Google

Gemini 2.5 Pro

by Googletext+image+file+audio+video->text7 endpoints
Neura Intelligence Index
53.5/ 100
Rank
#169
Confidence
medium
Benchmarks
7(18% coverage)

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...

Capabilities

Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Stop sequences
Deterministic seed

Modalities

Input
TextImageFileAudioVideo
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
65.5K tokens
Knowledge Cutoff
2025-01-31
Tokenizer
Gemini
Uptime (24h)
10000.0%
Blended Cost
$3.4375/1M tokens
Country
🇺🇸US
Model Family
Gemini 2.5
Release Date
May 20, 20251y

Supported Parameters

include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Benchmark Performance

general

BenchmarkScoreSource
SimpleQA
50.8
verified

coding

BenchmarkScoreSource
SWE-bench Verified
63.2
verified

math

BenchmarkScoreSource
AIME 2025
83
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
83
verified
Humanity's Last Exam
17.8
verified
ARC-AGI v2
4.9
verified

multimodal

BenchmarkScoreSource
MMMU
79.6
verified

Performance Over Time

Pricing

Per 1M tokens
Input$1.25
Output$10.00
Cache read$0.13
Cache write$0.38
Audio$1.25
Reasoning$10.00
Image$1.25
Added
June 17, 2025
Last synced 9/19/2026