Gemini 3 Flash Preview
Google Gemini 3 Flash Preview — pricing, 1049k context window, API cost calculator and alternatives.
By Google
Specs
- Provider
- Slug
- google/gemini-3-flash-preview
- Capabilities
- vision, tools, json_mode
Pricing freshness
- Tier
- standard
- Currency
- USD
- As of
- 2026-05-08 17:08 UTC
Pricing history
Tracking Gemini 3 Flash Preview pricing since 2026-05-08. We'll plot the chart here once it changes.
Quickstart — call Gemini 3 Flash Preview from your app
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-flash-preview:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GOOGLE_API_KEY" \
-d '{
"contents": [{"parts": [{"text": "Hello!"}]}]
}'Official docs: https://ai.google.dev/api/generate-content
# pip install google-genai
from google import genai
client = genai.Client() # reads GOOGLE_API_KEY from env
resp = client.models.generate_content(
model="gemini-3-flash-preview",
contents="Hello!",
)
print(resp.text)Official docs: https://ai.google.dev/api/generate-content
// npm install @google/genai
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: process.env.GOOGLE_API_KEY });
const resp = await ai.models.generateContent({
model: "gemini-3-flash-preview",
contents: "Hello!",
});
console.log(resp.text);Official docs: https://ai.google.dev/api/generate-content
Related models
Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.
Frequently asked questions
What is Gemini 3 Flash Preview?
Gemini 3 Flash Preview is a large language model API from Google with a 1M-token context window. It costs $0.5 per 1M input tokens and $3 per 1M output tokens.
How much does Gemini 3 Flash Preview cost?
Gemini 3 Flash Preview is priced at $0.5 per 1M input tokens and $3 per 1M output tokens via the Google API. A 50/50 input/output workload of 1M total tokens costs about $1.75.
What is the context window of Gemini 3 Flash Preview?
Gemini 3 Flash Preview supports up to 1M tokens of context per request — roughly 2097 pages of English text or 131072 lines of code at a typical density.
Does Gemini 3 Flash Preview support vision, tool use, or JSON mode?
Gemini 3 Flash Preview supports vision, tool/function calling, and structured JSON mode.
Who makes Gemini 3 Flash Preview?
Gemini 3 Flash Preview is built and operated by Google. Pricing, context window, and capabilities on this page are refreshed nightly from Google's public catalog.
Can I self-host Gemini 3 Flash Preview?
Gemini 3 Flash Preview is API-only — its weights are not publicly distributed by Google, so it cannot be self-hosted today.