Gemini 3 Flash Preview Search
Google logo

Gemini 3 Flash Preview Search

gemini-3-flash-preview-search
Google
Gemini-3-flash-preview-search integrates Google's official search functionality; the search feature incurs an additional separate fee log directly incorporated into the scoring, but the log details are not displayed; this will be fixed in the future to show the details; it only supports OpenAI-compatible format calls and does not support the Gemini SDK; for the Gemini native SDK, please directly set the official search parameters.

Pricing

PricingCache ReadInput AudioInput Audio Cached Web SearchCache Storage
$0.500$3.000
$0.05/M tokens$1/M tokens$0.1/M tokens$0.014/request$1/h/M tokens

Input Modalities

  • Text
  • Vision
  • Audio

Output Modalities

  • Text

Capabilities

  • Thinking
  • Web
  • Tools
  • Tool calling
  • Structured outputs

Providers

VertexAI gemini-3-flash-preview-search
Pricing$0.500$3.000
Cache Read$0.05/M tokens
Input Audio$1/M tokens
Input Audio Cached $0.1/M tokens
Web Search$0.014/request
Cache Storage$1/h/M tokens
Context1M
Max output65K
Latency50.9S
Throughput142.0TPS
Uptime
98.91% uptime 2 days ago
99.26% uptime yesterday
97.84% uptime today
Google AI Studio gemini-3-flash-preview-search
Pricing$0.500$3.000
Cache Read$0.05/M tokens
Input Audio$1/M tokens
Input Audio Cached $0.1/M tokens
Web Search$0.014/request
Cache Storage$1/h/M tokens
Context1M
Max output65K
Latency3.9S
Throughput153.1TPS
Uptime
100.00% uptime 2 days ago
0.00% uptime yesterday
100.00% uptime today

Performance for gemini-3-flash-preview-search

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview-search",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

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

Frequently asked questions

What is Gemini 3 Flash Preview Search?

Gemini-3-flash-preview-search integrates Google's official search functionality; the search feature incurs an additional separate fee log directly incorporated into the scoring, but the log details are not displayed; this will be fixed in the future to show the details; it only supports OpenAI-compatible format calls and does not support the Gemini SDK; for the Gemini native SDK, please directly set the official search parameters.