Last updated: 16/04/2025

Google Vertex AIOfficial Docs

Gemini 2.5 Pro Preview 03-25

gemini-2.5-pro-preview-03-25

active

Gemini 2.5 Pro Preview 03-25

Gemini 2.5 Pro is a powerful, versatile AI model capable of handling a wide range of tasks, including text, image, video, audio, transcription, and text-to-speech. With a context window of up to 1,048,576 tokens, it is well-suited for complex, long-form applications. The model supports fine-tuning for custom use cases and can be integrated with various tools for advanced automation.

Supports a 1,048,576 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications. Supports tool use for advanced automation. Capable of generating structured output formats.

Model Timeline

Launch Date

3/25/2025

Capabilities

Text

Input Pricing

$7e-7/ KTok

Context: 1,048,576 tokens

Output Pricing

$0.0000014/ KTok

Max tokens: 8,192

Vision Capabilities

Max resolution: 1080p
Max images per prompt: 16

Image

Input Pricing

1024 tokens/image

Transcription

Transcription Pricing

$1.50/minute

Embeddings

Embeddings Pricing

$0.0001/1k tokens

Fine-Tuning

Fine-Tuning Pricing

$80.00/MTok training

Additional Model Information

Tool Use

Yes

Structured Output

Yes

Reasoning

Yes

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop