How spend is metered
Spend is tracked per run and per month. The Usage tab shows month-to-date totals, per-run breakdowns, and budget remaining.Viewing usage
Budget caps
Set on the project viaPATCH /smr/projects/{project_id}:
| Field | Scope | What happens when hit |
|---|---|---|
run_usd_cents | Single run | Run stops immediately with stop_reason: budget_exhausted |
monthly_usd_cents | Calendar month across all runs | New runs are blocked until the next month |
timebox_seconds when triggering to cap run duration; when hit, the run stops with stopped.
Entitlements
Managed Research requires a Pro or Team plan. CheckGET /smr/projects/{project_id}/entitlements/managed_research for access status.
Pricing
Managed Research passes through LLM costs at cost. Orchestrator and worker agents run ongpt-5.2 by default; the optimization loop (GEPA/MIPRO) uses whatever model is configured in synth_ai.policy_optimization.policy.model.
Typical run costs depend on the number of trials, the size of your dataset, and the model. A small GEPA run on Banking77 (n_trials=4, small dataset) costs a few cents. A full overnight optimization run with many trials will cost more — set run_usd_cents to cap it.