Gemini 3.1 Flash Live Preview

GoogleMCP Tool CallReasoning

google/gemini-3.1-flash-live-previewClosed API

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

Benchmark Pricing$0.75 / 1M in$4.50 / 1M out

Context: 131,072 tokens•Max Output: 65,536 tokens•Knowledge: 2025-01•Released: 2026-03-26

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output65,53665.5K tokens

LicenseProprietaryCloud API only

Input Modalities

TextVisionAudioVideo

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Gemini 3.1 Flash Live Preview natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Gemini 3.1 Flash Live Preview via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.GOOGLE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "google/gemini-3.1-flash-live-preview",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);