Sample data. These figures are not a customer bill.Learn more
parezenparezen
Devbox Agents
Team · Sample · cloud
Home
  • Get startedSoon
  • Audits
  • Overview
Analyse
  • Spend
  • Cost per taskLock
  • Agents
  • Model comparisonSoon
  • Budgets
  • AlertsSoon
  • Reports
  • PR cost checksSoon
  • AdvisorsSoon
  • Spend analysis
Optimise
  • RecommendationsSoon
  • Routing policiesSoon
  • Shadow testsSoon
  • CachingSoon
  • TrimmingSoon
  • BatchSoon
  • Waste detectorSoon
Gateway
  • SetupSoon
  • ProvidersSoon
  • ModelsSoon
  • API keysSoon
  • DeploymentsSoon
  • PlaygroundSoon
  • LogsSoon
Savings & billing
  • Savings history
  • Savings ledger
  • Bill match
  • Billing
  • Invoices
Settings
  • Data & privacySoon
  • OrganisationSoon
  • ProjectsSoon
  • TeamSoon
  • RolesSoon
  • SSOSoon
  • Audit logSoon
Plan: Team · Sample ↗
DocsHelp

Sample data. Not a customer bill.

Devbox Agents/Playground

Playground

Planned

Sends a test request through a policy and shows the decision.

View
Sample reply for Code review agent. Parezen served openai/gpt-4.1-mini after the code review agent policy. This text is simulated and was not sent to a provider.
Export
curl https://api.parezen.com/v1/chat/completions \
  -H "Authorization: Bearer $PAREZEN_API_KEY" \
  -H "X-Parezen-Route: code-review-agent" \
  -d '{"model":"openai/gpt-4.1","messages":[{"role":"user","content":"Reply to this support ticket in two sentences."}]}'

Routing decision

Cheapest model that clears the route bar.

Requested
openai/gpt-4.1
Served
openai/gpt-4.1-mini
Provider
openai
Levers
right_size
Attempts
1 · ok
Tokens
640 in / 140 out
Estimated cost
$0.00048
Baseline
$0.0024
Latency
540 ms
Overhead
22 ms
Compare models