Google Gemini

Google's Gemini API for text, vision, and multimodal AI tasks via Google AI Studio. Roiva verifies connectivity and is structured to ingest per-model usage data when Google exposes a usage aggregation endpoint. For GCP-billed Gemini usage today, use the BigQuery integration with a billing export query.

← All integrations

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.

Model Usage

gemini.usage.input_tokens Input Tokens count

gemini.usage.output_tokens Output Tokens count

gemini.usage.total_tokens Total Tokens count

gemini.usage.request_count Request Count count

gemini.usage.<model_slug>.input_tokens Per-model input tokens (dynamic, e.g. gemini.usage.gemini_2_0_flash.input_tokens) count

gemini.usage.<model_slug>.output_tokens Per-model output tokens (dynamic) count

gemini.usage.<model_slug>.total_tokens Per-model total tokens (dynamic) count

gemini.usage.<model_slug>.request_count Per-model request count (dynamic) count

Common use cases

Track Gemini API token usage per initiative
Monitor usage across Gemini models (Flash, Pro, Ultra)
Measure cost-per-task for AI features built on Gemini

How to connect

In Google AI Studio: Go to aistudio.google.com and generate an API key
Back in Roiva: Paste the key here and save the connection
Back in Roiva: After connecting, link this connection to an initiative on the Initiatives tab

Tips for capturing value

Google AI Studio does not yet expose a usage aggregation API — connecting verifies your key is valid and the integration will start producing metrics automatically when Google adds one
For GCP-billed Gemini usage tracking today, use the BigQuery integration with a billing export query

Google Gemini

Coming Soon

Google Gemini integration is coming soon. Sign up to get notified when it's available.

Join the waitlist →

Related integrations

OpenAI

Anthropic