lifecycle event volume (events/successes/failures) over time
get/v1/analytics/integrations/connections/success-rate-timeseriesConnection lifecycle effective success rate (%) over time
get/v1/analytics/integrations/connections/failure-breakdownConnection lifecycle failures grouped by event_type + error_category
get/v1/analytics/policies/violation-ratePer-policy violation rate + action counts within a window
get/v1/analytics/policies/action-breakdownAction counts split into taken (enforced) vs would-be (monitor-mode shadow)
get/v1/analytics/policies/violations-timeseriesEvaluation + violation volume bucketed over time (enforced vs shadow)
get/v1/analytics/policies/monitor-rolloutEnforce-after-measure: per monitor-mode policy, would-be impact + TTFT-delta
get/v1/analytics/policies/dashboardOne-shot envelope of every policy analytics pipe
get/v1/analytics/policies/revisions/{revision_id}/disclaimer-statusWhether an enforcing agent_response policy is attached (TTFT disclaimer)
get/v1/analytics/model-router/cost/by-org-dailyModel-router cost bucketed over time
get/v1/analytics/model-router/cost/by-agentTop-N agents by model-router spend
get/v1/analytics/model-router/cost/by-modelTop-N served models by spend
get/v1/analytics/model-router/cost/by-operationCost and reliability grouped by operation
get/v1/analytics/model-router/cost/by-providerCost and reliability grouped by provider
get/v1/analytics/model-router/cost/by-sessionTop-N sessions (conversations) by spend
get/v1/analytics/model-router/cost/by-router-configTop-N router configs by model-router spend
get/v1/analytics/model-router/tokens/breakdownPer-model token usage breakdown (incl. billed tokens)
get/v1/analytics/model-router/cache/savingsPer-model prompt-cache usage and cost
get/v1/analytics/model-router/latencyPer-model latency percentiles (p50/p95/p99)
get/v1/analytics/model-router/fallback/rateFallback rate bucketed over time
get/v1/analytics/model-router/error/rateTerminal error rate over a window
get/v1/analytics/model-router/embeddings/cost/by-org-dailyEmbedding cost + tokens bucketed over time
get/v1/analytics/model-router/embeddings/cost/by-modelTop-N embedding models by spend
get/v1/analytics/model-router/embeddings/cost/by-sourceEmbedding spend grouped by call site
get/v1/analytics/model-router/embeddings/cost/by-kbTop-N knowledge bases by embedding spend
get/v1/analytics/model-router/embeddings/reliabilityEmbedding reliability + throughput per model
get/v1/analytics/model-router/smart-routing/impactSmart-routed vs non-smart-routed cost & reliability
get/v1/analytics/model-router/error/breakdownTerminal errors grouped by error category
get/v1/analytics/model-router/error/timeseriesTerminal error rate bucketed over time
get/v1/analytics/model-router/cost/trendCurrent vs previous equal-length window spend
get/v1/analytics/model-router/cost/per-successful-responseCost per terminal successful response, per model
get/v1/analytics/model-router/latency/timeseriesLatency percentiles bucketed over time
get/v1/analytics/model-router/latency/ttft-timeseriesTime-to-first-token percentiles over time (streaming)
get/v1/analytics/model-router/latency/ttft-by-modelTime-to-first-token percentiles per model (streaming)
get/v1/analytics/model-router/fallback/analysisPrimary vs fallback leg cost & reliability
get/v1/analytics/model-router/tokens/efficiencyToken-usage efficiency ratios per model
get/v1/analytics/model-router/dashboardOne-shot LLM analytics dashboard (fan-out of 6 pipes)
get/v1/analytics/model-router/embeddings/dashboardOne-shot embedding analytics dashboard (fan-out of 4 pipes)
get/v1/analytics/model-router/embeddings/cost/by-providerEmbedding cost + error rate per provider
get/v1/analytics/model-router/embeddings/error/breakdownEmbedding failures grouped by error category
get/v1/analytics/model-router/embeddings/retry/impactFirst-try vs retry embedding spend (wasted re-embeds)
get/v1/analytics/model-router/embeddings/latency/timeseriesEmbedding latency percentiles bucketed over time
get/v1/analytics/model-router/embeddings/dense-vs-sparseDense vs sparse embedding cost / throughput / reliability

ask-feather12

assistants41

billing3

communication12

conversation-exports4

conversations18

email7

email-drafts6

evals19

extraction-schemas4

extractions3

hitl10

identity28

integrations17

knowledge-base29

knowledge-base-acl6

knowledge-base-audit6

knowledge-base-connectors12

knowledge-base-evals13

knowledge-base-governance4

knowledge-gap-analytics9

library12

mcp-chat2

memory4

mocks16

model-router10

notifications19

personas7

policies22

privacy5

retention-policies4

scenarios7

sessions1

sim_suites15

simulation_runs6

sms5

teams15

tools17

voice40

webchat10

webhooks2

workflow-playground4

workflows22

analytics

Changes to Per-model prompt-cache usage and cost

get/v1/analytics/model-router/cache/savings

Aug 12, 20265a5597ebb2d6 Revision changes
- info
  endpoint added