Gemini 3.8 Live
Google Gemini 3.8 real-time bidirectional Live API model for low-latency voice agents. Supports text, image, and audio input with text and audio output.
- Input price
- $0.675–$0.825list $0.7510% off
- Output price
- $4.05–$4.95list $4.5010% off
- Context
- 131K
- Max output
- 66K
- 30-day uptime
- —
- Released
- 2026-09-15
InputTextImageAudioOutputTextAudio
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
Prices vary by provider. Showing Google Vertex AI, the lowest. Pick a provider above to see its prices.
- Input
- $0.675list $0.7510% off
- per 1M tokens
- Output
- $4.05list $4.5010% off
- per 1M tokens
- Cache read
- $0.675list $0.7510% off
- per 1M tokens
- Reasoning output
- $4.05list $4.5010% off
- per 1M tokens
- Audio input
- $2.70list $3.0010% off
- per 1M tokens
- Audio output
- $10.80list $12.0010% off
- per 1M tokens
- Image input
- $0.90list $1.0010% off
- per 1M tokens
- Web search
- $0.0126list $0.01410% off
- per request
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.00406
- 3K input tokens
- Agent first turn
- $0.0695
- 100K tokens of context, none cached
- Each later agent turn
- $0.0709
- context read from cache, plus 2K new tokens
- 20-turn agent task
- $1.42
- first turn plus 19 more
Try it
Talk with the model in real time, on your balance. Billed by usage like any API request; your browser will ask for the microphone, and headphones work best.
Similar models
Other models with the same output types at a similar price.