Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.uselayer.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Every request through Layer is logged with comprehensive metadata. Logs let you inspect individual requests, debug issues, and understand how your gates are performing.

​
Viewing Logs

Go to Dashboard → Logs to see a table of all requests with:
ColumnDescription
StatusSuccess or error
GateWhich gate handled the request
ModelThe model that was used (may differ from requested model if fallback triggered)
TokensInput + output token count
CostEstimated cost in USD
LatencyResponse time in milliseconds
TimeWhen the request was made

​
Filtering

Filter logs by:
  • Gate — See requests for a specific gate
  • Status — Show only successful or failed requests

​
Pagination

Logs are paginated with 50 entries per page by default.

​
Request Detail

Click any log entry to see full details:

​
Overview

  • Status, timestamp, gate name, model used
  • Token breakdown (input/output), cost, latency

​
Error Details

If the request failed, the error message and details are shown.

​
Request Payload

The full JSON request sent to the provider, including:
  • Messages array
  • System prompt
  • Tool definitions
  • Model parameters (temperature, max_tokens, etc.)

​
Response Payload

The full JSON response from the provider, including:
  • Generated content
  • Usage statistics
  • For image generation: inline preview with copy/download options
  • For tool calls: extracted tool use blocks

​
What’s Tracked

Every request log captures:
FieldDescription
model_requestedModel specified in the request
model_usedModel that actually handled the request (may differ with fallback routing)
prompt_tokensInput token count
completion_tokensOutput token count
cost_usdEstimated cost
latency_msResponse time
successWhether the request completed successfully
error_messageError details (if failed)
session_idSession identifier (agent gates only)
inferred_actionWhich sub-gate or action handled the request (agent gates only)
tool_callsExtracted tool use blocks from the response
tool_resultsExtracted tool results from the request

​
Logs API

Query logs programmatically: 
# List recent logs
curl "https://api.uselayer.ai/v1/logs?limit=20" \
  -H "Authorization: Bearer layer_your_key"

# Filter by gate
curl "https://api.uselayer.ai/v1/logs?gateId=your-gate-id&limit=20" \
  -H "Authorization: Bearer layer_your_key"

# Get overview analytics
curl "https://api.uselayer.ai/v1/logs/overview" \
  -H "Authorization: Bearer layer_your_key"
The overview endpoint returns aggregated stats:
  • Total requests, total cost, average latency
  • Active gate count
  • Recent request summaries

​
Data Retention

Request logs, including full request and response payloads, are retained according to your plan tier. The payloads contain the actual prompts and completions sent to/from providers.
A future update will add privacy controls allowing you to opt out of storing request/response content while still tracking metadata (cost, latency, tokens, success).