Sign In
Get Started
Get Started

Documentation

API Reference

Contributing

Overview

API Reference Overview
Chat Completions API
Anthropic Messages API

SDK Methods

chat()
image()
tts()
video()

Admin API

Admin API Overview
Gates API
API Keys Management

Chat

POST
Create a chat completion via a Layer gate

Image

POST
Generate an image via a Layer gate

Video

POST
Generate a video via a Layer gate

Embeddings

POST
Create vector embeddings via a Layer gate

TTS

POST
Synthesize speech from text via a Layer gate

OCR

POST
Extract text from an image or PDF via a Layer gate

Sessions

GET
List sessions for a gate
GET
Get gate-level aggregated session analysis
GET
Get a session by id
GET
List requests in a session
GET
Get a session trace (tree-structured)
GET
Get session analysis (insights)
POST
Trigger on-demand analysis for a session
POST
End a session (developer-initiated)
GET
Get feedback submitted for a session
POST
Submit user feedback for a session
POST
Apply an analysis recommendation to the gate config
GET
Get gate-level feedback summary
PATCH
Toggle whether a session is excluded from cross-session analysis
GET
Get the latest Cortex intelligence report for a gate
POST
Trigger an on-demand Cortex intelligence report for a gate
GET
List historical Cortex reports for a gate (metadata only)
GET
Get a specific historical Cortex report
GET
Get the topic distribution for a gate
GET
Get detailed gate feedback with topics and trends

Monitors

GET
List recent alert firings for a gate
GET
List alert configs for a gate
POST
Create an alert config for a gate
DEL
Delete an alert config
PATCH
Update an alert config
GET
List pattern monitors for a gate
POST
Create a pattern monitor for a gate
GET
Get a monitor with recent hits
DEL
Delete a pattern monitor
PATCH
Update a pattern monitor

Memory

GET
List memory entries for a gate
POST
Create a memory entry for a gate
DEL
Delete a memory entry
PATCH
Update a memory entry

Fleet

GET
Get aggregated fleet observability stats
GET
Get request volume timeline across the fleet
GET
Get cost breakdown by gate and model
GET
Get latency distribution across the fleet
GET
Get error rates and patterns across the fleet
GET
Get model usage distribution across the fleet
GET
Get quality score distribution across gates
GET
Get rolled-up recommendations across all gates
GET
Get aggregated anomalies and silent failures
GET
Get estimated cost savings opportunities across gates

Gates

GET
List gates owned by the authenticated user
POST
Create a new gate
GET
Get session-stats for every gate owned by the caller (batch)
GET
List OpenClaw-tagged gates with analytics
GET
Get a gate by its name
GET
List configuration history across every gate owned by the caller
GET
List activity-log entries across every gate owned by the caller
GET
List configuration history for a specific gate
GET
List activity-log entries for a specific gate
GET
List sessions for an agent gate
GET
Get aggregated session stats for a gate
GET
List sub-gates attached to an agent gate
POST
Create a new sub-gate and attach it to an agent gate
POST
Attach an existing gate as a sub-gate of an agent gate
DEL
Detach a sub-gate from an agent gate
POST
Lock a sub-gate to its parent agent gate
POST
Unlock a sub-gate from its parent agent gate
POST
Duplicate an existing gate
GET
List agent gates that use this gate as a sub-gate
GET
List soft-deleted (trashed) gates
GET
Get a gate by id
DEL
Soft-delete a gate (moves to trash for 30 days)
PATCH
Update a gate
GET
Check what depends on a gate (before deletion)
POST
Restore a soft-deleted gate from the trash
POST
Test a gate configuration with a sample request
POST
Get The Architect's model + config suggestions for a gate
POST
Roll a gate back to a previous configuration
GET
List cached routing decisions for a dynamic-orchestration agent gate
DEL
Flush cached routing decisions for a dynamic-orchestration agent gate

OpenAI Compat

POST
OpenAI-compatible chat completions (drop-in)
POST
OpenAI-compatible image generations (drop-in)
POST
OpenAI-compatible text-to-speech (drop-in)
POST
OpenAI-compatible embeddings (drop-in)

Anthropic Compat

POST
Anthropic-compatible messages (drop-in)

API Keys

GET
List API keys owned by the authenticated user
POST
Generate a new API key
DEL
Revoke an API key

Provider Keys

GET
List BYOK provider keys
POST
Register a BYOK provider key
PUT
Update a BYOK provider key
DEL
Delete a BYOK provider key
PATCH
Toggle a BYOK provider key active/inactive
POST
Test a BYOK provider key against the upstream provider

User

GET
Identify the authenticated principal

Registry

GET
Get the public model + provider registry

Analytics

POST
Track client-side analytics events

Experiments

GET
List experiments owned by the caller
POST
Create a new A/B test (experiment)
GET
Search gates available for experiment creation
GET
Get an experiment with per-variant metrics
DEL
Delete an experiment
PATCH
Update an experiment (with status-based field allowlist)
POST
Extend a running experiment’s collection window
POST
Apply the winning variant’s config to the gate
GET
List per-request assignments + metrics for an experiment
GET
Get full experiment analysis (sequential testing + multi-metric + SRM)
GET
List quality evaluations for an experiment
GET
Get time-series metrics for charting an experiment
GET
List shadow-mode request samples for an experiment
GET
Get the shadow-test summary + verdict
GET
Get the multi-aggregate shadow-analysis breakdown
POST
Promote a completed shadow experiment (apply or graduate to split)
GET
Check whether an experiment is eligible for promotion

Completion (v2 legacy)

POST
Generic completion endpoint (v2 — legacy)

List cached routing decisions for a dynamic-orchestration agent gate

curl --request GET \
  --url https://api.verlon.ai/v1/gates/:id/routing-decisions \
  --header 'Authorization: Bearer <token>'

{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Gates

List cached routing decisions for a dynamic-orchestration agent gate

Use when: caller wants to inspect the cached per-task routing decisions made by a dynamic-orchestration agent gate (debugging routing behavior)

Dynamic-orchestration agent gates cache routing decisions per task signature so the orchestrator doesn’t re-decide on every call. This endpoint exposes the cache for inspection. Empty array for gates that don’t use dynamic orchestration.

GET

gates

:id

routing-decisions

List cached routing decisions for a dynamic-orchestration agent gate

curl --request GET \
  --url https://api.verlon.ai/v1/gates/:id/routing-decisions \
  --header 'Authorization: Bearer <token>'

{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Documentation Index
Fetch the complete documentation index at: https://docs.verlon.ai/llms.txt
Use this file to discover all available pages before exploring further.

Authorizations

Authorization

string

header

required

Layer API key (prefixed sk-). Generated from the dashboard under Settings → API Keys, or via layer key create in the CLI.

Response

Array of cached routing decisions for the gate.

Roll a gate back to a previous configuration Flush cached routing decisions for a dynamic-orchestration agent gate

⌘I

website

Powered byThis documentation is built and hosted on Mintlify, a developer documentation platform