Unlock exclusive introductory pricing for the newly launched Gemini 3.5 Flash.
G

Gemini 3 Flash

入力:$0.4/M
出力:$2.4/M
文脈:1,048,576
最大出力:65.5k
リリース日:Dec 16, 2025

Gemini 3 Flash is a lightweight, efficient multimodal large-scale model from Google tailored for real-world scenarios that require fast responses and low latency.

新着
商用利用

Gemini 3 FlashのPlayground

Gemini 3 FlashのPlaygroundを探索 — モデルをテストし、リアルタイムでクエリを実行するインタラクティブな環境。プロンプトを試し、パラメータを調整し、即座に反復して開発を加速し、ユースケースを検証します。

What is Gemini 3 flash

“Gemini 3 Flash” is the Flas h/fast member of the Gemini-3 family: a lighter, lower-latency, cost-efficient variant of Google’s Gemini-3 models intended for high-throughput, real-time and scale-sensitive applications. A variant of the Gemini API model family that lets developers call a low-latency, cost-optimized Gemini 3 style model over CometAPI's API (same API surface as other Gemini models). It exposes the same multimodal inputs and structured output tools but prioritizes inference speed and throughput.

Main features :

  • Low latency / high throughput: tuned for fast responses and cost efficiency (Flash design point).
  • Multimodal input support: text, images, video snippets and audio in many Flash variants (API model entries list supported input types per variant).
  • Function calling & structured outputs: JSON/structured output enforcement for integration with tools and agents.
  • Agent/Tooling support: integrates with Google Search grounding, function/tool calling, and agent frameworks in the Gemini ecosystem.

How Gemini 3 Flash compares to other models

  • Versus Gemini-3 Pro (same family): Flash = speed/cost optimized; Pro = higher reasoning, multimodal fidelity, and Deep Think. Choose Flash for real-time UIs; Pro for accuracy-sensitive tasks.
  • Versus previous Gemini (2.5 Flash): Gemini-3 family improves reasoning and multimodal performance; Flash design point continues to target price/performance. If you currently use 2.5 Flash, Gemini-3 Fast/Flash is intended to give better quality at similar latency/cost.

Practical use cases (where Flash wins)

  • Realtime chatbots & voice agents: low latency for conversational UIs and streaming audio applications.
  • Customer support & high-volume summarization: cost-efficient summarization of long transcripts at scale.
  • Edge or embedded inference where response time matters: use flash/lite style variants for tight SLAs.
  • Mass document parsing / ingestion pipelines: Flash for indexing and pre-processing; escalate to Pro for high-value extraction/analysis.
  • Realtime code assistants / IDE plugins: fast code completions with lower billing cost (validate with Pro for complex refactors).

How to access Gemini 3 flash API

Step 1: Sign Up for API Key

Log in to cometapi.com. If you are not our user yet, please register first. Sign into your CometAPI console. Get the access credential API key of the interface. Click “Add Token” at the API token in the personal center, get the token key: sk-xxxxx and submit.

Step 2: Send Requests to Gemini 3 flash API

Select the “gemini-3-flash” endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience. Replace <YOUR_API_KEY> with your actual CometAPI key from your account. base url is Gemini Generating Content and Chat.

Insert your question or request into the content field—this is what the model will respond to . Process the API response to get the generated answer.

Step 3: Retrieve and Verify Results

Process the API response to get the generated answer. After processing, the API responds with the task status and output data.

See also Gemini 3 Pro Preview API

よくある質問

Gemini 3 Flashの料金

Gemini 3 Flashの競争力のある価格設定をご確認ください。さまざまな予算や利用ニーズに対応できるよう設計されています。柔軟なプランにより、使用した分だけお支払いいただけるため、要件の拡大に合わせて簡単にスケールアップできます。Gemini 3 Flashがコストを管理しながら、お客様のプロジェクトをどのように強化できるかをご覧ください。

Correction: gemini-3-flash variants (same price across variants)

Model familyVariant (model name)Input price (USD / 1M tokens)Output price (USD / 1M tokens)
gemini-3-flashgemini-3-flash$0.40$2.40
gemini-3-flashgemini-3-flash-preview$0.40$2.40
gemini-3-flashgemini-3-flash-all$0.40$2.40
gemini-3-flashgemini-3-flash-thinking$0.40$2.40
gemini-3-flashgemini-3-flash-preview-thinking$0.40$2.40

Gemini 3 FlashのサンプルコードとAPI

Gemini 3 Flash is a text-only large language model (LLM) exposed through CometAPI’s hosted API (and mirrored by vendor inference layers). The API supports standard chat/completion patterns, streaming responses, function/tool invocation, structured JSON output, and several “thinking” modes designed for agent-style workflows (interleaved / preserved / turn-level thinking).

#!/bin/bash

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash:generateContent" \
  -H "Authorization: $COMETAPI_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Explain how AI works in a few words"
          }
        ]
      }
    ]
  }'

cURL Code Example

#!/bin/bash

curl "https://api.cometapi.com/v1beta/models/gemini-3-flash:generateContent" \
  -H "Authorization: $COMETAPI_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Explain how AI works in a few words"
          }
        ]
      }
    ]
  }'

Python Code Example

from google import genai
import os

# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com"

client = genai.Client(
    http_options={"api_version": "v1beta", "base_url": BASE_URL},
    api_key=COMETAPI_KEY,
)

response = client.models.generate_content(
    model="gemini-3-flash",
    contents="Explain how AI works in a few words",
)

print(response.text)

JavaScript Code Example

// Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
const api_key = process.env.COMETAPI_KEY;
const base_url = "https://api.cometapi.com/v1beta";
const model = "gemini-3-flash";
const operator = "generateContent";

async function main() {
  const response = await fetch(`${base_url}/models/${model}:${operator}`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: api_key,
    },
    body: JSON.stringify({
      contents: [
        {
          parts: [{ text: "Explain how AI works in a few words" }],
        },
      ],
    }),
  });

  const data = await response.json();
  console.log(data.candidates[0].content.parts[0].text);
}

await main();

Gemini 3 Flashのバージョン

Gemini 3 Flashに複数のスナップショットが存在する理由としては、アップデート後の出力変動により旧版スナップショットの一貫性維持が必要な場合、開発者に適応・移行期間を提供するため、グローバル/リージョナルエンドポイントに対応する異なるスナップショットによるユーザー体験最適化などが考えられます。各バージョンの詳細な差異については、公式ドキュメントをご参照ください。

Model idDescriptionAvailabilityRequest
gemini-3-flash-allThe technology used is unofficial and the generation is unstable but Direct Internet etc，Chat format✅Chat format
gemini-3-flashAutomatically points to the latest model✅Gemini Generating Content
gemini-3-flash-previewOfficial Preview✅Gemini Generating Content