Skip to Content
v0.8.0 · shippedNative iOS / Android / Flutter / Capacitor SDKs, A2A discovery, SOC 2 readiness, residency, BYO storage, BYOK. Read the changelog →
Admin consoleCost & usage
Clustering, judging, PDCA, drift, anomaly pipelines · · open live demo ↗

Cost & usage

Route: /cost

The Cost page shows LLM token consumption and estimated spend across all AI pipelines for the selected project and time range.


What’s tracked

PipelineModels logged
fix-workerPrimary model (Anthropic / OpenAI), per fix_attempts row
classify-reportClassifier model, per classifications row
judge-batchJudge model, per judge_results row
inventory-proposeInventory model, per inventory_proposals row
pdca-runnerPlanner model, per pdca_runs row
test-gen-from-reportTest generator model

Each row records model, prompt_tokens, completion_tokens, and cost_usd (estimated using public pricing at time of logging).


Charts

  • Daily spend — bar chart of estimated USD per day
  • By pipeline — donut chart showing which workflows consume the most tokens
  • By model — which models are used and what they cost
  • Token efficiency — completion tokens per successful fix (lower is better)

Controlling costs

LeverWhere to set it
Model selectionSettings → PDCA settings → Model (use a smaller model for planning)
Max iterationsSettings → PDCA settings → Max iterations per run
Fix worker retriesfix-worker retries on Zod validation failure — reduce max_retries in env
Integration health probe cadenceProbes run on demand; avoid automating frequent polling

Export

Click Export CSV to download the raw cost log for the selected date range. Useful for chargeback / showback reporting in multi-team setups.


Last updated on