# Google: Gemini 2.5 Flash (batch)

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

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

## Specs

- Context length: 1048576 tokens
- Max output: 65535 tokens
- Modalities: file, image, text, audio, video
- Released: 2025-06-17

## Pricing

- Input: $0.15 per million tokens
- Output: $1.25 per million tokens

## Verdict

Gemini 2.5 Flash batch mode trades real-time response for aggressive cost reduction — $0.15/Mtok input makes it the cheapest multimodal option from a major vendor. Context window matches the full 1M tokens of the synchronous version, and you get the same vision, audio, and video capabilities. The catch: batch jobs queue and complete on Google's schedule, typically within hours. Reach for this when you're processing large document sets, video archives, or image collections where latency doesn't matter and budget does.

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