Gemini 3.8 Live
Google logo

Gemini 3.8 Live

gemini-3.8-livellms.txt
Google
New
Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency, audio-to-audio voice interaction experience, enabling real-time conversations without inference delays. It supports interleaved reasoning, asynchronous and synchronous function calling, and built-in proactive audio processing capabilities.

Pricing

Audio input $3.00/M, audio output $12/M. Text input $0.75/M, text output $4.5/M.

Input Modalities

  • Text
  • Vision
  • Audio
  • Video

Output Modalities

  • Text
  • Audio

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Audio output
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

VertexAI gemini-3.8-live
Pricing$2$0
Input Text$0.75/M tokens
Input Image$1/M tokens
Input Video$1/M tokens
Input Audio$3/M tokens
Output Text$4.5/M tokens
Output Audio$12/M tokens
PrecisionⓘNot Disclosed
Latency-
Throughput-
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for gemini-3.8-live

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Frequently asked questions

What is Gemini 3.8 Live?

Gemini 3.8 Live is a multimodal AI model from Google that delivers a low-latency, audio-to-audio voice interaction experience, enabling real-time conversations without inference delays. It supports interleaved reasoning, asynchronous and synchronous function calling, and built-in proactive audio processing capabilities.