What is Google: Gemini 3.1 Pro Preview's context window?

Google: Gemini 3.1 Pro Preview supports a context window of 1,048,576 tokens, allowing you to process large documents and maintain long conversations.

How to use Google: Gemini 3.1 Pro Preview 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 3.1 Pro Preview

Name: Google: Gemini 3.1 Pro Preview
Brand: google
Price: 2 USD
Availability: InStock

Chat

google/gemini-3.1-pro-preview

Compare Try in Playground Get started

Gemini 3.1 Pro Preview is the next generation of Google's Gemini series: a natively multimodal reasoning model positioned as Google's most advanced option for complex tasks. It can comprehend vast datasets and difficult problems spanning several information sources at once — text, audio, images, video and entire code repositories — and adds tool use, prompt caching, PDF input and web search on top. Context window: 1M tokens, output: 64K. This is a preview release, so behaviour may still change. Available via OpenAI and Gemini protocols.

Context Window

Max Output Tokens

66K

Released

2026-02-19

Capabilities

VisionFunction CallingReasoningPrompt CachingWeb SearchAudio InputVideo InputPDF Input

Available Providers

Vertex

Supported Protocols

openaigemini

Providers

Vertexprovider.type: "google_vertex"

Input Tokens

$2/M

Output Tokens

$12/M

Cache Read

$0.2/M

Cache Write

$4.5/M

Audio Input

$2/M

Cached Audio

$0.2/M

Web Search

$0.014/R

Protocols

openai/v1/chat/completions

gemini

Playground

Open in OfoxChat

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-3.1-pro-preview",
    contents="Hello!",
)

print(response.text)

Uptime & Status

Benchmarks

LMArena ↗Evaluated as gemini-3.1-pro-preview

Google: Gemini 3.1 Pro Preview scores 1486 in the Overall category of the LMArena text leaderboard (style control), ranking #9 of 374 models based on 79,682 human preference votes (updated 2026-07-12).

Benchmark scores for gemini-3.1-pro-preview on LMArena
Category	Arena Score	95% CI	Rank	Votes
Overall	1486	1482–1489	#9 of 374	79,682
Hard Prompts	1506	1502–1511	#9 of 374	50,878
Coding	1521	1515–1527	#18 of 369	21,775
Math	1491	1481–1501	#12 of 362	4,320
Creative Writing	1478	1472–1485	#8 of 372	13,330
Instruction Following	1481	1476–1486	#10 of 374	26,008
Chinese	1527	1517–1538	#11 of 344	4,170

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.