All Models

Gemini 3.8 Flash

gemini-flashReasoningTool CallingAttachmentsStructured Output

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.

Providers24
ReleasedSep 2, 2026
Input Modalitiestext, image, video, audio, pdf
Output Modalitiestext
Tarsk Usecoding

Benchmarks

41.2
Intelligence Index
76.3
Coding Index

Available Providers (24)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
NanoGPTgoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Vivgridgemini-3.8-flash$0.75/MTok$3.75/MTok1.0M128K
LLM Gatewaygoogle-vertex/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
LLM Gatewaygoogle-ai-studio/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Vertexgemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Requestygemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
CrossModelgemini/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Googlegemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Vercel AI Gatewaygoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1M65.5K
DevPass (LLM Gateway)gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M1.0M
GitHub Copilotgemini-3.8-flash$0.75/MTok$3.75/MTok1M64K
Kilo Gatewaygoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Merge Gatewaygoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
OpenRoutergoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Ofoxgoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1M65.5K
302.AIgemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Eden AIgoogle/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Eden AIvertex/gemini-3.8-flash@eu$0.75/MTok$3.75/MTok1.0M65.5K
Eden AIvertex/gemini-3.8-flash@us$0.75/MTok$3.75/MTok1.0M65.5K
Eden AIvertex/gemini-3.8-flash$0.75/MTok$3.75/MTok1.0M65.5K
Requestygemini-3.8-flash@eu$0.82/MTok$4.13/MTok1.0M65.5K
Cortecsgemini-3.8-flash$0.82/MTok$4.13/MTok1.0M65.5K
Venice AIgemini-3-8-flash$0.94/MTok$4.69/MTok1M65.5K
OpenCode Zengemini-3.8-flash$1.50/MTok$7.50/MTok1.0M65.5K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output