Gemini 2.5 Pro

Text Generation
Google DeepMind · gemini-2.5-pro
reasoning long-context coding

Most intelligent Google model with thinking mode and 2M token context

Context Window

2,000,000

tokens

Max Output

8,192

tokens

Input Pricing

$2.50

per million tokens

Output Pricing

$10.00

per million tokens

Core Capabilities

Vision Support
Function Calling
Streaming

Additional Capabilities

Multimodal

Native multimodal understanding

Thinking Mode

Advanced reasoning with thinking mode

Ultra Long Context

2M token context window

Benchmark Scores

Benchmark Score Ranking Date Scored Notes
LMSYS_Elo 1270.00 #5 March 05, 2025
MMLU 88.00 - March 01, 2025
SWE-bench_Verified 40.30 #5 March 01, 2025
TAU-bench_Retail 74.80 #3 March 01, 2025
Released: March 01, 2025