Optiak Docs
Observability

Application

The traffic, cost and individual requests of one application.

Application observability shows the traffic and cost of one application, and each request it sends through the Gateway. Use it to check that an application is healthy and to find out what happened to a specific request.

Required role

Organization AdminWorkspace AdminProject AdminApp AdminApp Viewer

Applies to

LLM requestsTool calls
Each role sees the applications it has access to. To see the Overview, a role needs View supported application configuration and metrics on the application. A role on the organization is not necessary. See Members and Access. App Viewers see the Overview only. The other roles also see each request in the Requests tab.

Why use it

Overview

The Dashboard for one application

  • Is the application healthy?
  • What does it cost, and what made the cost change?
  • Which models does it use?

Requests

One request at a time

  • Why did this request fail, or which check blocked it?
  • Which stage took the time?
  • What did Guardrails, the Context Engine and Smart Router change?
These are some of the questions they answer.

To compare applications, or to see the whole organization, use Organization.

Overview

ProjectsDefaultSupport Assistant

Support AssistantActive

support-assistant

Overview Requests Hidden for App ViewersConfiguration

Shortcut: on the Projects page, switch the list to Applications.

The console path to one application.

The Overview tab opens first. It starts with a summary of the application's configuration. Below the summary, it shows the Dashboard for this application only. Each metric uses the definition in Metrics, filtered to this application.

Usage

Requests

721 +10.1%

Input tokens

1.42M +14.8%

Output tokens

312K +9.6%

Cache hit rate

38.2% +4.1%

Metric: Requests Grouping: Model Bucket: Daily

Over time

Example data. Select the table icon to see the change of each row.
  • The Overview opens on Today. Pick the period at the top right. Each application keeps its own period. A change to the Dashboard period does not change it.
  • The charts use the Dashboard's controls: Metric, Grouping and Bucket.
  • There is no Application or Project grouping.
  • Two sections show only the total over time: Governance & Security and Data Integrations. Their metrics split only by application, so these charts have no Grouping control.

Each section links to the definitions of its metrics:

Requests

The Requests tab is next to the Overview. It lists each request that the application sent through the Gateway. Use the Status filter to select Success, Success with fallback, Failed or Blocked. Clear the status filter to show all requests in the selected period. Each row shows the model and provider when the request reached a model, then the latency, the tokens, the cost and the time.

Each row also shows the result of the request:

AllSuccessFailureBlockedToday7d30dCustom
RequestLatencyTokensCost
gpt-4.1-mini· OpenAISuccess2.67 s1,516$0.00041
claude-sonnet-4-5· Anthropic· FallbackSuccess with fallback4.12 s2,204$0.0118
gpt-4.1-mini· OpenAI· Rate limitedFailed766 ms0$0.00
Guardrails· Prompt Injection· BlockedBlocked41 ms0$0.00
Completed without LLM callNo model received it39 ms0$0.00
The Requests list, with one sample row for each result.

A Fallback row means that the first model failed and a fallback model returned the response.

Read a trace

Click a row to open the trace of the request. The trace shows each stage of the request as a bar on one timeline. Use the bars to find the stage that took the time. The top of the trace shows the trace ID, the provider key when the request made an LLM call, the endpoint, the time, the total latency, the cost and the number of events.

5c74572e-0819-4e80-8619-afdfda1ac60aOptiak keyResponses15/10/2026, 08:23:432.84 s$0.000416 events
Event
Gateway 2.84 s
Status
200
Method
POST
Endpoint
/v1/responses
Latency
2.84 s
Planner 2.83 s
Smart routing
No
Model
gpt-4.1-mini
Provider
OpenAI
Latency
2.83 s
Zero data retention
Yes
Block training providers
Yes
Guardrails PII 38 ms
Outcome
Redacted
Action
Redact
Stage
Input
PII entity types
EMAIL_ADDRESS
PII matches
1
Context build 62 ms
Token change
~−18.4%
Max input tokens
1,047,576
Smart Compression 56 ms
Action
Optimize
Items modified
3
Token change
~−18.4%
LLM Call 2.69 s
Model
gpt-4.1-mini
Provider
OpenAI
Data residency
EU
Latency
2.69 s
Provider key
Optiak key
Streaming
No
Input tokens
1,204
Cache read
0
Output tokens
312
Total tokens
1,516
The trace of one request, with sample data. Click a stage to see its details.
StageWhat it shows
GatewayThe HTTP status, method, endpoint and latency. For a tool call, it shows the operation and latency. See Gateway.
GuardrailsOne stage for each check, with its outcome, action, input or output, and block response. A Sensitive Data check also shows the entity types it found. See Guardrails.
PlannerThe requested model and provider, and the governance rules that applied. See Data Governance.
RetrievalThe documents that the request retrieved, with the data source, file, page and chunk for each. See Data Integrations.
Context buildThe messages and tokens before and after the Context Engine. Each component, such as Smart Compression, has its own stage. See Context Engine.
Smart routingThe time that Smart Router took to choose a model. See Smart Router.
LLM CallThe model, provider, data residency and provider key. It also shows the tokens, cache use and streaming, and the tools that the model saw, called and received. A BYOK or custom provider key shows its name. See Models.
Tool executionThe tool name, provider, outcome, attempt and latency of each tool call. See Tools.

A trace shows only the stages that ran for that request.

Blocked, redacted and optimized requests

Blocked

An input check stops the request. No model receives it.

Gateway
Planner
Guardrails Prompt InjectionBlocked
LLM Call

Redacted

The check masks personal data. The request continues.

Gateway
Planner
Guardrails PIIRedacted
LLM Callmasked text

Optimized

The Context Engine removes tokens before the LLM Call.

Gateway
Planner
Context build−18%
Before · 6,580 tokensAfter · 5,370 tokens
LLM Call
Three sample traces. The marked stage explains the result.

The trace also shows a request blocked with Refusal as blocked. See Actions. A component in Audit (no action) mode records its result but does not change the request. See Context Engine.

Copyright © 2026