Gemini 3.5 Flash vs Gemini 2.5 Flash
Compare Gemini 3.5 Flash and Gemini 2.5 Flash on key metrics including price, context length, throughput, and other model features.
AuthorGoogle
Context Length1.0M
Supports Tools
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.
Activity
Last 14 daysPrompt
268MCompletion
6MTotal
274MStartup
Startup
Latency (p50)2.90s
Throughput (p50)107.3 tok/s
Pricing
Input$0.75/M tokens
Output$4.00/M tokens
Cached input$0.07/M tokens
Features
Input Modalitiestext, image, audio, file
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools
AuthorGoogle
Context Length1.0M
Supports Tools
Gemini 2.5 Flash is Google’s high-performance workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. Includes built-in "thinking" capabilities and is configurable through a "max tokens for reasoning" parameter for fine-tuned performance.
Activity
Last 14 daysPrompt
107MCompletion
29MTotal
136MStartup
Startup
Latency (p50)1.05s
Throughput (p50)116.7 tok/s
Pricing
Input$0.15/M tokens
Output$1.25/M tokens
Cached input-
Features
Input Modalitiestext, image, file, audio
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools