Google: Gemini 3 Pro Preview

by Google

Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses. Built for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.

Avg Score

91.5%

232 answers

Avg Latency

10.7s

13 runs

Pricing

$2.00

input

$12.00

output

per 1M tokens

Context

1049K

tokens

Alternatives

Models with similar or better quality but different tradeoffs

Same Quality, Cheaper

Models with similar or better performance at a lower cost per token.

Model	Cost
Google: Gemini 3 Flash Preview	-96%
OpenAI: GPT-5.2	-74%
Google: Gemini 2.5 Pro	-7%

Same Quality, Faster

Models with similar or better performance but lower latency.

Model	Latency
Google: Gemini 3 Flash Preview	-83%
OpenAI: GPT-5.2	-54%
Google: Gemini 2.5 Pro	-9%

Same Cost, Better

Models at a similar price point with higher benchmark scores.

No alternatives found

Other Models from Google

Compare performance with other models from the same creator

Model	Score	Latency	Cost/1M
Google: Gemini 3 Flash Preview	90.8%	2.1s	$1.75
Google: Gemini 2.5 Pro	87.5%	9.9s	$5.63
Google: Gemini 2.5 Flash	80.5%	1.9s	$1.40
Google: Gemini 2.0 Flash	79.4%	1.8s	$0.25
Google: Gemini 2.5 Flash Lite	75.1%	1.4s	$0.25
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)	—	—	$7.00
Google: Gemini 2.5 Flash Image (Nano Banana)	—	—	$1.40
Google: Gemini 2.5 Flash Preview 09-2025	—	—	$1.40
Google: Gemini 2.5 Flash Lite Preview 09-2025	—	—	$0.25
Google: Gemini 2.5 Flash Image Preview (Nano Banana)	—	—	$1.40
Google: Gemma 3n 2B (free)	—	—	$0.0000
Google: Gemini 2.5 Pro Preview 06-05	—	—	$5.63
Google: Gemma 3n 4B	—	—	$0.0000
Google: Gemma 3n 4B	—	—	$0.03
Google: Gemini 2.5 Pro Preview 05-06	—	—	$5.63
Google: Gemma 3 4B	—	—	$0.0000
Google: Gemma 3 4B	—	—	$0.04
Google: Gemma 3 12B	—	—	$0.0000
Google: Gemma 3 12B	—	—	$0.07
Google: Gemma 3 27B	—	—	$0.0000
Google: Gemini 2.0 Flash Lite	—	—	$0.19
Google: Gemini 2.0 Flash Experimental (free)	—	—	$0.0000
Google: Gemma 2 27B	—	—	$0.65
Google: Gemma 2 9B	—	—	$0.06
Google: Gemma 3 27B	—	—	$0.09

Benchmark Performance

How this model performs across different benchmarks

Benchmark	Score	Rank
Karlsruhe Local Knowledge Benchmark	100.0%	1 / 35
Math Bench: Addition (1-10)	100.0%	7 / 35
Math Bench: Subtraction (1-10)	100.0%	7 / 35
Math Bench: Multiplication (1-10)	100.0%	7 / 35
Math Bench: Division (1-10)	100.0%	7 / 35
Math Bench: Arithmetic (1-100)	100.0%	14 / 35
Math Bench: Arithmetic (1-1000)	100.0%	7 / 35
Spatial Reasoning: Germany	94.5%	9 / 35
Character Frequency Bench	90.9%	9 / 35
Money Boy Cultural Literacy Test	85.7%	2 / 35
Product Recommendations	85.6%	4 / 36
German Memelord Bench	69.7%	1 / 35
Karl Lorey knowlege	26.7%	2 / 36

Price vs Performance

Compare cost efficiency across all models

Current model

Other models

X-axis uses log scale for better visualization of price range

Score Over Time

Performance trends across all benchmark runs

Benchmark Activity

Number of benchmark runs over time

Quickstart

Get started with this model using OpenRouter

View on OpenRouter

import { OpenRouter } from "@openrouter/sdk";

const openrouter = new OpenRouter({
  apiKey: "<OPENROUTER_API_KEY>"
});

const completion = await openrouter.chat.completions.create({
  model: "google/gemini-3-pro-preview",
  messages: [
    {
      role: "user",
      content: "Hello!"
    }
  ]
});

console.log(completion.choices[0].message.content);

Get your API key at openrouter.ai/keys