GGemini 2.5 Pro Preview 05-06API

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.

1MContext window · tokens

$1.25Input price · per M tokens

$10Output price · per M tokens

GoogleProvider

Prices update automatically — checked daily against provider list prices.

$3.44 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
cheaper than 35% of the 192 commercial models tracked here
31 of 34 Google models tracked here, from cheapest

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Gemini 2.5 Pro Preview 05-06, measured by Artificial Analysis. Higher is better. Measurement mode: May' 25.

Intelligence index22.7

GPQA82.2%

MMLU-Pro83.7%

Humanity's Last Exam19.9%

LiveCodeBench77%

SciCode41.6%

MATH-50098.6%

AIME84.3%

💰 Blended price$3.438 / 1M tokens

📈 Value6.6 intelligence points per $

vs. models measured heretop 60%

Scores higher than 40% of the 273 models measured by Artificial Analysis and tracked here.
Models at this level cost $0.76 per 1M tokens (median of 13) — this one costs $3.44.
Cheaper and better on this index: Grok 4.6 · GPT-5.6 Sol (batch) · GLM 5.3 and 108 more

Benchmark data by Artificial Analysis

About this model

Gemini 2.5 Pro Preview 05-06 is a commercial AI model by Google. The specifications below are tracked automatically: pricing is refreshed daily from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is Gemini 2.5 Pro Preview 05-06?

Gemini 2.5 Pro Preview 05-06 is an AI language model from Google. It is a proprietary model, available through an API. It scores 22.7 on the Artificial Analysis intelligence index.

Is Gemini 2.5 Pro Preview 05-06 free?

Gemini 2.5 Pro Preview 05-06 is not free: it costs $1.25 per million input tokens and $10 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

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

Independent benchmarks from Artificial Analysis give it GPQA 82.2%, MMLU-Pro 83.7%, Humanity's Last Exam 19.9%, LiveCodeBench 77%, SciCode 41.6%, MATH-500 98.6%, AIME 84.3%.