/
ON
oneloop-hq
Search skmtc…
⌘K
Docs
Sign in
Docs
History
Schema
Generate
Filter operations
analytics
110
get
/v1/analytics/tools/usage/timeseries
Tool invocations bucketed over time
get
/v1/analytics/tools/usage/by-type
Tool invocations grouped by tool_type
get
/v1/analytics/tools/usage/by-tool
Top-N tools by invocation count
get
/v1/analytics/tools/usage/by-agent
Tool invocations grouped by agent_id
get
/v1/analytics/tools/usage/unique-conversations
Distinct conversations per tool
get
/v1/analytics/tools/performance/timeseries
Latency percentiles bucketed over time
get
/v1/analytics/tools/performance/by-tool
Top-N slowest tools by p95
get
/v1/analytics/tools/performance/distribution
Latency histogram across fixed buckets
get
/v1/analytics/tools/performance/by-provider
Latency percentiles grouped by provider
get
/v1/analytics/tools/performance/retry-analysis
Per-retry-count breakdown with avg/p95 latency
get
/v1/analytics/tools/reliability/success-rate-timeseries
Success rate (%) bucketed over time
get
/v1/analytics/tools/reliability/error-breakdown
Failed-invocation count grouped by error_category
get
/v1/analytics/tools/reliability/error-breakdown-by-status
Failed-invocation count grouped by HTTP status_code
get
/v1/analytics/tools/reliability/ranking
Per-tool success rate ranked worst-first
get
/v1/analytics/tools/reliability/error-timeseries
Error count over time, split by error_category
get
/v1/analytics/tools/reliability/error-trend
Current vs previous window error-rate comparison
get
/v1/analytics/tools/reliability/timeout-analysis
Per-tool timeout rate and latency tail
get
/v1/analytics/tools/dashboard
Combined tool analytics dashboard envelope
get
/v1/analytics/tools/monitoring/anomaly-detection
Per-tool z-score anomaly scan vs a rolling baseline (window <= 1 day)
get
/v1/analytics/tools/monitoring/health-check
Per-tool health (healthy/degraded/critical) with threshold violations
get
/v1/analytics/sessions/volume-timeseries
New-session counts bucketed over time, split by channel
get
/v1/analytics/sessions/status-breakdown
Current distribution of sessions across statuses
get
/v1/analytics/sessions/resolution-time
Resolution-time percentiles by channel and priority
get
/v1/analytics/sessions/first-response-time
Time-to-first-response percentiles
get
/v1/analytics/sessions/by-channel
Per-channel comparison of session volume and quality
get
/v1/analytics/sessions/escalation-rate
Per-bucket escalation rate timeseries
get
/v1/analytics/sessions/message-distribution
Histogram of message count per session
get
/v1/analytics/sessions/turn-depth
Turn-depth summary (avg / single-turn rate / quantiles)
get
/v1/analytics/voice/volume-timeseries
Terminated-call counts bucketed over time (completed / failed / no_answer)
get
/v1/analytics/voice/outcome-breakdown
Distribution of terminated calls across call-statuses
get
/v1/analytics/voice/answer-rate-timeseries
Per-bucket answer/connection rate over time (share of LIVE calls that connected)
get
/v1/analytics/voice/warm-transfers/summary
Outbound warm-transfer success rate and successful setup latency
get
/v1/analytics/voice/warm-transfers/failure-reasons
Outbound warm-transfer failures grouped by normalized reason
get
/v1/analytics/voice/warm-transfers/setup-latency-timeseries
Successful outbound warm-transfer setup latency over time
get
/v1/analytics/voice/warm-transfers/dashboard
One-shot envelope of all outbound warm-transfer analytics
get
/v1/analytics/knowledge/documents/adoption
Per-KB adoption rate and document counts
get
/v1/analytics/knowledge/documents/ingestion-timeseries
Document-ingestion counts bucketed over time
get
/v1/analytics/knowledge/documents/processing-latency
Document processing-time percentiles bucketed over time
get
/v1/analytics/knowledge/documents/cleanup-summary
Failure-recovery analytics: failed / archived / cleaned_up / recovered
get
/v1/analytics/knowledge/documents/retrieval-timeseries
Search-call volume and latency percentiles bucketed over time
