Google: Gemini 2.5 Flash

GoogleID: google/gemini-2.5-flash

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 accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).

Pricing per 1M Tokens

Input (Prompt)$0.30
Output (Completion)$2.50
Cache Read$0.03
Cache Write$0.08
Image$0.30

Specifications

Context Length1.0M
Max Output Tokens66K
Input ModalitiesFile + Image + Text + Audio + Video
Output ModalitiesText
TokenizerGemini
Instruct TypeN/A
Top Provider Context1.0M
Top Provider Max Output66K
ModeratedNo

Compare this model

See how Google: Gemini 2.5 Flash stacks up against other models.

vs Google: Gemini 3.1 Flash Lite Previewvs Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)vs Google: Gemini 3.1 Pro Preview Custom Toolsvs Google: Gemini 3.1 Pro Previewvs Google: Gemini 3 Flash Preview

More from Google

Google: Gemini 3.1 Flash Lite Preview
Input$0.25
Context1.0M
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Input$0.50
Context66K
Google: Gemini 3.1 Pro Preview Custom Tools
Input$2.00
Context1.0M
Google: Gemini 3.1 Pro Preview
Input$2.00
Context1.0M
Google: Gemini 3 Flash Preview
Input$0.50
Context1.0M

Last updated: March 23, 2026

First tracked: March 23, 2026