What is Google: Gemini 3.5 Flash's context window?

Google: Gemini 3.5 Flash supports a context window of 1,000,000 tokens, allowing you to process large documents and maintain long conversations.

How to use Google: Gemini 3.5 Flash API via Ofox?

Simply set your base URL to https://api.ofox.io/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

Google: Gemini 3.5 Flash

Name: Google: Gemini 3.5 Flash
Brand: google
Price: 1.5 USD
Availability: InStock
Rating: 5 (1 reviews)

Chat

google/gemini-3.5-flash

Compare Try in Playground Get Started

Gemini 3.5 Flash is Google's efficient multimodal model delivering near-Pro level coding and reasoning at Flash-tier cost and speed. Optimized for coding tasks and parallel agent execution with configurable thinking levels. Released May 20, 2026.

Context Window

Max Output Tokens

66K

Released

2026-05-20

Capabilities

VisionFunction CallingReasoningPrompt CachingWeb SearchAudio InputVideo InputPDF Input

Available Providers

Vertex

Supported Protocols

openaigemini

Providers

Vertex

Input Tokens

$1.5/M

Output Tokens

$9/M

Cache Read

$0.15/M

Cache Write

$0.83/M

Audio Input

$3/M

Cached Audio

$0.3/M

Web Search

$0.014/R

Protocols

openai/v1/chat/completions

gemini

Code Examples

from google import genai

client = genai.Client(
    api_key="YOUR_OFOX_API_KEY",
    http_options={"api_version": "v1beta", "base_url": "https://api.ofox.io/gemini"},
)

response = client.models.generate_content(
    model="google/gemini-3.5-flash",
    contents="Hello!",
)

print(response.text)

Benchmarks

LMArena ↗Evaluated as gemini-3.5-flash-medium

Google: Gemini 3.5 Flash scores 1475 in the Overall category of the LMArena text leaderboard (style control), ranking #18 of 374 models based on 10,317 human preference votes (updated 2026-07-12).

Benchmark scores for gemini-3.5-flash-medium on LMArena
Category	Arena Score	95% CI	Rank	Votes
Overall	1475	1468–1482	#18 of 374	10,317
Hard Prompts	1494	1486–1502	#20 of 374	6,930
Coding	1508	1497–1519	#38 of 369	3,112
Math	1483	1457–1508	#14 of 362	495
Creative Writing	1470	1455–1485	#9 of 372	1,774
Instruction Following	1463	1452–1473	#26 of 374	3,603
Chinese	1530	1502–1557	#8 of 344	505

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.