Gemini 3.5 Transcribe Live
gemini-3.5-transcribe-livePricing
List prices at Vertex AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.00 | $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$1,575
- RAG over documents2,000 requests a day, 8K in / 0.6K out$756
- Coding agent1,000 requests a day, 40K in / 2K out$1,260
- Overnight batch20,000 requests a day, 4K in / 0.4K out$5,040
Where to run it
2 hosts serve Gemini 3.5 Transcribe Live. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Vertex AICloud gemini-3.5-transcribe-live | $0.00 / $21.00 | gemini-3.5-transcribe-live | |
Google AI StudioLab API gemini-3.5-transcribe-live | $3.50 / $21.00 +50% vs headline | gemini-3.5-transcribe-live |
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
- Text
- Produces
- Text
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
No cheaper Google model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
No cheaper open-weight match.
Call it
Using Vertex AI's API.
from google import genai
client = genai.Client() # reads GEMINI_API_KEY
response = client.models.generate_content(model="gemini-3.5-transcribe-live", contents="Hello")
print(response.text)curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-transcribe-live:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Hello"}]}]}'from litellm import completion
response = completion(
model="vertex_ai/gemini-3.5-transcribe-live",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemini 3.5 Transcribe Live cost?
On Vertex AI, Gemini 3.5 Transcribe Live costs $21.00 per million output tokens.
Which APIs offer Gemini 3.5 Transcribe Live?
Gemini 3.5 Transcribe Live runs on 2 APIs: Vertex AI and Google AI Studio.
What is Gemini 3.5 Transcribe Live's context window?
131K tokens, with up to 66K tokens in one reply.
Is Gemini 3.5 Transcribe Live being retired?
No retirement date is scheduled for it on any API we track.
What is Gemini 3.5 Transcribe Live's API model id?
Use gemini-3.5-transcribe-live with Vertex AI.
Sources
Raw catalog entry for gemini-3.5-transcribe-live on Vertex AI
{
"input_cost_per_audio_token": 0.0000035,
"input_cost_per_second": 0.0000875,
"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"
}