Try Bifrost Enterprise free for 14 days.
Request access[ MODEL COMPARISON ]
Compare gemini-3.5-transcribe-live-preview with other models
Select another model to compare pricing, limits, and capabilities with gemini-3.5-transcribe-live-preview.
VS
Models
gemini-3.5-transcribe-live-previewvertex_ai
-
-
Input Cost
$3.50/M
-
Output Cost
$21.00/M
-
Mode
Audio Transcription
-
Supported Endpoints
/v1/realtime
-
Provider
Google Vertex AI
-
Scale with the Fastest LLM Gateway
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Comparison Insights
Comprehensive analysis based on the latest model metadata from the comparison table above.
What should I know about gemini-3.5-transcribe-live-preview?
Overview
- gemini-3.5-transcribe-live-preview is a audio transcription model provided by Google Vertex AI.
Pricing
- Input processing costs $3.50 per million tokens.
- Output generation costs $21.00 per million tokens.
Availability
- Available through the following endpoints: /v1/realtime.
What capabilities does gemini-3.5-transcribe-live-preview support?
- Accepts audio input, allowing for voice-based interactions and audio processing.
gemini-3.5-transcribe-live-preview Pricing Overview
At $3.50 per 1M input tokens and $21.00 per 1M output tokens, gemini-3.5-transcribe-live-preview ranks 12 out of 12 audio transcription models by input cost. It is more expensive compared to the median of $2.50 for audio transcription models, and is cheaper than 0% of models in this category.