All Models

Gemini 2.5 Flash

Reasoning Tool Calling Attachments Structured Output

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).

Providers 18
Released Mar 20, 2025
Input Modalities pdf, image, text, audio, video
Output Modalities text
Tarsk Use coding

Benchmarks

20.6
Intelligence Index
17.8
Coding Index
60.3
Math Index

Available Providers (18)

Provider Model ID Input Cost Output Cost Context Max Output Docs
AIHubMix gemini-2.5-flash $0.07/MTok $0.30/MTok 1M 65K
QiHang gemini-2.5-flash $0.09/MTok $0.71/MTok 1.0M 65.5K
Poe google/gemini-2.5-flash $0.21/MTok $1.80/MTok 1.1M 65.5K
Jiekou.AI gemini-2.5-flash $0.27/MTok $2.25/MTok 1.0M 65.5K
ZenMux google/gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 64K
FastRouter google/gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Perplexity Agent google/gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Abacus gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
OpenRouter google/gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
302.AI gemini-2.5-flash $0.30/MTok $2.50/MTok 1M 65.5K
Vertex gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Google gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
SAP AI Core gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Firmware gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Requesty google/gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Vercel AI Gateway google/gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
NanoGPT gemini-2.5-flash $0.30/MTok $2.50/MTok 1.0M 65.5K
Qiniu gemini-2.5-flash —/MTok —/MTok 1.0M 64K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output