LLM Reference
Google AI Studio

Using Gemini 3.8 Live on Google AI Studio

Implementation guide · Gemini 3.8 · Google DeepMind

Serverless

Google AI Studio exposes Gemini 3.8 Live through model ID gemini-3.8-live. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-17. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Google AI Studio and generate an API key.
  2. 2
    Use the Google AI Studio SDK or REST API to call gemini-3.8-live — see the documentation for request format.
  3. 3
    You'll be billed $0.75/1M input, $4.50/1M output tokens. See full pricing.

Code Examples

Install
pip install google-genai
API key
GOOGLE_API_KEY
Model ID
gemini-3.8-live

Use the model name directly, e.g. "gemini-2.0-flash", "gemini-1.5-pro", or "gemini-2.5-pro-preview-05-06".

import os
from google import genai

client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
response = client.models.generate_content(
    model="gemini-3.8-live",
    contents="Hello"
)
print(response.text)

Pricing on Google AI Studio

TypePrice (per 1M)
Input tokens$0.75
Output tokens$4.50
Audio input$3.00

Capabilities

VisionMultimodalReasoningJSON / Tool useAudio

About Gemini 3.8 Live

Gemini 3.8 Live (API model code gemini-3.8-live) is Google DeepMind's low-latency native speech-to-speech / Live API model for real-time voice agents and dialogue, announced September 15, 2026 (blog publish ~17:00 UTC). First-party AI.dev model page: inputs text/images/audio/video; outputs text and audio; input limit 131,072 tokens; output limit 65,536; Live API supported; function calling supported; interleaved reasoning (Thinking) supported; search grounding supported; structured outputs / caching / code execution / batch not supported. Stable id gemini-3.8-live.

Model Specs

Released2026-09-15
Context131k