get
/v1/analytics/knowledge/documents/retrieval-by-agent
Per-agent retrieval breakdown: volume, hit-rate, and avg latency
get
/v1/analytics/knowledge/documents/top-retrieved
Top-N most-retrieved documents in a window
get
/v1/analytics/knowledge/documents/stale
Documents currently active but unretrieved (or stale beyond N days)
get
/v1/analytics/knowledge/inventory
Current-state KB inventory shape
get
/v1/analytics/knowledge/connectors/freshness
Per-source latest sync state and time-since-last-event
get
/v1/analytics/knowledge/dashboard
One-shot envelope of every knowledge analytics pipe
get
/v1/analytics/memory/ingestion-timeseries
Memory episode counts bucketed over time
get
/v1/analytics/memory/coverage
Memory coverage: users-with-memory / active-end-users (clamped 100%)
get
/v1/analytics/memory/recalls/timeseries
Memory recall volume bucketed over time with hit/miss + latency percentiles
get
/v1/analytics/memory/users/distribution
Per-user engagement quantiles (episodes/messages/recalls)
get
/v1/analytics/memory/dashboard
One-shot envelope of every memory analytics pipe
get
/v1/analytics/mocks/summary
Single-row dashboard summary: requests, match/error rates, latency
get
/v1/analytics/mocks/requests-timeseries
Mock request volume bucketed over time
get
/v1/analytics/mocks/latency-timeseries
Mock latency percentiles bucketed over time
get
/v1/analytics/mocks/match-rate-timeseries
Mock scenario match rate bucketed over time
get
/v1/analytics/mocks/top-scenarios
Top-N mock scenarios by request count
get
/v1/analytics/mocks/dashboard
One-shot envelope of every mock analytics pipe
get
/v1/analytics/integrations/summary
Single-row summary: invocations, failures, success rate, latency (vs prior window)
get
/v1/analytics/integrations/usage-timeseries
Integration tool-call volume bucketed over time
get
/v1/analytics/integrations/success-rate-timeseries
Effective success rate (%) bucketed over time
get
/v1/analytics/integrations/latency-timeseries
Integration tool-call latency percentiles bucketed over time
get
/v1/analytics/integrations/by-integration
Volume + reliability + p95 latency grouped by integration_key
get
/v1/analytics/integrations/by-mode
Volume + reliability + p95 latency grouped by mode (vendor_api/feather_mcp_client)
get
/v1/analytics/integrations/error-breakdown
Failures grouped by error_category (vendor_error / exception:<type>)
get
/v1/analytics/integrations/dashboard
One-shot envelope of every integration analytics pipe
get
/v1/analytics/integrations/connections/summary
Single-row connection-health summary: events, failures, success rate, latency
get
/v1/analytics/integrations/connections/by-integration
Connection health grouped by integration_key (events, success rate, p95 latency)
get
/v1/analytics/integrations/connections/events-timeseries
Connection lifecycle event volume (events/successes/failures) over time
get
/v1/analytics/integrations/connections/success-rate-timeseries
Connection lifecycle effective success rate (%) over time
get
/v1/analytics/integrations/connections/failure-breakdown
Connection lifecycle failures grouped by event_type + error_category
get
/v1/analytics/policies/violation-rate
Per-policy violation rate + action counts within a window
get
/v1/analytics/policies/action-breakdown
Action counts split into taken (enforced) vs would-be (monitor-mode shadow)
get
/v1/analytics/policies/violations-timeseries
Evaluation + violation volume bucketed over time (enforced vs shadow)
get
/v1/analytics/policies/monitor-rollout
Enforce-after-measure: per monitor-mode policy, would-be impact + TTFT-delta
get
/v1/analytics/policies/dashboard
One-shot envelope of every policy analytics pipe
get
/v1/analytics/policies/revisions/{revision_id}/disclaimer-status
Whether an enforcing agent_response policy is attached (TTFT disclaimer)
get
/v1/analytics/model-router/cost/by-org-daily
Model-router cost bucketed over time
get
/v1/analytics/model-router/cost/by-agent
