Google logo

Gemini 2.5 Pro Preview 06-05: Pricing, Context Window & Benchmarks

by Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

Input Price
$1.25/1M tokens
Output Price
$10.00/1M tokens
Intelligence
34.5
Coding
31.9

What you can do with Gemini 2.5 Pro Preview 06-05

Everyday Q&A and clear explanations

Writing help (emails, posts, summaries)

Idea generation and brainstorming

Learning support with step-by-step guidance

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Benchmark Highlights

6 tests
GPQA
84.4%
MMLU Pro
86.2%
LiveCodeBench
80.1%
Math 500
96.7%
AIME 2025
87.7%
HLE
21.1%
Metric Value
Provider Google
Context Window 1,048,576 tokens
Input Price $1.25/1M tokens
Output Price $10.00/1M tokens
Release Date Jun 5, 2025
Modalities file, image, text, audio
Capabilities Vision, Audio Input

Compare Gemini 2.5 Pro Preview 06-05 to other models

See how it stacks up on price, quality, and overall performance.

Frequently asked questions

What is Gemini 2.5 Pro Preview 06-05 good for?

Use Gemini 2.5 Pro Preview 06-05 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Gemini 2.5 Pro Preview 06-05 cost?

Pricing is based on usage. Current rates are $1.25/1M tokens for input and $10.00/1M tokens for output.

Can I try Gemini 2.5 Pro Preview 06-05 for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Gemini 2.5 Pro Preview 06-05 support images or audio?

Gemini 2.5 Pro Preview 06-05 can understand images.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.