Skip to content
Log In
Sign Up
Dashboard

Gemini 3 Pro Preview

Gemini 3 Pro Preview is the flagship reasoning model in the Gemini 3 generation for demanding agentic and analytical tasks, with improvements in multi-step function calling, complex image reasoning, long-document analysis, and instruction following over Gemini 2.5 Pro.

File InputTool UseReasoningVision (Image)Web Searchtiered-costImplicit Caching
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'google/gemini-3-pro-preview',
  prompt: 'Why is the sky blue?'
})
OverviewPlaygroundAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

About Gemini 3 Pro Preview

Gemini 3 Pro Preview is a pro-tier model in the Gemini 3 generation for tasks that demand deep reasoning and reliable multi-step execution. It improves substantially on Gemini 2.5 Pro in four areas: multi-step function calling, planning, reasoning over complex images and long documents, and instruction following. These capabilities determine whether an agent completes a sophisticated task reliably or produces compounding errors across steps.

Its handling of complex images alongside long documents sets it apart for analytical applications. As a reasoning model, Gemini 3 Pro Preview supports includeThoughts output via providerOptions, streaming the intermediate reasoning chain alongside the final response. This transparency helps in regulated or high-stakes applications where you need to audit the decision process. It also helps debug complex agentic workflows where pinpointing where the model went wrong requires more than reading the final answer.