Top-N agents by model-router spend
get
/v1/analytics/model-router/cost/by-model
Top-N served models by spend
get
/v1/analytics/model-router/cost/by-operation
Cost and reliability grouped by operation
get
/v1/analytics/model-router/cost/by-provider
Cost and reliability grouped by provider
get
/v1/analytics/model-router/cost/by-session
Top-N sessions (conversations) by spend
get
/v1/analytics/model-router/cost/by-router-config
Top-N router configs by model-router spend
get
/v1/analytics/model-router/tokens/breakdown
Per-model token usage breakdown (incl. billed tokens)
get
/v1/analytics/model-router/cache/savings
Per-model prompt-cache usage and cost
get
/v1/analytics/model-router/latency
Per-model latency percentiles (p50/p95/p99)
get
/v1/analytics/model-router/fallback/rate
Fallback rate bucketed over time
get
/v1/analytics/model-router/error/rate
Terminal error rate over a window
get
/v1/analytics/model-router/embeddings/cost/by-org-daily
Embedding cost + tokens bucketed over time
get
/v1/analytics/model-router/embeddings/cost/by-model
Top-N embedding models by spend
get
/v1/analytics/model-router/embeddings/cost/by-source
Embedding spend grouped by call site
get
/v1/analytics/model-router/embeddings/cost/by-kb
Top-N knowledge bases by embedding spend
get
/v1/analytics/model-router/embeddings/reliability
Embedding reliability + throughput per model
get
/v1/analytics/model-router/smart-routing/impact
Smart-routed vs non-smart-routed cost & reliability
get
/v1/analytics/model-router/error/breakdown
Terminal errors grouped by error category
get
/v1/analytics/model-router/error/timeseries
Terminal error rate bucketed over time
get
/v1/analytics/model-router/cost/trend
Current vs previous equal-length window spend
get
/v1/analytics/model-router/cost/per-successful-response
Cost per terminal successful response, per model
get
/v1/analytics/model-router/latency/timeseries
Latency percentiles bucketed over time
get
/v1/analytics/model-router/latency/ttft-timeseries
Time-to-first-token percentiles over time (streaming)
get
/v1/analytics/model-router/latency/ttft-by-model
Time-to-first-token percentiles per model (streaming)
get
/v1/analytics/model-router/fallback/analysis
Primary vs fallback leg cost & reliability
get
/v1/analytics/model-router/tokens/efficiency
Token-usage efficiency ratios per model
get
/v1/analytics/model-router/dashboard
One-shot LLM analytics dashboard (fan-out of 6 pipes)
get
/v1/analytics/model-router/embeddings/dashboard
One-shot embedding analytics dashboard (fan-out of 4 pipes)
get
/v1/analytics/model-router/embeddings/cost/by-provider
Embedding cost + error rate per provider
get
/v1/analytics/model-router/embeddings/error/breakdown
Embedding failures grouped by error category
get
/v1/analytics/model-router/embeddings/retry/impact
First-try vs retry embedding spend (wasted re-embeds)
get
/v1/analytics/model-router/embeddings/latency/timeseries
Embedding latency percentiles bucketed over time
get
/v1/analytics/model-router/embeddings/dense-vs-sparse
Dense vs sparse embedding cost / throughput / reliability
ask-feather
12
assistants
41
billing
3
communication
12
conversation-exports
4
conversations
18
email
7
email-drafts
6
evals
19
extraction-schemas
4
extractions
3
hitl
10
identity
28
integrations
17
knowledge-base
29
knowledge-base-acl
6
knowledge-base-audit
6
knowledge-base-connectors
12
knowledge-base-evals
13
knowledge-base-governance
4
knowledge-gap-analytics
9
library
12
mcp-chat
2
memory
4
mocks
16
model-router
10
notifications
19
personas
7
policies
22
privacy
5
retention-policies
4
scenarios
7
sessions
1
sim_suites
15
simulation_runs
6
sms
5
teams
15
tools
17
voice
40
webchat
10
webhooks
2
workflow-playground
4
workflows
22
analytics
Copy
Copy Markdown
Copy Markdown
Copying…
Copied
Copy failed
Changes to Time-to-first-token percentiles per model (streaming)
get
/v1/analytics/model-router/latency/ttft-by-model
Aug 12, 2026
5a5597ebb2d6
Revision changes
info
endpoint added