Gemini Live API (video input)

Overview

Best for: Cheapest realtime 'see and talk' assistant; video input adds only fractions of a cent per minute.

At a glance

Price is video input only on Gemini 3.8 Live (audio billed on top). Audio plus video sessions capped at 2 min without session management. fps is max input frame rate.

Features

• camera and screen frames as JPEG/PNG
• mediaResolution control of tokens per frame
• session resumption / compression for longer sessions

Pricing

Free tier: See Gemini API free tier (not checked here).

Source: ai.google.dev

Setup

1. Get a Gemini API key (or use ephemeral tokens in browsers).
2. Open a Live session with response_modalities AUDIO and media_resolution LOW.
3. Send JPEG frames at 1 fps or less with send_realtime_input(video=...).
4. Enable context window compression for sessions over 2 minutes.

Endpoint

Live API WebSocket via google-genai SDK

Authentication

GEMINI_API_KEY or ephemeral token

import asyncio
from google import genai
from google.genai import types

client = genai.Client()  # GEMINI_API_KEY
config = {
    "response_modalities": ["AUDIO"],
    "media_resolution": "MEDIA_RESOLUTION_LOW",  # 70 tokens/frame on Gemini 3
}

async def main(jpeg_frames):
    async with client.aio.live.connect(model="gemini-3.8-live", config=config) as s:
        for jpg in jpeg_frames:            # at most 1 frame per second
            await s.send_realtime_input(
                video=types.Blob(data=jpg, mime_type="image/jpeg"))
            await asyncio.sleep(1)
        await s.send_realtime_input(text="What do you see?")
        async for msg in s.receive():
            pass  # handle audio chunks / transcripts

# asyncio.run(main(frames))

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Plus 9 warnings that apply to all avatars and live video APIs. See category warnings.

Limits

• Max 1 frame per second
• Audio plus video sessions limited to 2 minutes unless you use session management/compression
• Context window 128k tokens for native audio models

Models and products

Docs and sources

Docs

• Live API capabilities
• Media resolution
• Pricing

Sources used

• ai.google.dev/gemini-api/docs/pricing
• ai.google.dev/gemini-api/docs/media-resolution
• ai.google.dev/gemini-api/docs/live-api/capabilities