Gemini 2.5 Flash (Free) vs Gemini 2.5 Flash — AI Model Comparison

Author

Context1.0M

Tool calling

Gemini 2.5 Flash is Google’s high-performance workhorse model, designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in thinking, and a max tokens for reasoning parameter lets you tune its performance.

Tokens, last 14 days

Prompt73M

Completion5.06M

Total78M

Performance

Latency (p50)7.08 s

Throughput (p50)130.2 tok/s

Pricing

InputFree

OutputFree

Cached input—

Features

Inputtext, image, file, audio

Outputtext

APIResponses, Chat Completions, Messages

Vision

Open model page

Author

Google

Context1.0M

Tool calling

Gemini 2.5 Flash is Google’s high-performance workhorse model, designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in thinking, and a max tokens for reasoning parameter lets you tune its performance.

Tokens, last 14 days

Prompt244M

Completion1.39M

Total246M

Performance

Latency (p50)2.05 s

Throughput (p50)179.1 tok/s