/ Models

Language models

Google: Gemini 2.5 Pro

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...

Maker
Google
Context window
1M
Max output
66K
Input / 1M
$1.25
Output / 1M
$10
1M in + 1M out
$11.25

Everything else

Max output66K
Input / 1M$1.25
Output / 1M$10
Cache read / 1M$0.125
Cache write / 1M$0.375
1M in + 1M out$11.25
Takestext, image, file, audio, video
Returnstext
Toolsyes
Reasoningalways on
Open weightsno
Released2025-06-17
Knowledge cutoff2025-01-31
Retires
Catalog idgoogle/gemini-2.5-pro

Benchmarks

sourceepoch
gpqa0.853
gpqaStderr0.0212
sweBenchVerified0.576
sweBenchVerifiedStderr0.0225
frontierMath0.141
frontierMathStderr0.0205
aime0.842
aimeStderr0.0481
simpleQA0.56
simpleQAStderr0.0157

Benchmark scores by Epoch AI, CC BY 4.0.

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models