Skip to content

Cost Management

The pipeline enforces token budgets at two levels to prevent runaway LLM costs.

Cost Ceilings

  • Per-article ceiling — each produce_article run has a maximum token budget. If exceeded, the pipeline stops and alerts
  • Monthly budget — aggregate monthly token spend is tracked across all flows. Alerts fire at configurable thresholds

Model Selection Strategy

Costs are managed by choosing the right model for each task:

  • Sonnet (more expensive) — creative writing, research synthesis, complex reasoning
  • Haiku (cheaper) — classification, scoring, structured evaluation

Image Generation Costs

DALL-E 3 image generation is tracked separately from token costs:

Size Cost per Image
1024×1024 $0.04
1024×1792 $0.08
1792×1024 $0.08

Image generation is optional — set OPENAI_API_KEY to enable. Articles without featured images proceed normally.

Tracking

Token usage is logged per agent call via the cost tracker. The dashboard Analytics page shows cost trends over time.

The current_flow_name ContextVar threads the active flow name to call_agent() for per-flow cost ceiling enforcement without modifying agent signatures.