BazaarLinkBazaarLink
Sign in

Gemini 3 Flash Preview

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

Intelligence#172 / 563
25
Artificial Analysis Intelligence Index
Speed#10 / 576
295.4
Output tokens per second (median)
Input Price#305 / 576
$0.50NT$ 16
USD / 1M tokens
Output Price#343 / 576
$3.00NT$ 97
USD / 1M tokens
First-token latency#513 / 576
4.99s
Time to first token (AA median)
ProviderGoogle
Released2025年12月
Model IDgoogle/gemini-3-flash-preview

Technical specifications

Context window
1M tokens
Reasoning
Yes
Input
TextImageFileAudioVideo
Output
Text

Pricing comparison

BazaarLink retail price alongside AA's observed market standard.

BazaarLink price our site

Input$0.50NT$ 16
Output$3.00NT$ 97
Cache read$0.05NT$ 2
Cache write$0.08NT$ 3
3:1 blended (est.)$1.13NT$ 36
All prices per 1M tokens. Supports TWD credit card / official invoice.

Market reference Artificial Analysis

Input$0.25
Output$1.50
Cache readAA not tracked
Cache writeAA not tracked
3:1 blended$0.56
Our price differs from AA reference by ~100%.
Source: artificialanalysis.ai

Independent benchmarks

Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.

Intelligence 25
Coding 35
Math
MMLU
GPQA 82
This modelCategory leader
Coding ability
#92out of 176 models
LiveCodeBench / SciCode and similar
Overall intelligence
#172out of 563 models
Aggregated across academic benchmarks
Time to first token
#513out of 576 models
AA 全球 p50:4.99 秒
Intelligence
25
Mid-tier
This model
25
Category leader
60
Median
15
Coding
35
Mid-tier
This model
35
Category leader
78
Median
36
GPQA
82%
This model
82%
Category leader
94%
Median
68%
HLE
16%
This model
16%
Category leader
53%
Median
7%
SciCode
42%
This model
42%
Category leader
60%
Median
33%
IFBench
77%
This model
77%
Category leader
83%
Median
44%
τ²-Bench Telecom
31%
This model
31%
Category leader
99%
Median
46%
AA-LCR
65%
This model
65%
Category leader
76%
Median
39%
Terminal-Bench Hard
24%
This model
24%
Category leader
66%
Median
14%

Top 5 — CodingCoding Index leaderboard

1GPT-5.6 Sol (xhigh)openai/gpt-5-6-sol-xhigh78$5 / $30
3GPT-5.6 Sol (high)openai/gpt-5-6-sol-high77$5 / $30
AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →

Quick Start

Use Gemini 3 Flash Preview via BazaarLink API — just change the base_url:

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://bazaarlink.ai/api/v1",
    api_key="sk-bl-YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="google/gemini-3-flash-preview",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://bazaarlink.ai/api/v1",
  apiKey: "sk-bl-YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "google/gemini-3-flash-preview",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Why use Gemini 3 Flash Preview via BazaarLink?

  • USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
  • OpenAI-compatible API — zero code changes required
  • Automatic failover — multi-provider redundancy for the same model
  • Chinese-language support — local team, instant help
Try Now← All Models

Frequently Asked Questions

What is Gemini 3 Flash Preview?

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

How much does the Gemini 3 Flash Preview API cost?

Gemini 3 Flash Preview costs $0.5000 per 1K input tokens and $3.0000 per 1K output tokens when accessed through BazaarLink.

How do I use Gemini 3 Flash Preview with the OpenAI SDK?

Set base_url to "https://bazaarlink.ai/api/v1" and use model ID "google/gemini-3-flash-preview". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.

What is the context window for Gemini 3 Flash Preview?

Gemini 3 Flash Preview supports a context window of 1,048,576 tokens.

Is Gemini 3 Flash Preview available for free?

Gemini 3 Flash Preview is a paid model. BazaarLink offers free trial credits on registration so you can test it without a credit card.

中轉站誠信檢測 · BazaarLink 獨家

已測試 endpoint
13
獨立 hosts
9
家族指紋一致率
54%
偵測到異常
11
資料範圍
過去 90

BazaarLink Probe 對聲稱提供此模型的 endpoint 進行家族指紋驗證與 V3 子模型對照。 如發現行為與真貨基準不符,會列入異常案例。

查看完整檢測報告 →

Related Models & Links

More from Google

Gemma 3 27b ItGemini 3.1 Flash Image PreviewGemini 2.5 ProGemma 2 27b ItGemini 3.1 Flash Lite PreviewGemma 3 4b It
All ModelsAPI DocumentationAPI Latency Probe
Support
Support
Hi! How can we help you?
Send a message and we'll get back to you soon.