Gemini 3.5 Transcribe Live
Google Gemini 3.5 low-latency speech-to-text over the Live API for bidirectional streaming audio transcription.
- Audio input
- $3.85per 1M tokens
- Context
- 131K
- Max output
- 66K
- 30-day uptime
- —
- Released
- 2026-08-26
InputAudioOutputText
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
All prices for this model, by service tier.
- Input
- $3.85
- per 1M tokens
- Output
- $23.10
- per 1M tokens
- Cache read
- $3.85
- per 1M tokens
- Reasoning output
- $23.10
- per 1M tokens
- Audio input
- $3.85
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.0231
- 3K input tokens
- Agent first turn
- $0.397
- 100K tokens of context, none cached
- Each later agent turn
- $0.404
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $8.08
- first turn plus 19 more
Try it
Speak and watch the words appear, on your balance. Billed by usage like any API request, and your browser will ask for the microphone.
Similar models
Other models with the same output types at a similar price.