# Google: Gemini 2.5 Pro (batch)

Provider: google  
Category: llm  
Model ID: `google/gemini-2.5-pro:batch`

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...

## Specs

- Context length: 1048576 tokens
- Max output: 65536 tokens
- Modalities: text, image, file, audio, video
- Released: 2025-06-17

## Pricing

- Input: $0.63 per million tokens
- Output: $5.00 per million tokens

## Verdict

Gemini 2.5 Pro batch mode trades real-time responsiveness for 50% cost savings on both input and output tokens compared to standard Gemini 2.5 Pro. Jobs complete within 24 hours, making this the right choice for high-volume document processing, overnight data analysis, or any workflow where you can queue requests and wait. Skip it if you need sub-second latency or interactive chat — the batch delay kills those use cases.

---
Last verified: 2026-09-04T02:00:56.012Z  
Canonical URL: https://switchy.build/directory/models/gemini-2-5-pro-batch