Google: Gemini 2.5 Flash Preview 09-2025

Image input Audio input Video input Text input File input Text output
Author's Description

Gemini 2.5 Flash Preview September 2025 Checkpoint 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).

Key Specifications
Cost
$$$$
Context
1M
Released
Sep 25, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Reasoning Stop Tools Top P Response Format Tool Choice Temperature Seed Include Reasoning Structured Outputs Max Tokens
Features

This model supports the following features:

Response Format Reasoning Structured Outputs Tools
Performance Summary

Google's Gemini 2.5 Flash Preview 09-2025 demonstrates strong overall performance, particularly excelling in speed, consistently ranking in the top tier (72nd percentile) across benchmarks. Its pricing is moderate, positioned at the 33rd percentile. A standout feature is its exceptional reliability, achieving a perfect 100% success rate, indicating minimal technical failures and consistent response delivery. The model exhibits significant strengths in specialized areas. It achieves perfect accuracy in both General Knowledge and Ethics, often being the most accurate model at its price point and speed. Its instruction following capabilities are highly proficient (90th percentile accuracy), and it performs very well in Mathematics (87th percentile accuracy) and Reasoning (81st percentile accuracy), aligning with its design for advanced tasks. Coding performance is solid at 66th percentile accuracy. A notable weakness is its performance in handling hallucinations, where it only achieved 88.0% accuracy, placing it in the 32nd percentile for appropriately acknowledging uncertainty. Despite this, its overall profile suggests a powerful tool for complex analytical and generative tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.3
Completion $2.5
Input Cache Read $0.075
Input Cache Write $0.383

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Google AI Studio
Google AI Studio | google/gemini-2.5-flash-preview-09-2025 1M $0.3 / 1M tokens $2.5 / 1M tokens
Google
Google | google/gemini-2.5-flash-preview-09-2025 1M $0.3 / 1M tokens $2.5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by google