AI
Anthropic
AI safety company and API provider for Claude — a family of models optimized for safety, accuracy, and nuanced reasoning.
What gets synced
Roiva writes these metric observations on each sync. Reference the key in a value formula to use this data in your ROI calculations.
API Usage
anthropic.usage.spend
Total Spend
currency
anthropic.usage.input_tokens
Input Tokens
count
anthropic.usage.output_tokens
Output Tokens
count
anthropic.usage.total_tokens
Total Tokens
count
anthropic.usage.<model_slug>.spend
Per-model spend (dynamic, e.g. anthropic.usage.claude_sonnet_4_6.spend)
currency
anthropic.usage.<model_slug>.input_tokens
Per-model input tokens (dynamic)
count
anthropic.usage.<model_slug>.output_tokens
Per-model output tokens (dynamic)
count
anthropic.usage.<model_slug>.total_tokens
Per-model total tokens (dynamic)
count
Common use cases
- Track Claude API spend per initiative to measure the cost side of AI ROI
- Monitor input and output token usage to identify efficiency opportunities
- Attribute AI costs to specific initiatives for accurate ROI calculation
- Compare cost-per-task before and after prompt or model optimizations
How to connect
- In Anthropic: Go to the Claude Console → Organization Settings → Admin Keys
- In Anthropic: Generate a new Admin API key (it will start with sk-ant-admin)
- Back in Roiva: Paste the key here — note this is different from a regular API key
- Back in Roiva: After connecting, link this connection to an initiative on the Initiatives tab
Tips for capturing value
- Admin API keys are required for usage data — regular API keys will return an authentication error
- Spend and token data is broken down by model, so you can see exactly which Claude model is driving costs
- Pairing Anthropic cost data with outcome data from your CRM or support platform gives you a complete ROI picture
Anthropic
Sign up to connect Anthropic and start tracking AI initiative outcomes.
Start free trial → Sign inRelated integrations
