impulse

Gemini 3.8 Live

Frontier labRealtime
API id gemini-3.8-live
Input / 1M
$0.75
at Google AI Studio
Output / 1M
$4.50
at Google AI Studio
Context window
131K
tokens
Max output
66K
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Pricing

List prices at Google AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.75$4.50

What it costs a month

At Google AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$563
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$522
  • Coding agent1,000 requests a day, 40K in / 2K out$1,170
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,880
Use your own numbers

Where to run it

2 hosts serve Gemini 3.8 Live. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
gemini-3.8-live
$0.75 / $4.50
gemini-3.8-live
$0.75 / $4.50
Show 1 more listings: regions, snapshots and variants
Google AI Studio
Alias
gemini-3.8-live
$0.75 / $4.50

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioImagesTextVideo
Produces
AudioText
Features
Audio inputAudio outputBuilt-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Google AI Studio.

Smaller Google models

Other frontier labs

Open-weight picks

No cheaper open-weight match.

Call it

Using Google AI Studio's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="gemini-3.8-live", contents="Hello")
print(response.text)

Quick answers

How much does Gemini 3.8 Live cost?

On Google AI Studio, Gemini 3.8 Live costs $0.75 per million input tokens and $4.50 per million output tokens.

Which APIs offer Gemini 3.8 Live?

Gemini 3.8 Live runs on 2 APIs: Google AI Studio and Vertex AI.

What is Gemini 3.8 Live's context window?

131K tokens, with up to 66K tokens in one reply.

Is Gemini 3.8 Live being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Gemini 3.8 Live?

Models that cost less and keep most of what it can do: Gemini Live 2.5 Flash Native Audio on Vertex AI (48% less) and GPT Realtime 2.1 Mini on OpenAI (38% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Gemini 3.8 Live's API model id?

Use gemini-3.8-live with Google AI Studio.

Sources

Raw catalog entry for gemini-3.8-live on Google AI Studio
{
  "input_cost_per_audio_token": 0.000003,
  "input_cost_per_image_token": 0.000001,
  "input_cost_per_token": 7.5e-7,
  "input_cost_per_video_per_second": 0.000033333333333333335,
  "litellm_provider": "gemini",
  "max_input_tokens": 131072,
  "max_output_tokens": 65536,
  "mode": "realtime",
  "output_cost_per_audio_token": 0.000012,
  "output_cost_per_token": 0.0000045,
  "source": "https://ai.google.dev/gemini-api/docs/pricing",
  "supported_endpoints": [
    "/v1/realtime"
  ],
  "supported_modalities": [
    "text",
    "image",
    "audio",
    "video"
  ],
  "supported_output_modalities": [
    "text",
    "audio"
  ],
  "supports_audio_input": true,
  "supports_audio_output": true,
  "supports_function_calling": true,
  "supports_vision": true,
  "supports_web_search": true,
  "gemini_audio_only_live": true,
  "supports_response_schema": false
}