Google

Gemini 3.8 Flash (batch)

by Googletext+image+file+audio+video->text1 endpoint

Overview

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Capabilities

Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Stop sequences
Deterministic seed

Modalities

Input
TextImageVideoFileAudio
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
65.5K tokens
Tokenizer
Gemini

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstool_choicetools

Pricing

Per 1M tokens
Input$0.38
Output$1.88
Cache read$0.04
Cache write$0.04
Audio$0.38
Reasoning$1.88
Image$0.38
Added
September 2, 2026
Last synced 9/16/2026