Monitor Flow executions, AI token usage, and costs to understand and optimize your Runtype spending.
Accessing usage data
- Go to Settings → Usage
- View usage analytics with charts and breakdowns
- Switch between 7-day, 30-day, or 90-day views
Key metrics
The Usage tab shows several chart views:
- Spend over time — Track spending trends
- Spend by category — See where costs are distributed
- Spend by model — Identify which models drive the most cost
- Spend by tool — See tool-level cost attribution
- Executions over time — Monitor execution volume
Usage data refreshes automatically. The tab shows a friendly empty state until you have run your first Flow or Agent.
Cost optimization tips
Use cheaper models when possible
GPT-5.4 Nano is significantly cheaper than GPT-5.4 for simple tasks.
Reduce max tokens
Lower max tokens limits prevent unnecessarily long responses.
Cache API responses
Store results in Records instead of making duplicate API calls.
Batch processing
Process multiple items per execution to amortize overhead costs.
Monitor and optimize prompts
Shorter, more focused prompts reduce input token costs.
Understanding provider billing
When using BYOK:
- Runtype estimates costs based on token usage
- Actual charges come from providers (OpenAI, Anthropic, etc.)
- Check provider dashboards for precise billing
- Runtype’s estimates help predict costs but aren’t invoices
Next steps
- Billing and plans to manage your subscription
- Connecting AI model providers for BYOK setup
- Running an Eval to test cheaper model alternatives
- Working with Logs to investigate expensive executions
