Calculate the cost of using gemini-3.5-transcribe from Vertex AI for your AI applications
Pricing data last updated:
Mode: Audio Transcription
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gemini-3.5-transcribe is an audio transcription model from Vertex AI. It is priced at $0.0001 per second of audio.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Similar audio transcription models from other providers
The most comparable audio transcription models to gemini-3.5-transcribe are: gpt-4o-mini-transcribe from Azure ($1.25/1M input tokens); gpt-4o-transcribe from Azure ($2.50/1M input tokens); gpt-4o-transcribe-diarize from Azure ($2.50/1M input tokens); gpt-4o-transcribe-diarize from OpenAI ($2.50/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
gemini-3.5-transcribe is priced based on audio seconds. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected audio seconds volume and the calculator will show the total cost breakdown.