What is Gemini 3.8 Live?

Gemini 3.8 Live is a model from Google Gemini AI, released on Sep 15, 2026. Google's native-audio Gemini model for real-time voice and video conversations over the Live API.

How much does Gemini 3.8 Live cost?

On the Respan gateway, Gemini 3.8 Live costs $0.75 per 1M input tokens and $4.50 per 1M output tokens on Google Gemini AI, after gateway discounts.

Which providers serve Gemini 3.8 Live on Respan?

Gemini 3.8 Live is served by Google Gemini AI through 2 routes. Google Gemini AI requires your own provider API key (BYOK).

What is Gemini 3.8 Live's context window?

Gemini 3.8 Live accepts up to 131K tokens of context on its largest provider route.

How do I use Gemini 3.8 Live with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "gemini/gemini-3.8-live". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Gemini 3.8 Live

Google's native-audio Gemini model for real-time voice and video conversations over the Live API.

Input / output price: $0.75 / $4.50 per 1M
Context: 131K tokens
Released: Sep 15, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "gemini/gemini-3.8-live".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="gemini/gemini-3.8-live",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "gemini/gemini-3.8-live",

  messages: [{ role: "user", content: "Hello!" }],

});

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

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "gemini/gemini-3.8-live",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 routes from 1 provider, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read	Capabilities
Google Gemini AIBYOK only`gemini/gemini-3.8-live`	131K	$0.75/M	$4.50/M	$0.00/M	+2
Google Gemini AIBYOK only`gemini/gemini-3.8-live-extended-thinking`	131K	$0.75/M	$4.50/M	$0.00/M	+2