modelgrep
G

Google: Gemini 2.5 Pro

google/gemini-2.5-pro

61st smartest of 180ReasoningToolsJSONVisionAudio
Use via OpenRouter ↗
Intelligence
34.6
61st of 180
Design Elo
1290
Data Viz
Speed
102
57th fastest
Latency
1.1s
first token
Input price
$1.25
228th cheapest
Context
1.0M
66K max out

How it compares

Smarter than66%
of all ranked models
Faster than81%
of all ranked models
Cheaper than23%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis63th percentile
Intelligence Index
34.6
Coding Index
32.0
Agentic Index
32.7
GPQA Diamond
84%
Humanity's Last Exam
21%
SciCode
43%
Tau²-Bench (agentic)
54%
Design Arena · Elo3,843 tournaments
Data Viz
1290
Website
1212
codecategories
1206
UI Component
1201
Game Dev
1181
3D
1163

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
Google$1.25$10.0098.6%
Google$1.25$10.0086%
Google AI Studio$1.25$10.0085.3%
Google$1.25$10.00

Specifications

Context window1.0M
Max output66K
Knowledge cutoffJan 2025
Input modalitiestext, image, file, audio, video
Output modalitiestext
Prompt caching
Cache read price$0.125/M
ModeratedNo

Gemini 2.5 Pro FAQ

How much does Gemini 2.5 Pro cost?

Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens via OpenRouter, making it 228th cheapest of 298 paid models.

How smart is Gemini 2.5 Pro?

Gemini 2.5 Pro scores 34.6 on the Artificial Analysis Intelligence Index, ranking 61st of 180 benchmarked models, with a GPQA Diamond score of 84%.

How fast is Gemini 2.5 Pro?

Gemini 2.5 Pro generates around 102 tokens per second with 1.1s time-to-first-token (p50), the 57th fastest tracked model.

What is Gemini 2.5 Pro's context window?

Gemini 2.5 Pro supports a 1.0M-token context window and can output up to 66K tokens. It accepts text, image, file, audio, video input.

Compare head-to-head