Google Gemini

Google's Gemini API for text, vision, and multimodal AI tasks via Google AI Studio. Roiva is structured to ingest per-model usage data once Google exposes a usage aggregation endpoint. For Gemini usage billed through Google Cloud, track spend with the Google Cloud integration.

← 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_input_tokens Per-model input tokens (one row per model, the model in the row's dimensions) count

gemini.usage.model_output_tokens Per-model output tokens (one row per model, the model in the row's dimensions) count

gemini.usage.model_total_tokens Per-model total tokens (one row per model, the model in the row's dimensions) count

gemini.usage.model_request_count Per-model request count (one row per model, the model in the row's dimensions) 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

Tips for capturing value

Google AI Studio doesn't expose a usage aggregation API yet, so a direct connector would have nothing to sync
For Gemini usage billed through Google Cloud, connect the Google Cloud integration and create a Cloud Billing budget limited to the Gemini API — Roiva attributes each budget's spend to an initiative by its name

Google Gemini

Coming Soon

There's no direct Google Gemini connector yet. Usage billed through Google Cloud can be tracked today with the Google Cloud integration.

Get your exposure report → Talk to the founder →

Related integrations

OpenAI

Anthropic