impulse

Gemini 3.5 Transcribe Live Preview

Frontier labTranscriptionPreview
API id gemini-3.5-transcribe-live-preview
Input / 1M
$3.50
at Vertex AI
Output / 1M
$21.00
at Vertex AI
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$3.50$21.00

What it costs a month

At Vertex AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$2,625
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$2,436
  • Coding agent1,000 requests a day, 40K in / 2K out$5,460
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$13,440
Use your own numbers

Where to run it

1 host serve Gemini 3.5 Transcribe Live Preview. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
gemini-3.5-transcribe-live-preview
$3.50 / $21.00

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
Audio
Produces
Text
Features
Audio input

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 Vertex AI.

Smaller Google models

Other frontier labs

Open-weight picks

Call it

Using Vertex AI's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="gemini-3.5-transcribe-live-preview", contents="Hello")
print(response.text)

Quick answers

How much does Gemini 3.5 Transcribe Live Preview cost?

On Vertex AI, Gemini 3.5 Transcribe Live Preview costs $3.50 per million input tokens and $21.00 per million output tokens.

Which APIs offer Gemini 3.5 Transcribe Live Preview?

Gemini 3.5 Transcribe Live Preview runs on 1 API: Vertex AI.

Is Gemini 3.5 Transcribe Live Preview being retired?

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

What are cheaper alternatives to Gemini 3.5 Transcribe Live Preview?

Models that cost less and keep most of what it can do: Gemini 3.5 Transcribe Live on Vertex AI (33% less), GPT-4o Transcribe on OpenAI (44% less), GPT-4o Transcribe Diarize on OpenAI (44% less) and Granite Speech 3.3 8B on Replicate (84% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Gemini 3.5 Transcribe Live Preview's API model id?

Use gemini-3.5-transcribe-live-preview with Vertex AI.

Sources

Raw catalog entry for gemini-3.5-transcribe-live-preview on Vertex AI
{
  "input_cost_per_audio_token": 0.0000035,
  "input_cost_per_token": 0.0000035,
  "litellm_provider": "vertex_ai",
  "mode": "audio_transcription",
  "output_cost_per_token": 0.000021,
  "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
  "supported_endpoints": [
    "/v1/realtime"
  ],
  "supported_modalities": [
    "audio"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_audio_input": true
}